mlsanityData to 7 Oct 2026

Improving Dialogue State Tracking by Joint Slot Modeling

arXiv 2109.14144 ↗First posted 29 Sep 2021cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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. Our implementation is available at https://github.com/CTinRay/Trippy-Joint.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 28 references that are in the map. First posted on arXiv 29 Sep 2021.

Builds on

22 of 28 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  3. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  4. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
  5. 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 201
  6. 2016Neural Belief Tracker: Data-Driven Dialogue State Trackingcited by 142
  7. 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
  8. 2020MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systemscited by 103
  9. 2020DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialoguecited by 89
  10. 2019Efficient Dialogue State Tracking by Selectively Overwriting Memorycited by 76
  11. 2019Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Trackingcited by 75
  12. 2020SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teachingcited by 71
10 more
  1. 2018Conversational AI: The Science Behind the Alexa Prizecited by 63
  2. 2019SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Trackingcited by 63
  3. 2019Dialog State Tracking: A Neural Reading Comprehension Approachcited by 62
  4. 2019Global-to-local Memory Pointer Networks for Task-Oriented Dialoguecited by 47
  5. 2020CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackerscited by 43
  6. 2018Large-Scale Multi-Domain Belief Tracking with Knowledge Sharingcited by 29
  7. 2018An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Trackingcited by 27
  8. 2020MA-DST: Multi-Attention Based Scalable Dialog State Trackingcited by 24
  9. 2017Scalable Multi-Domain Dialogue State Trackingcited by 22
  10. 2017An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialogcited by 17

Built on by

Not cited yet.