Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision
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_ | 1866909345400225792 |
|---|---|
| author | Christmann, Philipp Vakulenko, Svitlana Sorodoc, Ionut Teodor Byrne, Bill de Gispert, Adrià |
| author_facet | Christmann, Philipp Vakulenko, Svitlana Sorodoc, Ionut Teodor Byrne, Bill de Gispert, Adrià |
| contents | Long-form question answering (LFQA) aims at generating in-depth answers to end-user questions, providing relevant information beyond the direct answer. However, existing retrievers are typically optimized towards information that directly targets the question, missing out on such contextual information. Furthermore, there is a lack of training data for relevant context. To this end, we propose and compare different weak supervision techniques to optimize retrieval for contextual information. Experiments demonstrate improvements on the end-to-end QA performance on ASQA, a dataset for long-form question answering. Importantly, as more contextual information is retrieved, we improve the relevant page recall for LFQA by 14.7% and the groundedness of generated long-form answers by 12.5%. Finally, we show that long-form answers often anticipate likely follow-up questions, via experiments on a conversational QA dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08623 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision Christmann, Philipp Vakulenko, Svitlana Sorodoc, Ionut Teodor Byrne, Bill de Gispert, Adrià Computation and Language Information Retrieval Long-form question answering (LFQA) aims at generating in-depth answers to end-user questions, providing relevant information beyond the direct answer. However, existing retrievers are typically optimized towards information that directly targets the question, missing out on such contextual information. Furthermore, there is a lack of training data for relevant context. To this end, we propose and compare different weak supervision techniques to optimize retrieval for contextual information. Experiments demonstrate improvements on the end-to-end QA performance on ASQA, a dataset for long-form question answering. Importantly, as more contextual information is retrieved, we improve the relevant page recall for LFQA by 14.7% and the groundedness of generated long-form answers by 12.5%. Finally, we show that long-form answers often anticipate likely follow-up questions, via experiments on a conversational QA dataset. |
| title | Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2410.08623 |