Recommendations by Concise User Profiles from Review Text
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_ | 1866912248759320576 |
|---|---|
| author | Torbati, Ghazaleh Haratinezhad Tigunova, Anna Yates, Andrew Weikum, Gerhard |
| author_facet | Torbati, Ghazaleh Haratinezhad Tigunova, Anna Yates, Andrew Weikum, Gerhard |
| contents | Recommender systems perform well for popular items and users with ample interactions (likes, ratings etc.). This work addresses the difficult and underexplored case of users who have very sparse interactions but post informative review texts. This setting naturally calls for encoding user-specific text with large language models (LLM). However, feeding the full text of all reviews through an LLM has a weak signal-to-noise ratio and incurs high costs of processed tokens. This paper addresses these two issues. It presents a light-weight framework, called CUP, which first computes concise user profiles and feeds only these into the training of transformer-based recommenders. For user profiles, we devise various techniques to select the most informative cues from noisy reviews. Experiments, with book reviews data, show that fine-tuning a small language model with judiciously constructed profiles achieves the best performance, even in comparison to LLM-generated rankings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_01314 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Recommendations by Concise User Profiles from Review Text Torbati, Ghazaleh Haratinezhad Tigunova, Anna Yates, Andrew Weikum, Gerhard Information Retrieval Recommender systems perform well for popular items and users with ample interactions (likes, ratings etc.). This work addresses the difficult and underexplored case of users who have very sparse interactions but post informative review texts. This setting naturally calls for encoding user-specific text with large language models (LLM). However, feeding the full text of all reviews through an LLM has a weak signal-to-noise ratio and incurs high costs of processed tokens. This paper addresses these two issues. It presents a light-weight framework, called CUP, which first computes concise user profiles and feeds only these into the training of transformer-based recommenders. For user profiles, we devise various techniques to select the most informative cues from noisy reviews. Experiments, with book reviews data, show that fine-tuning a small language model with judiciously constructed profiles achieves the best performance, even in comparison to LLM-generated rankings. |
| title | Recommendations by Concise User Profiles from Review Text |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2311.01314 |