HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Tracking
원문 초록
Recent works on end-to-end trainable neural network based approaches have demonstrated state-of-the-art results on dialogue state tracking. The best performing approaches estimate a probability distribution over all possible slot values. However, these approaches do not scale for large value sets commonly present in real-life applications and are not ideal for tracking slot values that were not observed in the training set. To tackle these issues, candidate-generation-based approaches have been proposed. These approaches estimate a set of values that are possible at each turn based on the conversation history and/or language understanding outputs, and hence enable state tracking over unseen values and large value sets however, they fall short in terms of performance in comparison to the first group. In this work, we analyze the performance of these two alternative dialogue state tracking methods, and present a hybrid approach (HyST) which learns the appropriate method for each slot type. To demonstrate the effectiveness of HyST on a rich-set of slot types, we experiment with the recently released MultiWOZ-2.0 multi-domain, task-oriented dialogue-dataset. Our experiments show that HyST scales to multi-domain applications. Our best performing model results in a relative improvement of 24% and 10% over the previous SOTA and our best baseline respectively.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking
Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking
Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics
Amendable Generation for Dialogue State Tracking
Dialogue State Tracking with a Language Model using Schema-Driven Prompting
Effective Sequence-to-Sequence Dialogue State Tracking
토론
이 논문과 연결된 포럼 글이 아직 없습니다.