Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.16371 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915404389023744 |
|---|---|
| author | Kamateri, Eleni Chikkamath, Renukswamy Salampasis, Michail Andersson, Linda Endres, Markus |
| author_facet | Kamateri, Eleni Chikkamath, Renukswamy Salampasis, Michail Andersson, Linda Endres, Markus |
| contents | Effective query formulation is a key challenge in long-document Information Retrieval (IR). This challenge is particularly acute in domain-specific contexts like patent retrieval, where documents are lengthy, linguistically complex, and encompass multiple interrelated technical topics. In this work, we present the application of recent extractive and abstractive summarization methods for generating concise, purpose-specific summaries of patent documents. We further assess the utility of these automatically generated summaries as surrogate queries across three benchmark patent datasets and compare their retrieval performance against conventional approaches that use entire patent sections. Experimental results show that summarization-based queries significantly improve prior-art retrieval effectiveness, highlighting their potential as an efficient alternative to traditional query formulation techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16371 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing patent retrieval using automated patent summarization Kamateri, Eleni Chikkamath, Renukswamy Salampasis, Michail Andersson, Linda Endres, Markus Information Retrieval Effective query formulation is a key challenge in long-document Information Retrieval (IR). This challenge is particularly acute in domain-specific contexts like patent retrieval, where documents are lengthy, linguistically complex, and encompass multiple interrelated technical topics. In this work, we present the application of recent extractive and abstractive summarization methods for generating concise, purpose-specific summaries of patent documents. We further assess the utility of these automatically generated summaries as surrogate queries across three benchmark patent datasets and compare their retrieval performance against conventional approaches that use entire patent sections. Experimental results show that summarization-based queries significantly improve prior-art retrieval effectiveness, highlighting their potential as an efficient alternative to traditional query formulation techniques. |
| title | Enhancing patent retrieval using automated patent summarization |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2507.16371 |