Upload 5 files

app.py

@@ -2,12 +2,46 @@ import gradio as gr
 from description import *
 
 from reference_string_parsing import *
-from summarization import *
-from dataset_extraction import *
+from controlled_summarization import *
 
 with gr.Blocks(css="#htext span {white-space: pre-line}") as demo:
     gr.Markdown("# Gradio Demo for SciAssist")
     with gr.Tabs():
+
+        # Controlled Summarization
+        with gr.TabItem("Summarization"):
+
+            with gr.Box():
+                gr.Markdown(ctrlsum_file_md)
+                with gr.Row():
+                    with gr.Column():
+                        ctrlsum_file = gr.File(label="Input File")
+                        ctrlsum_str = gr.TextArea(label="Input String")
+                        with gr.Column():
+                            gr.Markdown("* Length 0 will exert no control over length.")
+                            # ctrlsum_file_beams = gr.Number(label="Number of beams for beam search", value=1, precision=0)
+                            # ctrlsum_file_sequences = gr.Number(label="Number of generated summaries", value=1, precision=0)
+                            ctrlsum_file_length = gr.Slider(0,300,step=50, label="Length")
+                            ctrlsum_file_keywords = gr.Textbox(label="Keywords",max_lines=1)
+                        with gr.Row():
+                            ctrlsum_file_btn = gr.Button("Generate")
+                    ctrlsum_file_output = gr.Textbox(
+                        elem_id="htext",
+                        label="Summary",
+                    )
+                ctrlsum_file_examples = gr.Examples(examples=[["examples/BERT_body.txt", 100, "", ""],["examples/BERT_paper.pdf", 0, "BERT"]],
+                                                inputs=[ctrlsum_file, ctrlsum_file_length, ctrlsum_file_keywords])
+
+        ctrlsum_file_btn.click(
+            fn=ctrlsum_for_file,
+            inputs=[ctrlsum_file, ctrlsum_file_length, ctrlsum_file_keywords, ctrlsum_str],
+            outputs=[ctrlsum_file_output, ctrlsum_str]
+        )
+        def clear():
+            return None,0,None
+
+        ctrlsum_file.change(clear, inputs=None,outputs=[ctrlsum_str,ctrlsum_file_length,ctrlsum_file_keywords])
+
         # Reference String Parsing
         with gr.TabItem("Reference String Parsing"):
             with gr.Box():
@@ -60,51 +94,6 @@ with gr.Blocks(css="#htext span {white-space: pre-line}") as demo:
             outputs=rsp_str_output
         )
 
-        # Single Document Summarization
-        with gr.TabItem("Single Document Summarization"):
-            with gr.Box():
-                gr.Markdown(ssum_str_md)
-                with gr.Row():
-                    with gr.Column():
-                        ssum_str = gr.Textbox(label="Input String")
-                        with gr.Column():
-                            ssum_str_beams = gr.Number(label="Number of beams for beam search", value=1, precision=0)
-                            ssum_str_sequences = gr.Number(label="Number of generated summaries", value=1, precision=0)
-                        with gr.Row():
-                            ssum_str_btn = gr.Button("Generate")
-                    ssum_str_output = gr.Textbox(
-                        elem_id="htext",
-                        label="Summary",
-                    )
-                ssum_str_examples = gr.Examples(examples=[[ssum_str_example, 1, 1], ],
-                                                inputs=[ssum_str, ssum_str_beams, ssum_str_sequences])
-            with gr.Box():
-                gr.Markdown(ssum_file_md)
-                with gr.Row():
-                    with gr.Column():
-                        ssum_file = gr.File(label="Input File")
-                        with gr.Column():
-                            ssum_file_beams = gr.Number(label="Number of beams for beam search", value=1, precision=0)
-                            ssum_file_sequences = gr.Number(label="Number of generated summaries", value=1, precision=0)
-                        with gr.Row():
-                            ssum_file_btn = gr.Button("Generate")
-                    ssum_file_output = gr.Textbox(
-                        elem_id="htext",
-                        label="Summary",
-                    )
-                ssum_file_examples = gr.Examples(examples=[["examples/BERT_body.txt", 10, 2],["examples/BERT_paper.pdf", 1, 1]],
-                                                inputs=[ssum_file, ssum_file_beams, ssum_file_sequences])
-
-        ssum_file_btn.click(
-            fn=ssum_for_file,
-            inputs=[ssum_file, ssum_file_beams, ssum_file_sequences],
-            outputs=ssum_file_output
-        )
-        ssum_str_btn.click(
-            fn=ssum_for_str,
-            inputs=[ssum_str, ssum_str_beams, ssum_str_sequences],
-            outputs=ssum_str_output
-        )
 
