Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.08322 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911053700399104 |
|---|---|
| author | Cao, Yixuan Chen, Zhengrong Xia, Chengxuan Wu, Kun Luo, Ping |
| author_facet | Cao, Yixuan Chen, Zhengrong Xia, Chengxuan Wu, Kun Luo, Ping |
| contents | Quantitative facts are continually generated by companies and governments, supporting data-driven decision-making. While common facts are structured, many long-tail quantitative facts remain buried in unstructured documents, making them difficult to access. We propose the task of Quantity Retrieval: given a description of a quantitative fact, the system returns the relevant value and supporting evidence. Understanding quantity semantics in context is essential for this task. We introduce a framework based on description parsing that converts text into structured (description, quantity) pairs for effective retrieval. To improve learning, we construct a large paraphrase dataset using weak supervision based on quantity co-occurrence. We evaluate our approach on a large corpus of financial annual reports and a newly annotated quantity description dataset. Our method significantly improves top-1 retrieval accuracy from 30.98 percent to 64.66 percent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_08322 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Efficient Quantity Retrieval from Text:An Approach via Description Parsing and Weak Supervision Cao, Yixuan Chen, Zhengrong Xia, Chengxuan Wu, Kun Luo, Ping Information Retrieval Machine Learning Quantitative facts are continually generated by companies and governments, supporting data-driven decision-making. While common facts are structured, many long-tail quantitative facts remain buried in unstructured documents, making them difficult to access. We propose the task of Quantity Retrieval: given a description of a quantitative fact, the system returns the relevant value and supporting evidence. Understanding quantity semantics in context is essential for this task. We introduce a framework based on description parsing that converts text into structured (description, quantity) pairs for effective retrieval. To improve learning, we construct a large paraphrase dataset using weak supervision based on quantity co-occurrence. We evaluate our approach on a large corpus of financial annual reports and a newly annotated quantity description dataset. Our method significantly improves top-1 retrieval accuracy from 30.98 percent to 64.66 percent. |
| title | Towards Efficient Quantity Retrieval from Text:An Approach via Description Parsing and Weak Supervision |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2507.08322 |