Dialogue Coherence Assessment Without Explicit Dialogue Act Labels
This work addresses the problem of improving dialogue coherence assessment for natural language processing applications by reducing reliance on explicit labels, though it is incremental as it builds on existing multi-task learning methods.
The paper tackled the problem of dialogue coherence assessment by addressing limitations of existing models that rely on entity mentions and explicit dialogue act labels, introducing a multi-task learning approach that uses dialogue act prediction as an auxiliary task to improve utterance representations. The result showed substantial performance gains, with more than 20 accuracy points improvement on the DailyDialogue corpus and competitive performance on the SwitchBoard corpus.
Recent dialogue coherence models use the coherence features designed for monologue texts, e.g. nominal entities, to represent utterances and then explicitly augment them with dialogue-relevant features, e.g., dialogue act labels. It indicates two drawbacks, (a) semantics of utterances is limited to entity mentions, and (b) the performance of coherence models strongly relies on the quality of the input dialogue act labels. We address these issues by introducing a novel approach to dialogue coherence assessment. We use dialogue act prediction as an auxiliary task in a multi-task learning scenario to obtain informative utterance representations for coherence assessment. Our approach alleviates the need for explicit dialogue act labels during evaluation. The results of our experiments show that our model substantially (more than 20 accuracy points) outperforms its strong competitors on the DailyDialogue corpus, and performs on par with them on the SwitchBoard corpus for ranking dialogues concerning their coherence.