id stringlengths 1 3 | all_gold stringlengths 2 376 | raw_text stringlengths 20 472 | messages listlengths 3 3 |
|---|---|---|---|
0 | {"ALGORITHM": ["naive Bayes classifier", "Gaussian mixture model", "variational autoencoders"]} | Typical generative model approaches include naive Bayes classifier s, Gaussian mixture model s, variational autoencoders and others. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
1 | {"CONFERENCE": ["ELRA", "LREC", "International Language Resources and Evaluation Conference"]} | Finally, every other year, ELRA organizes a major conference LREC, the International Language Resources and Evaluation Conference. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
2 | {"ALGORITHM": ["maximum likelihood estimate", "HMM"]} | The task is usually to derive the maximum likelihood estimate of the parameters of the HMM given the of output sequences. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
3 | {"ALGORITHM": ["neural network", "Support vector machine", "AdaBoost"]} | Unlike neural network s and Support vector machine, the AdaBoost training process selects only those features known to improve the predictive power of the model, reducing dimensionality and potentially improving execution time as irrelevant features need not be computed. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
4 | {"MISC": ["Troponymy", "semantic network"], "PRODUCT": ["WordNet database"]} | Troponymy is one of the possible relations between verb s in the semantic network of the WordNet database. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
5 | {"TASK": ["knowledge representation"], "FIELD": ["artificial intelligence"]} | A frame language is a technology used for knowledge representation in artificial intelligence. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
6 | {"METRICS": ["NIST", "Bilingual evaluation understudy"], "MISC": ["brevity penalty"]} | NIST also differs from Bilingual evaluation understudy in its calculation of the brevity penalty insofar as small variations in translation length do not impact the overall score as much. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
7 | {"ALGORITHM": ["neural net", "naive Bayes classifier", "gradient descent", "stochastic gradient descent"], "FIELD": ["supervised learning"]} | The model is initially fit on a training dataset, The model (e.g. a neural net or a naive Bayes classifier) is trained on the training dataset using a supervised learning method, for example using optimization methods such as gradient descent or stochastic gradient descent. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
8 | {"PRODUCT": ["FrameNet"], "TASK": ["question answering", "paraphrasing", "recognizing textual entailment", "information extraction", "Semantic Role Labeling"]} | FrameNet has been used in applications like question answering, paraphrasing, recognizing textual entailment, and information extraction, either directly or by means of Semantic Role Labeling tools. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
9 | {"FIELD": ["data analysis", "statistical analysis"], "MISC": ["spreadsheets", "databases", "generalized audit software", "business intelligence"], "PRODUCT": ["Excel", "Access", "SAS", "ACL", "Arbutus", "EAS", "Crystal Reports", "Business Objects"]} | This would include programs such as data analysis and extraction tools, spreadsheets (e.g. Excel), databases (e.g. Access), statistical analysis (e.g. SAS), generalized audit software (e.g. ACL, Arbutus, EAS), business intelligence (e.g. Crystal Reports and Business Objects), etc. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
10 | {"ORGANISATION": ["Rethink Robotics", "iRobot"], "RESEARCHER": ["Rodney Brooks"], "PRODUCT": ["Baxter", "industrial robot"]} | Rethink Robotics - founded by Rodney Brooks, previously with iRobot - introduced Baxter in September 2012; as an industrial robot designed to safely interact with neighboring human workers, and be programmable for performing simple tasks. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
11 | {"FIELD": ["text mining"], "TASK": ["text categorization", "text clustering", "concept / entity extraction", "production of granular taxonomies", "sentiment analysis", "document summarization", "entity relation modeling", "named entity recognition"]} | Typical text mining tasks include text categorization, text clustering, concept / entity extraction, production of granular taxonomies, sentiment analysis, document summarization, and entity relation modeling (i.e., learning relations between named entity recognition). | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
12 | {"METRICS": ["precision", "TRUE negative rate"]} | Nonetheless, stemming reduces precision, or TRUE negative rate, for such systems. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
13 | {"TASK": ["keyword spotting"], "MISC": ["wake word", "hot word"], "PRODUCT": ["Alexa", "Siri"]} | A special case of keyword spotting is wake word (also called hot word) detection used by personal digital assistants such as Alexa or Siri to wake up when their name is spoken. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
