نماذج تتبع حكومية الحوار تلعب دورا مهما في نظام حوار موجه نحو المهام.ومع ذلك، فإن معظمهم يصطادون أنواع الفتحات بشكل مشروط بإدخال المدخلات بشكل مشروط.نكتشف أنه قد يتسبب في الخلط النموذج من خلال أنواع الفتحات التي تشترك في نفس نوع البيانات.لتخفيف هذه المشكلة، نقترح Trippy-MRF و Trippy-LSTM النماذج التي تطرح الفتحات بشكل مشترك.تظهر نتائجنا أنهم قادرون على تخفيف الارتباك المذكور أعلاه، ويدفعون الحديث في DataSet MultiWoz 2.1 من 58.7 إلى 61.3.
Dialogue state tracking models play an important role in a task-oriented dialogue system. However, most of them model the slot types conditionally independently given the input. We discover that it may cause the model to be confused by slot types that share the same data type. To mitigate this issue, we propose TripPy-MRF and TripPy-LSTM that models the slots jointly. Our results show that they are able to alleviate the confusion mentioned above, and they push the state-of-the-art on dataset MultiWoz 2.1 from 58.7 to 61.3.
References used
https://aclanthology.org/
Sequence-to-sequence models have been applied to a wide variety of NLP tasks, but how to properly use them for dialogue state tracking has not been systematically investigated. In this paper, we study this problem from the perspectives of pre-trainin
Abstract Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined s
Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data. In this work, we propose to transfer the cross-task knowledge from genera
This paper aims at providing a comprehensive overview of recent developments in dialogue state tracking (DST) for task-oriented conversational systems. We introduce the task, the main datasets that have been exploited as well as their evaluation metr
Recently, the focus of dialogue state tracking has expanded from single domain to multiple domains. The task is characterized by the shared slots between domains. As the scenario gets more complex, the out-of-vocabulary problem also becomes severer.