Evaluation of Table Representations to Answer Questions from Tables in Documents : A Case Study using 3GPP Specifications
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916375466868736 |
|---|---|
| author | Roychowdhury, Sujoy Soman, Sumit Ranjani, HG Sharma, Avantika Gunda, Neeraj Bala, Sai Krishna |
| author_facet | Roychowdhury, Sujoy Soman, Sumit Ranjani, HG Sharma, Avantika Gunda, Neeraj Bala, Sai Krishna |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_17008 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluation of Table Representations to Answer Questions from Tables in Documents : A Case Study using 3GPP Specifications Roychowdhury, Sujoy Soman, Sumit Ranjani, HG Sharma, Avantika Gunda, Neeraj Bala, Sai Krishna Information Retrieval Machine Learning 68T50 I.2.7 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. |
| title | Evaluation of Table Representations to Answer Questions from Tables in Documents : A Case Study using 3GPP Specifications |
| topic | Information Retrieval Machine Learning 68T50 I.2.7 |
| url | https://arxiv.org/abs/2408.17008 |