         # Dataset Extraction
         with gr.TabItem("Dataset Mentions Extraction"):
@@ -153,4 +142,4 @@ with gr.Blocks(css="#htext span {white-space: pre-line}") as demo:
         )
 
 
-demo.launch()
+demo.launch(share=False)

controlled_summarization.py

@@ -0,0 +1,59 @@
+from typing import List, Tuple
+import torch
+from SciAssist import Summarization
+
+device = "gpu" if torch.cuda.is_available() else "cpu"
+
+ctrlsum_pipeline = Summarization(os_name="nt",checkpoint="google/flan-t5-base")
+
+
+def ctrlsum_for_str(input,length=None, keywords=None) -> List[Tuple[str, str]]:
+
+    if keywords is not None:
+        keywords = keywords.strip().split(",")
+        if keywords[0] == "":
+            keywords = None
+    if length==0 or length is None:
+        length = None
+    results = ctrlsum_pipeline.predict(input, type="str",
+                                    length=length, keywords=keywords)
+
+    output = []
+    for res in results["summary"]:
+        output.append(f"{res}\n\n")
+    return "".join(output)
+
+
+def ctrlsum_for_file(input, length=None, keywords=None, text="") -> List[Tuple[str, str]]:
+    if input == None:
+        if text=="":
+            return None
+        else:
+            return ctrlsum_for_str(text,length,keywords),text
+    else:
+        filename = input.name
+        if keywords is not None:
+            keywords = keywords.strip().split(",")
+            if keywords[0] == "":
+                keywords = None
+        if length==0:
+            length = None
+        # Identify the format of input and parse reference strings
+        if filename[-4:] == ".txt":
+            results = ctrlsum_pipeline.predict(filename, type="txt",
+                                            save_results=False,
+                                            length=length, keywords=keywords)
+        elif filename[-4:] == ".pdf":
+            results = ctrlsum_pipeline.predict(filename,
+                                            save_results=False, length=length, keywords=keywords)
+        else:
+            return [("File Format Error !", None)]
+
+        output = []
+        for res in results["summary"]:
+            output.append(f"{res}\n\n")
+        return "".join(output), results["raw_text"]
+
+
+
+ctrlsum_str_example = "Language model pre-training has been shown to be effective for improving many natural language processing tasks ( Dai and Le , 2015 ; Peters et al. , 2018a ; Radford et al. , 2018 ; Howard and Ruder , 2018 ) . These include sentence-level tasks such as natural language inference ( Bowman et al. , 2015 ; Williams et al. , 2018 ) and paraphrasing ( Dolan and Brockett , 2005 ) , which aim to predict the relationships between sentences by analyzing them holistically , as well as token-level tasks such as named entity recognition and question answering , where models are required to produce fine-grained output at the token level ( Tjong Kim Sang and De Meulder , 2003 ; Rajpurkar et al. , 2016 ) . There are two existing strategies for applying pre-trained language representations to downstream tasks : feature-based and fine-tuning . The feature-based approach , such as ELMo ( Peters et al. , 2018a ) , uses task-specific architectures that include the pre-trained representations as additional features . The fine-tuning approach , such as the Generative Pre-trained Transformer ( OpenAI GPT ) ( Radford et al. , 2018 ) , introduces minimal task-specific parameters , and is trained on the downstream tasks by simply fine-tuning all pretrained parameters . The two approaches share the same objective function during pre-training , where they use unidirectional language models to learn general language representations . We argue that current techniques restrict the power of the pre-trained representations , especially for the fine-tuning approaches . The major limitation is that standard language models are unidirectional , and this limits the choice of architectures that can be used during pre-training . For example , in OpenAI GPT , the authors use a left-toright architecture , where every token can only attend to previous tokens in the self-attention layers of the Transformer ( Vaswani et al. , 2017 ) . Such restrictions are sub-optimal for sentence-level tasks , and could be very harmful when applying finetuning based approaches to token-level tasks such as question answering , where it is crucial to incorporate context from both directions . In this paper , we improve the fine-tuning based approaches by proposing BERT : Bidirectional Encoder Representations from Transformers . BERT alleviates the previously mentioned unidirectionality constraint by using a `` masked language model '' ( MLM ) pre-training objective , inspired by the Cloze task ( Taylor , 1953 ) . The masked language model randomly masks some of the tokens from the input , and the objective is to predict the original vocabulary id of the masked arXiv:1810.04805v2 [ cs.CL ] 24 May 2019 word based only on its context . Unlike left-toright language model pre-training , the MLM objective enables the representation to fuse the left and the right context , which allows us to pretrain a deep bidirectional Transformer . In addition to the masked language model , we also use a `` next sentence prediction '' task that jointly pretrains text-pair representations . The contributions of our paper are as follows : • We demonstrate the importance of bidirectional pre-training for language representations . Unlike Radford et al . ( 2018 ) , which uses unidirectional language models for pre-training , BERT uses masked language models to enable pretrained deep bidirectional representations . This is also in contrast to Peters et al . ( 2018a ) , which uses a shallow concatenation of independently trained left-to-right and right-to-left LMs . • We show that pre-trained representations reduce the need for many heavily-engineered taskspecific architectures . BERT is the first finetuning based representation model that achieves state-of-the-art performance on a large suite of sentence-level and token-level tasks , outperforming many task-specific architectures . • BERT advances the state of the art for eleven NLP tasks . The code and pre-trained models are available at https : //github.com/ google-research/bert . "

