Coherence Models for Dialogue
By Alessandra Cervone, Evgeny A. Stepanov, Giuseppe Riccardi. 2018
25 citations recorded by the source corpus.
Coherence across multiple turns is a major challenge for state-of-the-art dialogue models. Arguably the most successful approach to automatically learning text coherence is the entity grid, which relies on modelling patterns of distribution of entities across multiple sentences of a text. Originally applied to the evaluation of automatic summaries and the news genre, among its many extensions, this model has also been successfully used to assess dialogue coherence. Nevertheless, both the original grid and its extensions do not model intents, a crucial aspect that has been studied widely in the literature in connection to dialogue structure. We propose to augment the original grid document representation for dialogue with the intentional structure of the conversation. Our models outperform the original grid representation on both text discrimination and insertion, the two main standard tasks for coherence assessment across three different dialogue datasets, confirming that intents play a key role in modelling dialogue coherence.
Subfields: Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Dilek Z. Hakkani-Tür
- Behnam Hedayatnia
- Raefer Gabriel
- Anu Venkatesh
- Chandra Khatri
- Liang Lin
- Luis Fernando D'Haro
- Haizhou Li
Citations in the corpus
- Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators (2019, background): “• Entity Grid: Cervone et al. (2018); Barzilay and Lapata (2008) show that entities and DA transitions across turns can be strong features for assessing dialog coherence.”
- Towards Quantifiable Dialogue Coherence Evaluation (2021, methodology): “1The code and trained checkpoints are available at https: //github.com/James-Yip/QuantiDCE. systems (Cervone et al., 2018).”
- DynaEval: Unifying Turn and Dialogue Level Evaluation (2021, background): “…they still face difficulties in mimicking human conversations in the sense that they lack certain conversation-level attributes, such as coherence (Cervone et al., 2018), consistency (Welleck et al., 2019; Nie et al., 2020), diversity (Li et al., 2016; Wu et al., 2020) and engagement…”
- FineD-Eval: Fine-grained Automatic Dialogue-Level Evaluation (2022, result): “This strategy has been widely adopted in previous dialogue coherence studies (Cervone et al., 2018; Mesgar et al., 2020; Zhang et al., 2021a).”