IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidance
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909162769743872 |
|---|---|
| author | Jang, Yunah Lee, Kang-il Bae, Hyunkyung Lee, Hwanhee Jung, Kyomin |
| author_facet | Jang, Yunah Lee, Kang-il Bae, Hyunkyung Lee, Hwanhee Jung, Kyomin |
| contents | Conversational search aims to retrieve passages containing essential information to answer queries in a multi-turn conversation. In conversational search, reformulating context-dependent conversational queries into stand-alone forms is imperative to effectively utilize off-the-shelf retrievers. Previous methodologies for conversational query reformulation frequently depend on human-annotated rewrites. However, these manually crafted queries often result in sub-optimal retrieval performance and require high collection costs. To address these challenges, we propose Iterative Conversational Query Reformulation (IterCQR), a methodology that conducts query reformulation without relying on human rewrites. IterCQR iteratively trains the conversational query reformulation (CQR) model by directly leveraging information retrieval (IR) signals as a reward. Our IterCQR training guides the CQR model such that generated queries contain necessary information from the previous dialogue context. Our proposed method shows state-of-the-art performance on two widely-used datasets, demonstrating its effectiveness on both sparse and dense retrievers. Moreover, IterCQR exhibits superior performance in challenging settings such as generalization on unseen datasets and low-resource scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_09820 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidance Jang, Yunah Lee, Kang-il Bae, Hyunkyung Lee, Hwanhee Jung, Kyomin Information Retrieval Conversational search aims to retrieve passages containing essential information to answer queries in a multi-turn conversation. In conversational search, reformulating context-dependent conversational queries into stand-alone forms is imperative to effectively utilize off-the-shelf retrievers. Previous methodologies for conversational query reformulation frequently depend on human-annotated rewrites. However, these manually crafted queries often result in sub-optimal retrieval performance and require high collection costs. To address these challenges, we propose Iterative Conversational Query Reformulation (IterCQR), a methodology that conducts query reformulation without relying on human rewrites. IterCQR iteratively trains the conversational query reformulation (CQR) model by directly leveraging information retrieval (IR) signals as a reward. Our IterCQR training guides the CQR model such that generated queries contain necessary information from the previous dialogue context. Our proposed method shows state-of-the-art performance on two widely-used datasets, demonstrating its effectiveness on both sparse and dense retrievers. Moreover, IterCQR exhibits superior performance in challenging settings such as generalization on unseen datasets and low-resource scenarios. |
| title | IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidance |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2311.09820 |