Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2405.01403 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909188142137344 |
|---|---|
| author | Ferreira, Patrícia Martins, Daniel Alves, Ana Silva, Catarina Oliveira, Hugo Gonçalo |
| author_facet | Ferreira, Patrícia Martins, Daniel Alves, Ana Silva, Catarina Oliveira, Hugo Gonçalo |
| contents | The design of dialogue flows is a critical but time-consuming task when developing task-oriented dialogue (TOD) systems. We propose an approach for the unsupervised discovery of flows from dialogue history, thus making the process applicable to any domain for which such an history is available. Briefly, utterances are represented in a vector space and clustered according to their semantic similarity. Clusters, which can be seen as dialogue states, are then used as the vertices of a transition graph for representing the flows visually. We present concrete examples of flows, discovered from MultiWOZ, a public TOD dataset. We further elaborate on their significance and relevance for the underlying conversations and introduce an automatic validation metric for their assessment. Experimental results demonstrate the potential of the proposed approach for extracting meaningful flows from task-oriented conversations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_01403 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unsupervised Flow Discovery from Task-oriented Dialogues Ferreira, Patrícia Martins, Daniel Alves, Ana Silva, Catarina Oliveira, Hugo Gonçalo Computation and Language Artificial Intelligence The design of dialogue flows is a critical but time-consuming task when developing task-oriented dialogue (TOD) systems. We propose an approach for the unsupervised discovery of flows from dialogue history, thus making the process applicable to any domain for which such an history is available. Briefly, utterances are represented in a vector space and clustered according to their semantic similarity. Clusters, which can be seen as dialogue states, are then used as the vertices of a transition graph for representing the flows visually. We present concrete examples of flows, discovered from MultiWOZ, a public TOD dataset. We further elaborate on their significance and relevance for the underlying conversations and introduce an automatic validation metric for their assessment. Experimental results demonstrate the potential of the proposed approach for extracting meaningful flows from task-oriented conversations. |
| title | Unsupervised Flow Discovery from Task-oriented Dialogues |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2405.01403 |