14 | {"PROGRAMMING_LANGUAGE": ["Prova", "Prolog", "Java"]} | Prova is an open source programming language that combines Prolog with Java. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
15 | {"ORGANISATION": ["Tocibai Machine", "Toshiba", "CoCom"], "PRODUCT": ["CNC milling"], "COUNTRY": ["Soviet Union"], "MISC": ["COMECON"]} | In 1987, Tocibai Machine, a subsidiary of Toshiba, was accused of illegally selling CNC milling s used to produce very quiet submarine propellers to the Soviet Union in violation of the CoCom agreement, an international embargo on certain countries to COMECON countries. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
16 | {"RESEARCHER": ["Engelberger"], "PRODUCT": ["Unimate industrial robotic arm"], "LOCATION": ["Robot Hall of Fame"]} | Engelberger's most famous co-invention, the Unimate industrial robotic arm, was among the first inductees into the Robot Hall of Fame in 2003. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
17 | {"MISC": ["static html", "CGI"], "PERSON": ["Dalton"], "FIELD": ["augmented reality"], "PROGRAMMING_LANGUAGE": ["Java"]} | Originally controlled via static html web pages using CGI, work by Dalton saw the introduction of an augmented reality Java -based interface that met with limited success. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
18 | {"TASK": ["LMF specification"], "ORGANISATION": ["ISO"], "CONFERENCE": ["LREC", "LREC"]} | The first publication about the LMF specification as it has been ratified by ISO (this paper became (in 2015) the 9th most cited paper within the LREC conferences from LREC papers): | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
19 | {"METRICS": ["confusion matrix", "accuracy"], "ALGORITHM": ["k -NN classification"]} | A confusion matrix or matching matrix is often used as a tool to validate the accuracy of k -NN classification. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
20 | {"ALGORITHM": ["Decision tree"], "FIELD": ["statistics", "data mining", "machine learning"]} | Decision tree learning is one of the predictive modeling approaches used in statistics, data mining and machine learning. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
21 | {"MISC": ["prosody"], "FIELD": ["signal processing"], "ALGORITHM": ["linear predictive coding", "PSOLA"]} | At runtime, the target prosody of a sentence is superimposed on these minimal units by means of signal processing techniques such as linear predictive coding, PSOLA | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
22 | {"FIELD": ["artificial intelligence", "machine learning"], "TASK": ["facial imagery"]} | This approach utilized artificial intelligence and machine learning to allow researchers to visibly compare conventional and thermal facial imagery. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
23 | {"FIELD": ["computer science", "artificial intelligence", "soft computing"], "ALGORITHM": ["evolutionary computation"], "TASK": ["global optimization"], "MISC": ["biological evolution"]} | In computer science, evolutionary computation is a family of algorithms for global optimization inspired by biological evolution, and the subfield of artificial intelligence and soft computing studying these algorithms. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
24 | {"METRICS": ["confusion matrix", "mean squared error"]} | For instance, one can combine some measure based on the confusion matrix with the mean squared error evaluated between the raw model outputs and the actual values. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
25 | {"PRODUCT": ["word2vec model", "word2vec"], "RESEARCHER": ["Mikolov"]} | The majority are results of the word2vec model developed by Mikolov et al or variants of word2vec. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
26 | {"CONFERENCE": ["CVPR", "International Conference on Computer Vision", "ICCV"]} | It was during this time that a total of 43 publications were recognized by the CVPR and the International Conference on Computer Vision (ICCV). | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
27 | {"PRODUCT": ["AIBO"], "FIELD": ["artificial intelligence", "Computer vision"]} | The AIBO has seen much use as an inexpensive platform for artificial intelligence education and research, because integrates a computer, Computer vision, and articulators in a package vastly cheaper than conventional research robots. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
28 | {"CONFERENCE": ["International Conference on Computer Vision 2021"]} | She served as Program Chair of International Conference on Computer Vision 2021. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
29 | {"RESEARCHER": ["Scheinman"], "ORGANISATION": ["Unimation", "Unimation", "General Motors"], "PRODUCT": ["Programmable Universal Machine for Assembly", "PUMA"]} | Scheinman, after receiving a fellowship from Unimation to develop his designs, sold those designs to Unimation who further developed them with support from General Motors and later marketed it as the Programmable Universal Machine for Assembly (PUMA). | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
