Neural Passage Quality Estimation for Static Pruning
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_ | 1866914874680934400 |
|---|---|
| author | Chang, Xuejun Mishra, Debabrata Macdonald, Craig MacAvaney, Sean |
| author_facet | Chang, Xuejun Mishra, Debabrata Macdonald, Craig MacAvaney, Sean |
| contents | Neural networks -- especially those that use large, pre-trained language models -- have improved search engines in various ways. Most prominently, they can estimate the relevance of a passage or document to a user's query. In this work, we depart from this direction by exploring whether neural networks can effectively predict which of a document's passages are unlikely to be relevant to any query submitted to the search engine. We refer to this query-agnostic estimation of passage relevance as a passage's quality. We find that our novel methods for estimating passage quality allow passage corpora to be pruned considerably while maintaining statistically equivalent effectiveness; our best methods can consistently prune >25% of passages in a corpora, across various retrieval pipelines. Such substantial pruning reduces the operating costs of neural search engines in terms of computing resources, power usage, and carbon footprint -- both when processing queries (thanks to a smaller index size) and when indexing (lightweight models can prune low-quality passages prior to the costly dense or learned sparse encoding step). This work sets the stage for developing more advanced neural "learning-what-to-index" methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_12170 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neural Passage Quality Estimation for Static Pruning Chang, Xuejun Mishra, Debabrata Macdonald, Craig MacAvaney, Sean Information Retrieval Neural networks -- especially those that use large, pre-trained language models -- have improved search engines in various ways. Most prominently, they can estimate the relevance of a passage or document to a user's query. In this work, we depart from this direction by exploring whether neural networks can effectively predict which of a document's passages are unlikely to be relevant to any query submitted to the search engine. We refer to this query-agnostic estimation of passage relevance as a passage's quality. We find that our novel methods for estimating passage quality allow passage corpora to be pruned considerably while maintaining statistically equivalent effectiveness; our best methods can consistently prune >25% of passages in a corpora, across various retrieval pipelines. Such substantial pruning reduces the operating costs of neural search engines in terms of computing resources, power usage, and carbon footprint -- both when processing queries (thanks to a smaller index size) and when indexing (lightweight models can prune low-quality passages prior to the costly dense or learned sparse encoding step). This work sets the stage for developing more advanced neural "learning-what-to-index" methods. |
| title | Neural Passage Quality Estimation for Static Pruning |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2407.12170 |