mlsanityData to 7 Oct 2026

Representations for Question Answering from Documents with Tables and Text

arXiv 2101.10573 ↗First posted 26 Jan 2021cs.CLcited by 21

Not on the map. Why?

Abstract (arXiv)

Tables in Web documents are pervasive and can be directly used to answer many of the queries searched on the Web, motivating their integration in question answering. Very often information presented in tables is succinct and hard to interpret with standard language representations. On the other hand, tables often appear within textual context, such as an article describing the table. Using the information from an article as additional context can potentially enrich table representations. In this work we aim to improve question answering from tables by refining table representations based on information from surrounding text. We also present an effective method to combine text and table-based predictions for question answering from full documents, obtaining significant improvements on the Natural Questions dataset.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 16 of its 20 references that are in the map. First posted on arXiv 26 Jan 2021.

Builds on

16 of 20 references.

References · 16

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  4. 2018Self-Attention with Relative Position Representationscited by 1,112
  5. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  6. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  7. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  8. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 263
  9. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
  10. 2018Open Domain Question Answering Using Early Fusion of Knowledge Bases and Textcited by 167
  11. 2019A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualizationcited by 88
  12. 2020INFOTABS: Inference on Tables as Semi-structured Datacited by 84
4 more
  1. 2019A BERT Baseline for the Natural Questionscited by 33
  2. 2019Answering Conversational Questions on Structured Data without Logical Formscited by 24
  3. 2020RikiNet: Reading Wikipedia Pages for Natural Question Answeringcited by 21
  4. 2019Generating Logical Forms from Graph Representations of Text and Entitiescited by 10

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 9; 2023: 5; 2024: 1; 2025: 1.

21 papers.

Sort:

By area:

  1. 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 166
  2. 2021Open Domain Question Answering over Tables via Dense Retrievalcited by 74
  3. 2022Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Taskscited by 42
  4. 2022A Survey on Table Question Answering: Recent Advancescited by 41
  5. 2021Open Domain Question Answering with A Unified Knowledge Interfacecited by 32
  6. 2022ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examplescited by 29
  7. 2023TempTabQA: Temporal Question Answering for Semi-Structured Tablescited by 27
  8. 2021ReasonBERT: Pre-trained to Reason with Distant Supervisioncited by 22
  9. 2022STable: Table Generation Framework for Encoder-Decoder Modelscited by 15
  10. 2022Table Retrieval May Not Necessitate Table-specific Model Designcited by 11
  11. 2021Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoningcited by 9
  12. 2022MuGER2: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answeringcited by 9
9 more
  1. 2024Enhancing Temporal Understanding in LLMs for Semi-structured Tablescited by 8
  2. 2023cTBLS: Augmenting Large Language Models with Conversational Tablescited by 7
  3. 2022Realistic Data Augmentation Framework for Enhancing Tabular Reasoningcited by 4
  4. 2022Korean-Specific Dataset for Table Question Answeringcited by 3
  5. 2022Enhancing Tabular Reasoning with Pattern Exploiting Trainingcited by 3
  6. 2023InfoSync: Information Synchronization across Multilingual Semi-structured Tablescited by 3
  7. 2025Structural Deep Encoding for Table Question Answeringcited by 2
  8. 2023MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answeringcited by 1
  9. 2023Semi-Structured Object Sequence Encoderscited by 0