30 | {"TASK": ["binary classification", "multiclass classification classification tasks"], "RESEARCHER": ["Gebel"]} | An overview of calibration methods for binary classification and multiclass classification classification tasks is given by Gebel (2009) | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
31 | {"TASK": ["optical character recognition", "OCR", "speech synthesis", "speech recognition"]} | He is involved in fields such as optical character recognition (OCR), speech synthesis, speech recognition technology, and electronic keyboard instruments. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
32 | {"PRODUCT": ["Kaldi toolkit"]} | For more recent and state-of-the-art techniques, Kaldi toolkit can be used. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
33 | {"RESEARCHER": ["Johnson-Laird", "William James"], "ORGANISATION": ["American Philosophical Society", "Royal Society", "British Academy", "Association for Psychological Science", "Cognitive Science Society"]} | Johnson-Laird is a Fellow of the American Philosophical Society, a Fellow of the Royal Society, a Fellow of the British Academy, a William James Fellow of the Association for Psychological Science, and a Fellow of the Cognitive Science Society. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
34 | {"CONFERENCE": ["IEEE International Conference on Image Processing"], "RESEARCHER": ["Rui Hu", "Mark Banard", "John Collomosse"], "ALGORITHM": ["HOG descriptor"], "TASK": ["sketch based image retrieval", "SBIR"]} | At the IEEE International Conference on Image Processing in 2010, Rui Hu, Mark Banard, and John Collomosse extended the HOG descriptor for use in sketch based image retrieval (SBIR). | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
35 | {"METRICS": ["BLEU", "precision"]} | BLEU uses a modified form of precision to compare a candidate translation against multiple reference translations. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
36 | {"METRICS": ["relative entropy"]} | For the case of a general base space math (Y,\ mathcal {B},\ nu) / math (i.e. a base space which is not countable), one typically considers the relative entropy. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
37 | {"COUNTRY": ["United States", "United Kingdom", "Mexico"], "ORGANISATION": ["National Park Service", "NPS", "Historic Scotland", "HS", "World Monuments Fund", "Instituto Nacional de Antropología y Historia", "INAH"], "MISC": ["CyArk", "website"]} | As of October 2011, the already-existing partnerships with the United States' National Park Service (NPS), the United Kingdom's Historic Scotland (HS), World Monuments Fund, and Mexico's Instituto Nacional de Antropología y Historia (INAH) had been greatly expanded,, CyArk website | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
38 | {"ALGORITHM": ["Kernel SVMs"], "FIELD": ["machine-learning"], "PRODUCT": ["LIBSVM", "MATLAB"]} | Kernel SVMs are available in many machine-learning toolkits, including LIBSVM, MATLAB, and others. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
39 | {"MISC": ["Loebner Prize Competition"], "LOCATION": ["Brighton Centre", "Brighton"], "COUNTRY": ["UK"], "CONFERENCE": ["Interspeech 2009 conference"]} | The 2009 Loebner Prize Competition was held September 6, 2009 at the Brighton Centre, Brighton UK in conjunction with the Interspeech 2009 conference. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
40 | {"PRODUCT": ["QRIO robot", "AIBO", "R-CODE", "Aperios operating system"]} | The humanoid QRIO robot was designed as the successor to AIBO, and runs the same base R-CODE Aperios operating system. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
41 | {"MISC": ["Speech waveforms"], "ALGORITHM": ["HMMs", "maximum likelihood"]} | Speech waveforms are generated from HMMs themselves based on the maximum likelihood criterion. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
42 | {"PRODUCT": ["Google Translate", "Google"], "TASK": ["multilingual statistical machine translation", "neural machine translation"]} | Google Translate is a free multilingual statistical machine translation and neural machine translation service developed by Google, to translate text and websites from one language into another. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
43 | {"FIELD": ["computer vision", "image analysis", "pattern recognition", "digital image processing"], "TASK": ["optical character recognition", "fingerprint recognition", "visual inspection or compression"]} | Skeletons are widely used in computer vision, image analysis, pattern recognition and digital image processing for purposes such as optical character recognition, fingerprint recognition, visual inspection or compression. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
44 | {"CONFERENCE": ["ImageNet Large Scale Visual Recognition Challenge"], "TASK": ["object classification and detection"]} | The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object classification and detection, with millions of images and hundreds of object classes. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
45 | {"RESEARCHER": ["Bengio", "Geoffrey Hinton", "Yann LeCun"], "MISC": ["Godfathers of AI", "Godfathers of Deep Learning"]} | Bengio, together with Geoffrey Hinton and Yann LeCun, are referred to by some as the Godfathers of AI and Godfathers of Deep Learning. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
