PAQA: Toward ProActive Open-Retrieval Question Answering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916138729865216 |
|---|---|
| author | Erbacher, Pierre Nie, Jian-Yun Preux, Philippe Soulier, Laure |
| author_facet | Erbacher, Pierre Nie, Jian-Yun Preux, Philippe Soulier, Laure |
| contents | Conversational systems have made significant progress in generating natural language responses. However, their potential as conversational search systems is currently limited due to their passive role in the information-seeking process. One major limitation is the scarcity of datasets that provide labelled ambiguous questions along with a supporting corpus of documents and relevant clarifying questions. This work aims to tackle the challenge of generating relevant clarifying questions by taking into account the inherent ambiguities present in both user queries and documents. To achieve this, we propose PAQA, an extension to the existing AmbiNQ dataset, incorporating clarifying questions. We then evaluate various models and assess how passage retrieval impacts ambiguity detection and the generation of clarifying questions. By addressing this gap in conversational search systems, we aim to provide additional supervision to enhance their active participation in the information-seeking process and provide users with more accurate results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_16608 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PAQA: Toward ProActive Open-Retrieval Question Answering Erbacher, Pierre Nie, Jian-Yun Preux, Philippe Soulier, Laure Computation and Language Information Retrieval Conversational systems have made significant progress in generating natural language responses. However, their potential as conversational search systems is currently limited due to their passive role in the information-seeking process. One major limitation is the scarcity of datasets that provide labelled ambiguous questions along with a supporting corpus of documents and relevant clarifying questions. This work aims to tackle the challenge of generating relevant clarifying questions by taking into account the inherent ambiguities present in both user queries and documents. To achieve this, we propose PAQA, an extension to the existing AmbiNQ dataset, incorporating clarifying questions. We then evaluate various models and assess how passage retrieval impacts ambiguity detection and the generation of clarifying questions. By addressing this gap in conversational search systems, we aim to provide additional supervision to enhance their active participation in the information-seeking process and provide users with more accurate results. |
| title | PAQA: Toward ProActive Open-Retrieval Question Answering |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2402.16608 |