Table-based Fact Verification
14 papers with code • 1 benchmarks • 2 datasets
Verifying facts given semi-structured data.
TabFact
InfoTabS
Most implemented papers
TabFact: A Large-scale Dataset for Table-based Fact Verification
wenhuchen/Table-Fact-Checking
•
•
ICLR 2020
To this end, we construct a large-scale dataset called TabFact with 16k Wikipedia tables as the evidence for 118k human-annotated natural language statements, which are labeled as either ENTAILED or REFUTED.
Understanding tables with intermediate pre-training
google-research/tapas
•
•
Findings of the Association for Computational Linguistics 2020
To be able to use long examples as input of BERT models, we evaluate table pruning techniques as a pre-processing step to drastically improve the training and prediction efficiency at a moderate drop in accuracy.
TAPEX: Table Pre-training via Learning a Neural SQL Executor
microsoft/Table-Pretraining
•
•
ICLR 2022
TAPEX addresses the data scarcity challenge via guiding the language model to mimic a SQL executor on the diverse, large-scale and high-quality synthetic corpus.
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.
Table-based Fact Verification with Salience-aware Learning
luka-group/salience-aware-learning
•
•
Findings (EMNLP) 2021
From one perspective, our system conducts masked salient token prediction to enhance the model for alignment and reasoning between the table and the statement.
Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification
Specifically, we first retrieve logic-level program-like evidence from the given table and statement as supplementary evidence for the table.
Exploring Decomposition for Table-based Fact Verification
arielsho/decomposition-table-reasoning
•
•
Findings (EMNLP) 2021
Fact verification based on structured data is challenging as it requires models to understand both natural language and symbolic operations performed over tables.
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering over knowledge bases.
Table-based Fact Verification with Self-adaptive Mixture of Experts
thumlp/samoe
•
•
Findings (ACL) 2022
The table-based fact verification task has recently gained widespread attention and yet remains to be a very challenging problem.
Binding Language Models in Symbolic Languages
We propose Binder, a training-free neural-symbolic framework that maps the task input to a program, which (1) 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, (2) adopts an LM as both the program parser and the underlying model called by the API during execution, and (3) requires only a few in-context exemplar annotations.
