paper-with-me

홈 › Papers

Evaluation of Table Representations to Answer Questions from Tables in Documents : A Case Study using 3GPP Specifications

2024-08-30 · Sujoy Roychowdhury, Sumit Soman, HG Ranjani, Avantika Sharma, Neeraj Gunda, Sai Krishna Bala

With the ubiquitous use of document corpora for question answering, one important aspect which is especially relevant for technical documents is the ability to extract information from tables which are interspersed with text. The major challenge in this is that unlike free-flow text or isolated set of tables, the representation of a table in terms of what is a relevant chunk is not obvious. We conduct a series of experiments examining various representations of tabular data interspersed with text to understand the relative benefits of different representations. We choose a corpus of $3^{rd}$ Generation Partnership Project (3GPP) documents since they are heavily interspersed with tables. We create expert curated dataset of question answers to evaluate our approach. We conclude that row level representations with corresponding table header information being included in every cell improves the performance of the retrieval, thus leveraging the structural information present in the tabular data.

📄 PDF Abstract BibTeX arXiv:2408.17008

Code (0)

등록된 구현이 없습니다.

Tasks

Question AnsweringRetrieval

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Representations for Question Answering from Documents with Tables and Text

2021-01-26 · EACL 2021 2 · Vicky Zayats, Kristina Toutanova, Mari Ostendorf

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…

Natural QuestionsQuestion Answering

Multi-modal Retrieval of Tables and Texts Using Tri-encoder Models

2021-08-09 · EMNLP (MRQA) 2021 11 · Bogdan Kostić, Julian Risch, Timo Möller

Open-domain extractive question answering works well on textual data by first retrieving candidate texts and then extracting the answer from those candidates. However, some questions cannot be answered by text alone but …

Extractive Question-AnsweringQuestion AnsweringRetrieval

MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering

2023-05-22 · Vaishali Pal, Andrew Yates, Evangelos Kanoulas, Maarten de Rijke

Recent advances in tabular question answering (QA) with large language models are constrained in their coverage and only answer questions over a single table. However, real-world queries are complex in nature, often over…

Question Answering

BioTABQA: Instruction Learning for Biomedical Table Question Answering

2022-07-06 · Man Luo, Sharad Saxena, Swaroop Mishra, Mihir Parmar 외

Table Question Answering (TQA) is an important but under-explored task. Most of the existing QA datasets are in unstructured text format and only few of them use tables as the context. To the best of our knowledge, none …

Question Answering

Compositional Semantic Parsing on Semi-Structured Tables

2015-08-03 · IJCNLP 2015 7 · Panupong Pasupat, Percy Liang

Two important aspects of semantic parsing for question answering are the breadth of the knowledge source and the depth of logical compositionality. While existing work trades off one aspect for another, this paper simult…

Question AnsweringSemantic Parsing