Spaces:
Running
Running
Add description to card metadata (#1)
Browse files- Add description to card metadata (2190d2ee0e59582fc2c13cbaaa4ebe5d3282fb70)
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
-
title:
|
3 |
-
emoji: 🤗
|
4 |
colorFrom: blue
|
5 |
colorTo: red
|
6 |
sdk: gradio
|
@@ -8,10 +8,10 @@ sdk_version: 3.0.2
|
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
tags:
|
11 |
-
- evaluate
|
12 |
-
- metric
|
|
|
13 |
---
|
14 |
-
|
15 |
## Metric description
|
16 |
|
17 |
CoVal is a coreference evaluation tool for the [CoNLL](https://huggingface.co/datasets/conll2003) and [ARRAU](https://catalog.ldc.upenn.edu/LDC2013T22) datasets which implements of the common evaluation metrics including MUC [Vilain et al, 1995](https://aclanthology.org/M95-1005.pdf), B-cubed [Bagga and Baldwin, 1998](https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.34.2578&rep=rep1&type=pdf), CEAFe [Luo et al., 2005](https://aclanthology.org/H05-1004.pdf), LEA [Moosavi and Strube, 2016](https://aclanthology.org/P16-1060.pdf) and the averaged CoNLL score (the average of the F1 values of MUC, B-cubed and CEAFe).
|
|
|
1 |
---
|
2 |
+
title: null
|
3 |
+
emoji: 🤗
|
4 |
colorFrom: blue
|
5 |
colorTo: red
|
6 |
sdk: gradio
|
|
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
tags:
|
11 |
+
- evaluate
|
12 |
+
- metric
|
13 |
+
description: "CoVal is a coreference evaluation tool for the CoNLL and ARRAU datasets which\nimplements of the common evaluation metrics including MUC [Vilain et al, 1995],\nB-cubed [Bagga and Baldwin, 1998], CEAFe [Luo et al., 2005],\nLEA [Moosavi and Strube, 2016] and the averaged CoNLL score\n(the average of the F1 values of MUC, B-cubed and CEAFe)\n[Denis and Baldridge, 2009a; Pradhan et al., 2011].\n\nThis wrapper of CoVal currently only work with CoNLL line format:\nThe CoNLL format has one word per line with all the annotation for this word in column separated by spaces:\nColumn\tType\tDescription\n1\tDocument ID\tThis is a variation on the document filename\n2\tPart number\tSome files are divided into multiple parts numbered as 000, 001, 002, ... etc.\n3\tWord number\n4\tWord itself\tThis is the token as segmented/tokenized in the Treebank. Initially the *_skel file contain the placeholder [WORD] which gets replaced by the actual token from the Treebank which is part of the OntoNotes release.\n5\tPart-of-Speech\n6\tParse bit\tThis is the bracketed structure broken before the first open parenthesis in the parse, and the word/part-of-speech leaf replaced with a *. The full parse can be created by substituting the asterix with the \"([pos] [word])\" string (or leaf) and concatenating the items in the rows of that column.\n7\tPredicate lemma\tThe predicate lemma is mentioned for the rows for which we have semantic role information. All other rows are marked with a \"-\"\n8\tPredicate Frameset ID\tThis is the PropBank frameset ID of the predicate in Column 7.\n9\tWord sense\tThis is the word sense of the word in Column 3.\n10\tSpeaker/Author\tThis is the speaker or author name where available. Mostly in Broadcast Conversation and Web Log data.\n11\tNamed Entities\tThese columns identifies the spans representing various named entities.\n12:N\tPredicate Arguments\tThere is one column each of predicate argument structure information for the predicate mentioned in Column 7.\nN\tCoreference\tCoreference chain information encoded in a parenthesis structure.\nMore informations on the format can be found here (section \"*_conll File Format\"): http://www.conll.cemantix.org/2012/data.html\n\nDetails on the evaluation on CoNLL can be found here: https://github.com/ns-moosavi/coval/blob/master/conll/README.md\n\nCoVal code was written by @ns-moosavi.\nSome parts are borrowed from https://github.com/clarkkev/deep-coref/blob/master/evaluation.py\nThe test suite is taken from https://github.com/conll/reference-coreference-scorers/\nMention evaluation and the test suite are added by @andreasvc.\nParsing CoNLL files is developed by Leo Born."
|
14 |
---
|
|
|
15 |
## Metric description
|
16 |
|
17 |
CoVal is a coreference evaluation tool for the [CoNLL](https://huggingface.co/datasets/conll2003) and [ARRAU](https://catalog.ldc.upenn.edu/LDC2013T22) datasets which implements of the common evaluation metrics including MUC [Vilain et al, 1995](https://aclanthology.org/M95-1005.pdf), B-cubed [Bagga and Baldwin, 1998](https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.34.2578&rep=rep1&type=pdf), CEAFe [Luo et al., 2005](https://aclanthology.org/H05-1004.pdf), LEA [Moosavi and Strube, 2016](https://aclanthology.org/P16-1060.pdf) and the averaged CoNLL score (the average of the F1 values of MUC, B-cubed and CEAFe).
|