Papers with TabFact

10 papers
Understanding tables with intermediate pre-training (2020.findings-emnlp)

Copied to clipboard

Challenge: Textual entailment is well studied, but is less well studied for table enlargement . a new dataset of millions of examples is used to train the model .
Approach: They adapt a table-based BERT model to recognize entailment from a dataset . they evaluate table pruning techniques as a pre-processing step to improve model efficiency .
Outcome: The proposed model improves training and prediction efficiency at a moderate drop in accuracy.
Large Language Models are few(1)-shot Table Reasoners (2023.findings-eacl)

Copied to clipboard

Challenge: Recent literature has shown that large language models are excellent few-shot reasoners to solve text reasoning tasks.
Approach: They evaluated LLMs on popular table QA and fact verification datasets like WikiTableQuestion, FetaQA, TabFact, and FEVEROUS and found they are competent at complex reasoning over table structures.
Outcome: The proposed models are more competent at complex reasoning over table structures than tuned T5-large models.
TWT: Table with Written Text for Controlled Data-to-Text Generation (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods output hallucinated text that is not faithful on TWT.
Approach: They propose to generate text conditioned on the structured data and a prefix by leveraging pre-trained neural models.
Outcome: The proposed approach outperforms state-of-the-art methods under automatic and human evaluation metrics.
Table Fact Verification with Structure-Aware Transformer (2020.emnlp-main)

Copied to clipboard

Challenge: Pre-trained models cannot be used to encode semi-structured data because of their nature.
Approach: They propose a Structure-Aware Transformer which injects table structural information into mask . method could combine symbolic and linguistic reasoning, they propose .
Outcome: The proposed method outperforms baseline on a large scale table verification dataset.
NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable capabilities in parsing textual data and generating code.
Approach: They propose a framework that normalizes web tables to support symbolic reasoning . they compare NormTab to a stand-alone framework that can normalize tabular data .
Outcome: The proposed framework outperforms traditional models on symbolic reasoning tasks on tabular data.
Weakly Supervised Semantic Parsing by Learning from Mistakes (2021.findings-emnlp)

Copied to clipboard

Challenge: Weakly supervised semantic parsing requires searching consistent logical forms in a huge space and dealing with spurious logical form.
Approach: They propose a learning framework that trains parsers via utterance-denotation pairs . they use utterrance-logical form pairs created from mistakes to bootstrap parser .
Outcome: The proposed framework outperforms state-of-the-art methods on WikiSQL, TabFact and other datasets.
PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training (2022.emnlp-main)

Copied to clipboard

Challenge: Table-based fact verification has attracted a lot of attention recently due to the lack of datasets that can be used to pre-train language models to be aware of common table operations.
Approach: They propose a table-based fact verification tool that pre-trains language models to be aware of common table operations such as aggregating a column or comparing tuples.
Outcome: The proposed method outperforms previous methods on two table-based fact verification datasets TabFact and SEM-TAB- FACTS.
Table-based Fact Verification With Salience-aware Learning (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for fact verification use tabular data with tokens, but training requires labeled training data.
Approach: They propose a system that identifies token-level salience in the statement with probing-based saliency estimation.
Outcome: The proposed system improves on TabFact benchmark by replacing non-salient terms with tokens.
ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples (2022.emnlp-main)

Copied to clipboard

Challenge: Existing models with table-specific architectures and pre-training methods perform well on understanding table structures but lack table reasoning skills.
Approach: They propose to pre-train tables with table reasoning skills without complex architectures . they define 7 table reasoning skill, and then pre-teach them to generate tables .
Outcome: The proposed model improves on four tasks and is available on github.
RePanda: Pandas-powered Tabular Verification and Reasoning (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for fact-checking tabular data rely on black-box models with opaque reasoning.
Approach: They propose a structured fact verification approach that translates claims into executable pandas queries.
Outcome: The proposed method outperforms existing methods and demonstrates strong OOD robustness.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations