Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy
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_ | 1866914706246074368 |
|---|---|
| author | Kang, SeongKu Agarwal, Shivam Jin, Bowen Lee, Dongha Yu, Hwanjo Han, Jiawei |
| author_facet | Kang, SeongKu Agarwal, Shivam Jin, Bowen Lee, Dongha Yu, Hwanjo Han, Jiawei |
| contents | Document retrieval has greatly benefited from the advancements of large-scale pre-trained language models (PLMs). However, their effectiveness is often limited in theme-specific applications for specialized areas or industries, due to unique terminologies, incomplete contexts of user queries, and specialized search intents. To capture the theme-specific information and improve retrieval, we propose to use a corpus topical taxonomy, which outlines the latent topic structure of the corpus while reflecting user-interested aspects. We introduce ToTER (Topical Taxonomy Enhanced Retrieval) framework, which identifies the central topics of queries and documents with the guidance of the taxonomy, and exploits their topical relatedness to supplement missing contexts. As a plug-and-play framework, ToTER can be flexibly employed to enhance various PLM-based retrievers. Through extensive quantitative, ablative, and exploratory experiments on two real-world datasets, we ascertain the benefits of using topical taxonomy for retrieval in theme-specific applications and demonstrate the effectiveness of ToTER. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_04160 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy Kang, SeongKu Agarwal, Shivam Jin, Bowen Lee, Dongha Yu, Hwanjo Han, Jiawei Information Retrieval Artificial Intelligence Document retrieval has greatly benefited from the advancements of large-scale pre-trained language models (PLMs). However, their effectiveness is often limited in theme-specific applications for specialized areas or industries, due to unique terminologies, incomplete contexts of user queries, and specialized search intents. To capture the theme-specific information and improve retrieval, we propose to use a corpus topical taxonomy, which outlines the latent topic structure of the corpus while reflecting user-interested aspects. We introduce ToTER (Topical Taxonomy Enhanced Retrieval) framework, which identifies the central topics of queries and documents with the guidance of the taxonomy, and exploits their topical relatedness to supplement missing contexts. As a plug-and-play framework, ToTER can be flexibly employed to enhance various PLM-based retrievers. Through extensive quantitative, ablative, and exploratory experiments on two real-world datasets, we ascertain the benefits of using topical taxonomy for retrieval in theme-specific applications and demonstrate the effectiveness of ToTER. |
| title | Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2403.04160 |