Leveraging Explicit Reasoning for Inference Integration in Commonsense-Augmented Dialogue Models
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_ | 1866917897463398400 |
|---|---|
| author | Finch, Sarah E. Choi, Jinho D. |
| author_facet | Finch, Sarah E. Choi, Jinho D. |
| contents | Open-domain dialogue systems need to grasp social commonsense to understand and respond effectively to human users. Commonsense-augmented dialogue models have been proposed that aim to infer commonsense knowledge from dialogue contexts in order to improve response quality. However, existing approaches to commonsense-augmented dialogue rely on implicit reasoning to integrate commonsense inferences during response generation. In this study, we explore the impact of explicit reasoning against implicit reasoning over commonsense for dialogue response generation. Our findings demonstrate that separating commonsense reasoning into explicit steps for generating, selecting, and integrating commonsense into responses leads to better dialogue interactions, improving naturalness, engagement, specificity, and overall quality. Subsequent analyses of these findings unveil insights into the effectiveness of various types of commonsense in generating responses and the particular response traits enhanced through explicit reasoning for commonsense integration. Our work advances research in open-domain dialogue by achieving a new state-of-the-art in commonsense-augmented response generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09138 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Explicit Reasoning for Inference Integration in Commonsense-Augmented Dialogue Models Finch, Sarah E. Choi, Jinho D. Computation and Language Open-domain dialogue systems need to grasp social commonsense to understand and respond effectively to human users. Commonsense-augmented dialogue models have been proposed that aim to infer commonsense knowledge from dialogue contexts in order to improve response quality. However, existing approaches to commonsense-augmented dialogue rely on implicit reasoning to integrate commonsense inferences during response generation. In this study, we explore the impact of explicit reasoning against implicit reasoning over commonsense for dialogue response generation. Our findings demonstrate that separating commonsense reasoning into explicit steps for generating, selecting, and integrating commonsense into responses leads to better dialogue interactions, improving naturalness, engagement, specificity, and overall quality. Subsequent analyses of these findings unveil insights into the effectiveness of various types of commonsense in generating responses and the particular response traits enhanced through explicit reasoning for commonsense integration. Our work advances research in open-domain dialogue by achieving a new state-of-the-art in commonsense-augmented response generation. |
| title | Leveraging Explicit Reasoning for Inference Integration in Commonsense-Augmented Dialogue Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.09138 |