natural-language-processing-11

Table-based Fact Verification

3260 papers • 126 benchmarks • 313 datasets

Verifying facts given semi-structured data.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in table-based-fact-verification-11

Trend

Dataset

Best Model

Actions

TabFact

Libraries

i

Use these libraries to find table-based-fact-verification-11 models and implementations

Datasets

TabFact

InfoTabS

Subtasks

No subtasks available.

Most implemented papers

TAPEX: Table Pre-training via Learning a Neural SQL Executor

Qian Liu, Jian-Guang Lou, Zeqi Lin, Jiaqi Guo•Thu Jul 15 2021

TAPEX is proposed to show that table pre-training can be achieved by learning a neural SQL executor over a synthetic corpus, which is obtained by automatically synthesizing executable SQL queries and their execution outputs.

329

Content

0

Paper Graph

TabFact: A Large-scale Dataset for Table-based Fact Verification

Wenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang, Hong Wang, SHIYANG LI, Xiyou Zhou, William Yang Wang•Wed Sep 04 2019

A large-scale dataset with 16k Wikipedia tables as the evidence for 118k human-annotated natural language statements, which are labeled as either ENTAILED or REFUTED is constructed and two different models are designed: Table-BERT and Latent Program Algorithm (LPA).

622 0

Paper Graph

Understanding tables with intermediate pre-training

Julian Martin Eisenschlos, Syrine Krichene, Thomas Müller•Wed Sep 30 2020

This work adapts TAPAS (Herzig et al., 2020), a table-based BERT model, to recognize entailment, and creates a balanced dataset of millions of automatically created training examples which are learned in an intermediate step prior to fine-tuning.

130 0

Paper Graph

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

Harshit Varma, Aadish Jain, Pratik Ratadiya, Abhishek Rathi•Thu Dec 31 2020

This paper describes the approach for Task 9 of SemEval 2021: Statement Verification and Evidence Finding with Tables, whereby the TAPAS model is extended to adapt to the ‘unknown’ class of statements by finetuning it on an augmented version of the task data.

2 0

Paper Graph

Table-based Fact Verification with Salience-aware Learning

Fei Wang, Muhao Chen, J. Pujara, Kexuan Sun, Pedro A. Szekely•Wed Sep 08 2021

Inspired by counterfactual causality, this system identifies token-level salience in the statement with probing-based salience estimation and applies salience-aware data augmentation to generate a more diverse set of training instances by replacing non-salient terms.

21 0

Paper Graph

Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification

Ting Liu, Qi Shi, Yu Zhang, Qingyu Yin•Mon Sep 13 2021

This work forms the table-based fact verification task as an evidence retrieval and reasoning framework, proposing the Logic-level Evidence Retrieval and Graph-based Verification network (LERGV) and shows the effectiveness of the proposed approach on the large-scale benchmark TABFACT.

21 0

Paper Graph

Exploring Decomposition for Table-based Fact Verification

Xiao-Dan Zhu, Xiaoyu Yang•Tue Sep 21 2021

This paper proposes a program-guided approach to constructing a pseudo dataset for decomposition model training that achieves the new state-of-the-art performance, an 82.7\% accuracy, on the TabFact benchmark.

25 0

Paper Graph

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models

Michihiro Yasunaga, Noah A. Smith, Sida I. Wang, Chien-Sheng Wu, Caiming Xiong, Luke Zettlemoyer, Victor Zhong, Tao Yu, Dragomir R. Radev, Ziyu Yao, Pengcheng Yin, Rui Zhang, Ruiqi Zhong, Lingpeng Kong, Ming Zhong, Bailin Wang, Tianbao Xie, Peng Shi, Chen Henry Wu, Ansong Ni, Torsten Scholak, Chengzu Li, Connor Boyle•Sat Jan 15 2022

The UnifiedSKG framework is proposed, which unifies 21 SKG tasks into a text-to-text format, aiming to promote systematic SKG research, instead of being exclusive to a single task, domain, or dataset.

341 0

Paper Graph

Table-based Fact Verification with Self-adaptive Mixture of Experts

Yuxuan Zhou, Xien Liu, Kaiyin Zhou, Ji Wu•Mon Apr 18 2022

A mixture-of-experts neural network to recognize and execute different types of reasoning and a self-adaptive method is developed to teach the management module combining results of different experts more efficiently without external knowledge.

18 0

Paper Graph

Binding Language Models in Symbolic Languages

Caiming Xiong, Luke S. Zettlemoyer, Dragomir R. Radev, Tianbao Xie, Yushi Hu, Chengzu Li, Zhoujun Cheng, Peng Shi, Rahul Nadkarni, M. Ostendorf, N. A. Smith•Wed Oct 05 2022

Binder is a training-free neural-symbolic framework that maps the task input to a program, which allows binding a unified API of language model (LM) functionalities to a programming language (e.g., SQL, Python) to extend its grammar coverage and thus tackle more diverse questions.

278 0

Paper Graph

Adding a benchmark result helps the community track progress.