Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking

Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics (*SEM), pages 154–167 Barcelona, Spain (Online), December 12–13, 2020 154 Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking Jian-Guo Zhang1∗ Kazuma Hashimoto2† Chien-Sheng Wu2 Yao Wan3 Philip S. Yu1 Richard Socher2 Caiming Xiong2 1 University of Illinois at Chicago, Chicago, USA 2Salesforce Research, Palo Alto, USA 3Huazhong University of Science and Technology, Wuhan, China {jzhan51,psyu}@uic.edu, wanyao@hust.edu.cn {k.hashimoto,wu.jason,rsocher,cxiong}@salesforce.com Abstract Dialog state tracking (DST) is a core compo- nent in task-oriented dialog systems. Exist- ing approaches for DST mainly fall into one of two categories, namely, ontology-based and ontology-free methods. An ontology-based method selects a value from a candidate-value list for each target slot, while an ontology-free method extracts spans from dialog contexts. Recent work introduced a BERT-based model to strike a balance between the two methods by pre-defining categorical and non-categorical slots. However, it is not clear enough which slots are better handled by either of the two slot types, and the way to use the pre-trained model has not been well investigated. In this paper, we propose a simple yet effective dual- strategy model for DST, by adapting a single BERT-style reading comprehension model to jointly handle both the categorical and non- categorical slots. Our experiments on the Mul- tiWOZ datasets show that our method signif- icantly outperforms the BERT-based counter- part, finding that the key is a deep interaction between the domain-slot and context informa- tion. When evaluated on noisy (MultiWOZ 2.0) and cleaner (MultiWOZ 2.1) settings, our method performs competitively and robustly across the two different settings. