Knowledge Augmented BERT Mutual Network in Multi-turn Spoken Dialogues
This work addresses the challenge of long-term slot contexts in multi-turn spoken dialogues for SLU systems, representing an incremental improvement through hybrid methods.
The paper tackled the problem of modeling multi-turn dynamics in spoken language understanding (SLU) by proposing a BERT-based joint model with a knowledge attention module and gating mechanism to leverage dialogue contexts and filter external knowledge. The result showed considerable improvements over competitive baselines on two multi-turn dialogue datasets.
Modern spoken language understanding (SLU) systems rely on sophisticated semantic notions revealed in single utterances to detect intents and slots. However, they lack the capability of modeling multi-turn dynamics within a dialogue particularly in long-term slot contexts. Without external knowledge, depending on limited linguistic legitimacy within a word sequence may overlook deep semantic information across dialogue turns. In this paper, we propose to equip a BERT-based joint model with a knowledge attention module to mutually leverage dialogue contexts between two SLU tasks. A gating mechanism is further utilized to filter out irrelevant knowledge triples and to circumvent distracting comprehension. Experimental results in two complicated multi-turn dialogue datasets have demonstrate by mutually modeling two SLU tasks with filtered knowledge and dialogue contexts, our approach has considerable improvements compared with several competitive baselines.