AttesTable at SemEval-2021 Task 9: Extending Statement Verification with Tables for Unknown Class, and Semantic Evidence Finding

This paper describes our approach for Task 9 of SemEval 2021: Statement Verification and Evidence Finding with Tables. We participated in both subtasks, namely statement verification and evidence finding. For the subtask of statement verification, we extend the TAPAS model to adapt to the ‘unknown’ class of statements by finetuning it on an augmented version of the task data. For the subtask of evidence finding, we finetune the DistilBERT model in a Siamese setting.

[1]  Samuel R. Bowman,et al.  A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference , 2017, NAACL.

[2]  Lucian Popa,et al.  Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context , 2020, ArXiv.

[3]  Thomas Muller,et al.  TaPas: Weakly Supervised Table Parsing via Pre-training , 2020, ACL.

[4]  Ting Liu,et al.  Learn to Combine Linguistic and Symbolic Information for Table-based Fact Verification , 2020, COLING.

[5]  Sara Rosenthal,et al.  SemEval-2021 Task 9: Fact Verification and Evidence Finding for Tabular Data in Scientific Documents (SEM-TAB-FACTS) , 2021, SEMEVAL.

[6]  Quan Liu,et al.  Program Enhanced Fact Verification with Verbalization and Graph Attention Network , 2020, EMNLP.

[7]  Percy Liang,et al.  Compositional Semantic Parsing on Semi-Structured Tables , 2015, ACL.

[8]  Aditya Malte,et al.  Multilingual Cyber Abuse Detection using Advanced Transformer Architecture , 2019, TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON).

[9]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[10]  Nan Duan,et al.  LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network , 2020, ACL.

[11]  Richard Socher,et al.  Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning , 2018, ArXiv.

[12]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[13]  Christopher Potts,et al.  A large annotated corpus for learning natural language inference , 2015, EMNLP.

[14]  Wenhu Chen,et al.  TabFact: A Large-scale Dataset for Table-based Fact Verification , 2019, ICLR.

[15]  Thomas Muller,et al.  Understanding tables with intermediate pre-training , 2020, FINDINGS.

[16]  Thomas Wolf,et al.  DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter , 2019, ArXiv.

[17]  Frank Hutter,et al.  Decoupled Weight Decay Regularization , 2017, ICLR.

[18]  Ming-Wei Chang,et al.  Search-based Neural Structured Learning for Sequential Question Answering , 2017, ACL.

[19]  Aditya Malte,et al.  Evolution of transfer learning in natural language processing , 2019, ArXiv.

[20]  Deepak Mishra,et al.  An Attention Ensemble Based Approach for Multilabel Profanity Detection , 2019, 2019 International Conference on Data Mining Workshops (ICDMW).

[21]  Mayank Jobanputra,et al.  Unsupervised Question Answering for Fact-Checking , 2019, EMNLP.

[22]  Eneko Agirre,et al.  SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation , 2017, *SEMEVAL.