46 | {"ORGANISATION": ["IEEE"]} | He is a Life Fellow of IEEE. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
47 | {"ORGANISATION": ["NSA Bethesda", "Walter Reed National Military Medical Center"]} | NSA Bethesda is responsible for base operational support for its major tenant, the Walter Reed National Military Medical Center. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
48 | {"FIELD": ["supervised learning", "unsupervised learning", "reinforcement learning"]} | The three major learning paradigms are supervised learning, unsupervised learning and reinforcement learning. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
49 | {"TASK": ["control", "planning and scheduling", "answer diagnostic and consumer questions", "handwriting recognition", "natural language understanding", "speech recognition", "facial recognition"]} | Examples include control, planning and scheduling, the ability to answer diagnostic and consumer questions, handwriting recognition, natural language understanding, speech recognition and facial recognition. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
50 | {"CONFERENCE": ["Association for the Advancement of Artificial Intelligence"]} | In 1991 he was elected as a fellow of the Association for the Advancement of Artificial Intelligence (1990, founding fellow). | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
51 | {"MISC": ["Toeplitz matrix"], "ALGORITHM": ["Levinson recursion"], "METRICS": ["mean squared error"]} | However, by formulating the problem as the solution of a Toeplitz matrix and using Levinson recursion, we can relatively quickly estimate a filter with the smallest mean squared error possible. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
52 | {"CONFERENCE": ["15th edition of Campus Party Spain"], "LOCATION": ["City of Arts and Sciences", "Valencia"]} | In July 2011 the 15th edition of Campus Party Spain will be held at the City of Arts and Sciences in Valencia. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
53 | {"PRODUCT": ["chess", "go"]} | Often this is generally only possible at the very end of complicated games such as chess or go, since it is not computationally feasible to look ahead as far as the completion of the game, except towards the end, and instead, positions are given finite values as estimates of the degree of belief that they will lead to ... | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
54 | {"ALGORITHM": ["multinomial logit model", "perceptron algorithm", "support vector machine", "linear discriminant analysis"]} | The difference between the multinomial logit model and numerous other methods, models, algorithms, etc. with the same basic setup (the perceptron algorithm, support vector machine s, linear discriminant analysis, etc. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
55 | {"CONFERENCE": ["Association for Computational Linguistics"]} | Association for Computational Linguistics, published by | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
56 | {"PRODUCT": ["Facial recognition system"]} | In computerised Facial recognition system, each face is represented by a large number of pixel values. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
57 | {"PERSON": ["Daniel Pearl", "Judea"], "ORGANISATION": ["Wall Street Journal", "Daniel Pearl Foundation"], "COUNTRY": ["Pakistan"]} | In 2002, his son, Daniel Pearl, a journalist working for the Wall Street Journal was kidnapped and murdered in Pakistan, leading Judea and the other members of the family and friends to create the Daniel Pearl Foundation. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
58 | {"ORGANISATION": ["Red Envelope Entertainment"], "PERSON": ["John Waters"]} | As of late 2006, Red Envelope Entertainment also expanded into producing original content with filmmakers such as John Waters. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
59 | {"ORGANISATION": ["Beth Israel Deaconess Medical Center"]} | The building is now part of the Beth Israel Deaconess Medical Center. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
60 | {"FIELD": ["artificial intelligence"], "TASK": ["knowledge representation"]} | A common theme of this work is the adoption of a sign-theoretic perspective on issues of artificial intelligence and knowledge representation. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
61 | {"TASK": ["neural machine translation", "NMT", "machine translation", "word alignment", "language modeling", "statistical machine translation", "SMT"]} | For instance, the term neural machine translation (NMT) emphasizes the fact that deep learning-based approaches to machine translation directly learn sequence-to-sequence transformations, obviating the need for intermediate steps such as word alignment and language modeling that was used in statistical machine translat... | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
62 | {"FIELD": ["WSD"], "PRODUCT": ["WordNet"]} | Most research in the field of WSD is performed by using WordNet as a reference sense inventory for. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
