PSentScore: Evaluating Sentiment Polarity in Dialogue Summarization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914782201774080 |
|---|---|
| author | Zhou, Yongxin Ringeval, Fabien Portet, François |
| author_facet | Zhou, Yongxin Ringeval, Fabien Portet, François |
| contents | Automatic dialogue summarization is a well-established task with the goal of distilling the most crucial information from human conversations into concise textual summaries. However, most existing research has predominantly focused on summarizing factual information, neglecting the affective content, which can hold valuable insights for analyzing, monitoring, or facilitating human interactions. In this paper, we introduce and assess a set of measures PSentScore, aimed at quantifying the preservation of affective content in dialogue summaries. Our findings indicate that state-of-the-art summarization models do not preserve well the affective content within their summaries. Moreover, we demonstrate that a careful selection of the training set for dialogue samples can lead to improved preservation of affective content in the generated summaries, albeit with a minor reduction in content-related metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_12371 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | PSentScore: Evaluating Sentiment Polarity in Dialogue Summarization Zhou, Yongxin Ringeval, Fabien Portet, François Computation and Language Automatic dialogue summarization is a well-established task with the goal of distilling the most crucial information from human conversations into concise textual summaries. However, most existing research has predominantly focused on summarizing factual information, neglecting the affective content, which can hold valuable insights for analyzing, monitoring, or facilitating human interactions. In this paper, we introduce and assess a set of measures PSentScore, aimed at quantifying the preservation of affective content in dialogue summaries. Our findings indicate that state-of-the-art summarization models do not preserve well the affective content within their summaries. Moreover, we demonstrate that a careful selection of the training set for dialogue samples can lead to improved preservation of affective content in the generated summaries, albeit with a minor reduction in content-related metrics. |
| title | PSentScore: Evaluating Sentiment Polarity in Dialogue Summarization |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2307.12371 |