dataset_extraction.py

@@ -6,7 +6,7 @@ device = "gpu" if torch.cuda.is_available() else "cpu"
 de_pipeline = DatasetExtraction(os_name="nt")
 
 
-def de_for_str(input) -> List[Tuple[str, str]]:
+def de_for_str(input):
     results = de_pipeline.extract(input, type="str", save_results=False)
 
     output = []

description.py

@@ -16,8 +16,6 @@ To **test on a file**, the input can be:
 ssum_str_md = '''
 To **test on strings**, simply input a string.
 
-**Note**: The **number of beams** should be **divisible** by the **number of generated summaries** for group beam search.
-
 '''
 
 ssum_file_md = '''
@@ -28,10 +26,32 @@ To **test on a file**, the input can be:
 - A pdf file which contains a whole scientific documention without any preprocessing(including title, author, body text...).
 
 
-**Note**: The **number of beams** should be **divisible** by the **number of generated summaries** for group beam search.
+'''
+
+# - The **number of beams** should be **divisible** by the **number of generated summaries** for group beam search.
+ctrlsum_str_md = '''
+To **test on strings**, simply input a string.
+
+**Note**: 
+
+- Length 0 will exert no control over length.
+ 
+
+'''
+
+ctrlsum_file_md = '''
+To **test on a file**, the input can be:
+
+- A txt file which contains the content to be summarized.
+
+- A pdf file which contains a whole scientific documention without any preprocessing(including title, author, body text...).
+
+
 
 '''
 
+
+
 de_str_md = '''
 To **test on strings**, simply input a string.
 '''