63 | {"MISC": ["PhD"], "RESEARCHER": ["Richard Zemel", "Zoubin Ghahramani"]} | Notable former PhD students and postdoctoral researchers from his group include Richard Zemel, and Zoubin Ghahramani. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
64 | {"METRICS": ["confusion matrix", "ROC"]} | Each prediction result or instance of a confusion matrix represents one point in the ROC space. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
65 | {"RESEARCHER": ["Thrun", "Wolfram Burgard", "Dieter Fox"], "PRODUCT": ["robotic tour guide"], "LOCATION": ["Deutsches Museum Bonn"]} | In 1997 Thrun and his colleagues Wolfram Burgard and Dieter Fox developed the world's first robotic tour guide in the Deutsches Museum Bonn (1997). | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
66 | {"PRODUCT": ["WordNet"], "MISC": ["semantic relation"], "FIELD": ["natural language processing", "artificial intelligence"]} | WordNet is a lexical database of semantic relation s between word s in more than 200 languages. its primary use is in automatic natural language processing and artificial intelligence applications. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
67 | {"FIELD": ["natural language processing", "speech processing"], "CONFERENCE": ["Association for Computational Linguistics", "North American Chapter of the Association for Computational Linguistics", "EMNLP", "HLT"]} | Conferences in the field of natural language processing, such as Association for Computational Linguistics, North American Chapter of the Association for Computational Linguistics, EMNLP, and HLT, are beginning to include papers on speech processing. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
68 | {"PROGRAMMING_LANGUAGE": ["Java"], "MISC": ["parts of speech", "electronic medical record"]} | A set of Java programs use the lexicon to work through the variations in biomedical texts by relating words by their parts of speech, which can be helpful in web searches or searches through an electronic medical record. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
69 | {"ALGORITHM": ["LPBoost", "TotalBoost", "BrownBoost", "xgboost", "MadaBoost"]} | There are many more recent algorithms such as LPBoost, TotalBoost, BrownBoost, xgboost, MadaBoost,, and others. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
70 | {"PROGRAMMING_LANGUAGE": ["Python"]} | This is an example implementation in Python: | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
71 | {"PRODUCT": ["Mattel", "Intellivision"], "TASK": ["Intellivoice Voice Synthesis"]} | The Mattel Intellivision game console offered the Intellivoice Voice Synthesis module in 1982. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
72 | {"TASK": ["machine translation", "high-accuracy knowledge-based MT", "Statistical machine translation", "generalized example-based MT"], "FIELD": ["machine learning"]} | He also worked on machine translation, both high-accuracy knowledge-based MT and machine learning for Statistical machine translation (such as generalized example-based MT). | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
73 | {"ORGANISATION": ["Wolfram Mathematica", "Mathematica"], "ALGORITHM": ["neural networks"], "FIELD": ["machine learning", "image processing", "geometry", "data science", "visualizations"]} | Wolfram Mathematica (usually termed Mathematica) is a modern technical computing system spanning most areas of technical - including neural networks, machine learning, image processing, geometry, data science, visualizations, and others. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
74 | {"PRODUCT": ["digitally operated and programmable robot", "Unimate"], "RESEARCHER": ["George Devol"]} | The first digitally operated and programmable robot was invented by George Devol in 1954 and was ultimately called the Unimate. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
75 | {"ALGORITHM": ["DBNs", "DBMs"], "TASK": ["Object recognition", "speech recognition"]} | Like DBNs, DBMs can learn complex and abstract internal representations of the input in tasks such as Object recognition or speech recognition, using limited, labeled data to fine-tune the representations built using a large set of unlabeled sensory input data. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
76 | {"TASK": ["vision based activity recognition"], "CONFERENCE": ["ICCV", "CVPR"]} | Scientific conferences where vision based activity recognition work often appears are ICCV and CVPR. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
77 | {"FIELD": ["statistics"], "ALGORITHM": ["expectation-maximization", "EM"], "METRICS": ["maximum likelihood", "maximum a posteriori", "MAP"], "MISC": ["latent variable"]} | In statistics, an expectation-maximization (EM) algorithm is an iterative method to find maximum likelihood or maximum a posteriori (MAP) estimates of parameter s in statistical model s, where the model depends on unobserved latent variable s. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
78 | {"METRICS": ["FALSE Positive Rate", "FPR", "FALSE Negative Rate", "FNR"]} | Similarly, investigators sometimes report the FALSE Positive Rate (FPR) as well as the FALSE Negative Rate (FNR). | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
