[EMNLP 2022] Unifying and multi-tasking structured knowledge grounding with language models

End-to-end neural table-text understanding models.

This repo is for Korean wiki table question answering datasets described in the paper of Korean-Specific Dataset for Table Question Answering

Code and Data for ICLR2021 Paper "Open Question Answering over Tables and Text"

Dataset for TACL 2022 paper: "FeTaQA: Free-form Table Question Answering"

Data and code for ACL 2022 paper "MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data"

TAT-QA (Tabular And Textual dataset for Question Answering) contains 16,552 questions associated with 2,757 hybrid contexts from real-world financial reports.

This repository contains source code for the TaBERT model, a pre-trained language model for learning joint representations of natural language utterances and (semi-)structured tables for semantic p…

A dataset of complex questions on semi-structured Wikipedia tables

Data and Code for ICLR2020 Paper "TabFact: A Large-scale Dataset for Table-based Fact Verification"

NLP Information-grounded dialogue over heterogeneous information

AI Tool for querying natural language on tabular data.

[SUKI'22] Table Retrieval May Not Necessitate Table-Specific Model Design

[ACL 2022] A hierarchical table dataset for question answering and data-to-text generation.

This project makes available the code and data from our NAACL paper: "Capturing Row and Column Semantics in Transformer Based Question Answering over Tables"

Code for COLING 2022 long paper: Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder

A comprehensive paper list of Reasoning over Tables.

TUTA and ForTaP for Structure-Aware and Numerical-Reasoning-Aware Table Pre-Training

Code and data for "TURL: Table Understanding through Representation Learning"

[EMNLP 2022] TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data

ICLR 2022 Paper, SOTA Table Pre-training Model, TAPEX: Table Pre-training via Learning a Neural SQL Executor

Data and Code for EMNLP 2022 paper "ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples"

Code for paper "PLoG: Table-to-Logic Pretraining for Logical Table-to-Text Generation"

resources for the IBM Airlines Table-Question-Answering Benchmark

DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data (AAAI 2023)

NeurIPS'22 | TransTab: Learning Transferable Tabular Transformers Across Tables