Description-Based Text Similarity
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914884063592448 |
|---|---|
| author | Ravfogel, Shauli Pyatkin, Valentina Cohen, Amir DN Manevich, Avshalom Goldberg, Yoav |
| author_facet | Ravfogel, Shauli Pyatkin, Valentina Cohen, Amir DN Manevich, Avshalom Goldberg, Yoav |
| contents | Identifying texts with a given semantics is central for many information seeking scenarios. Similarity search over vector embeddings appear to be central to this ability, yet the similarity reflected in current text embeddings is corpus-driven, and is inconsistent and sub-optimal for many use cases. What, then, is a good notion of similarity for effective retrieval of text?
We identify the need to search for texts based on abstract descriptions of their content, and the corresponding notion of \emph{description based similarity}. We demonstrate the inadequacy of current text embeddings and propose an alternative model that significantly improves when used in standard nearest neighbor search. The model is trained using positive and negative pairs sourced through prompting a LLM, demonstrating how data from LLMs can be used for creating new capabilities not immediately possible using the original model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_12517 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Description-Based Text Similarity Ravfogel, Shauli Pyatkin, Valentina Cohen, Amir DN Manevich, Avshalom Goldberg, Yoav Computation and Language Information Retrieval Machine Learning Identifying texts with a given semantics is central for many information seeking scenarios. Similarity search over vector embeddings appear to be central to this ability, yet the similarity reflected in current text embeddings is corpus-driven, and is inconsistent and sub-optimal for many use cases. What, then, is a good notion of similarity for effective retrieval of text? We identify the need to search for texts based on abstract descriptions of their content, and the corresponding notion of \emph{description based similarity}. We demonstrate the inadequacy of current text embeddings and propose an alternative model that significantly improves when used in standard nearest neighbor search. The model is trained using positive and negative pairs sourced through prompting a LLM, demonstrating how data from LLMs can be used for creating new capabilities not immediately possible using the original model. |
| title | Description-Based Text Similarity |
| topic | Computation and Language Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2305.12517 |