Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation
This work addresses a specific bottleneck in dialogue processing for improving coherence and efficiency in conversational AI systems, representing an incremental advance over prior methods.
The paper tackles the problem of incomplete utterance rewriting in dialogue systems, where existing methods often produce irrelevant or redundant tokens, by proposing a multi-task learning framework with editing operation guidance and a two-dimensional utterance augmentation strategy, achieving state-of-the-art performance on three datasets in both open-domain and task-oriented dialogue.
Although existing fashionable generation methods on Incomplete Utterance Rewriting (IUR) can generate coherent utterances, they often result in the inclusion of irrelevant and redundant tokens in rewritten utterances due to their inability to focus on critical tokens in dialogue context. Furthermore, the limited size of the training datasets also contributes to the insufficient training of the IUR model. To address the first issue, we propose a multi-task learning framework EO-IUR (Editing Operation-guided Incomplete Utterance Rewriting) that introduces the editing operation labels generated by sequence labeling module to guide generation model to focus on critical tokens. Furthermore, we introduce a token-level heterogeneous graph to represent dialogues. To address the second issue, we propose a two-dimensional utterance augmentation strategy, namely editing operation-based incomplete utterance augmentation and LLM-based historical utterance augmentation. The experimental results on three datasets demonstrate that our EO-IUR outperforms previous state-of-the-art (SOTA) baselines in both open-domain and task-oriented dialogue. The code will be available at https://github.com/Dewset/EO-IUR.