79 | {"METRICS": ["signal to noise ratio", "confusion matrix"], "FIELD": ["sciences", "artificial intelligence"]} | The concept is similar to the signal to noise ratio used in the sciences and confusion matrix used in artificial intelligence. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
80 | {"FIELD": ["Human Augmentation"], "RESEARCHER": ["Steve Mann", "Ray Kurzweil", "Marvin Minsky"], "CONFERENCE": ["Virtual Reality Toronto conference"]} | The Code of Ethics on Human Augmentation, which was originally introduced by Steve Mann in 2004 and refined with Ray Kurzweil and Marvin Minsky in 2013, was ultimately ratified at the Virtual Reality Toronto conference on June 25, 2017. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
81 | {"PERSON": ["Walter R. Booth", "Cecil Hepworth"], "ORGANISATION": ["U.K. Kinoplastikon"]} | In 1913, Walter R. Booth directed 10 films for the U.K. Kinoplastikon, presumably in collaboration with Cecil Hepworth. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
82 | {"LOCATION": ["Chicago", "Cow Palace"]} | They introduced their new robot in 1961 at a trade show at Chicago's Cow Palace. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
83 | {"PRODUCT": ["chatbot"], "TASK": ["word-classification"], "FIELD": ["natural language processing", "Artificial intelligence"]} | While some chatbot applications use extensive word-classification processes, natural language processing processors, and sophisticated Artificial intelligence, others simply scan for general keywords and generate responses using common phrases obtained from an associated library or database. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
84 | {"PRODUCT": ["WaveNet"]} | The WaveNet model proposed in 2016 achieves great performance on speech quality. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
85 | {"PRODUCT": ["ALE"], "MISC": ["Emergency management", "disaster relief", "ordinary communication", "extraordinary situation response"], "ORGANISATION": ["American Red Cross", "FEMA", "Disaster Medical Assistance Team", "NATO", "Federal Bureau of Investigation", "United Nations", "AT & T", "Civil Air Patrol", "ARES"]} | Organizations known to use ALE for Emergency management, disaster relief, ordinary communication or extraordinary situation response: American Red Cross, FEMA, Disaster Medical Assistance Team s, NATO, Federal Bureau of Investigation, United Nations, AT & T, Civil Air Patrol, (ARES). | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
86 | {"ALGORITHM": ["Kronecker delta", "sigmoid function"]} | Here, the Kronecker delta is used for simplicity (cf. the derivative of a sigmoid function, being expressed via the function itself). | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
87 | {"RESEARCHER": ["Ray Solomonoff", "Samuel Rathmanner", "Marcus Hutter"]} | The theory is based in philosophical foundations, and was founded by Ray Solomonoff around 1960. Samuel Rathmanner and Marcus Hutter. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
88 | {"PRODUCT": ["WordNet"], "MISC": ["semantic network", "psycholinguistic principles"]} | WordNet, a freely available database originally designed as a semantic network based on psycholinguistic principles, was expanded by addition of definitions and is now also viewed as a dictionary. | [
{
"role": "system",
"content": "You are a precise biomedical Named Entity Recognition (NER) assistant.\n\nYou will receive:\n- a TEXT (a sentence or short passage from biomedical literature);\n- a list of ENTITY TYPES (uppercase labels, e.g. \"DRUG\", \"PROCESS\").\n\nYour task: for every entity type in the... |
CrossNER Evaluation Subsets (First-Phase Protocol)
Part of the code, data and models of the bachelor thesis Structuring Universal Chain-of-thought for Named Entity Recognition (Department of Computer Science and Engineering, University of Bologna, 2026). All the repositories cited by name belong to the same organization.
The five CrossNER target domains (DFKI-SLT/cross_ner,
Liu et al., 2021) in exactly the format of bioner-eval-subset, so the same
evaluation code scores them: same system and user prompt, same construction of the requested types
(up to 6: a random number of the row's present types plus absent distractors drawn with inverse
frequency from the domain's train split), plus raw_text and all_gold.
| Config | Rows (full test set) |
|---|---|
crossner_ai |
431 |
crossner_literature |
416 |
crossner_music |
465 |
crossner_politics |
651 |
crossner_science |
543 |
- Labels converted to the evaluation's UPPER_SNAKE style (
programlang→PROGRAMMING_LANGUAGE,musicalartist→MUSICAL_ARTIST, ...). miscis never requested and is not in the prompt gold (as in UniversalNER's benchmark); its spans remain inall_goldunderMISC.- The system prompt is the benchmarks' one verbatim (it mentions biomedical text), so the dataset is the only thing that changes with respect to the biomedical evaluation.
Built with 04_evaluation/build_crossner_eval.py. The second phase of the project uses a different query protocol on the same sentences (all gold types plus 1-3 distractors): see free-vs-structured-cot-eval.
- Downloads last month
- 48