SumRec: A Framework for Recommendation using Open-Domain Dialogue
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_ | 1866929236242071552 |
|---|---|
| author | Asahara, Ryutaro Takahashi, Masaki Iwahashi, Chiho Inaba, Michimasa |
| author_facet | Asahara, Ryutaro Takahashi, Masaki Iwahashi, Chiho Inaba, Michimasa |
| contents | Chat dialogues contain considerable useful information about a speaker's interests, preferences, and experiences.Thus, knowledge from open-domain chat dialogue can be used to personalize various systems and offer recommendations for advanced information.This study proposed a novel framework SumRec for recommending information from open-domain chat dialogue.The study also examined the framework using ChatRec, a newly constructed dataset for training and evaluation. To extract the speaker and item characteristics, the SumRec framework employs a large language model (LLM) to generate a summary of the speaker information from a dialogue and to recommend information about an item according to the type of user.The speaker and item information are then input into a score estimation model, generating a recommendation score.Experimental results show that the SumRec framework provides better recommendations than the baseline method of using dialogues and item descriptions in their original form. Our dataset and code is publicly available at https://github.com/Ryutaro-A/SumRec |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_04523 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SumRec: A Framework for Recommendation using Open-Domain Dialogue Asahara, Ryutaro Takahashi, Masaki Iwahashi, Chiho Inaba, Michimasa Machine Learning Computation and Language Chat dialogues contain considerable useful information about a speaker's interests, preferences, and experiences.Thus, knowledge from open-domain chat dialogue can be used to personalize various systems and offer recommendations for advanced information.This study proposed a novel framework SumRec for recommending information from open-domain chat dialogue.The study also examined the framework using ChatRec, a newly constructed dataset for training and evaluation. To extract the speaker and item characteristics, the SumRec framework employs a large language model (LLM) to generate a summary of the speaker information from a dialogue and to recommend information about an item according to the type of user.The speaker and item information are then input into a score estimation model, generating a recommendation score.Experimental results show that the SumRec framework provides better recommendations than the baseline method of using dialogues and item descriptions in their original form. Our dataset and code is publicly available at https://github.com/Ryutaro-A/SumRec |
| title | SumRec: A Framework for Recommendation using Open-Domain Dialogue |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2402.04523 |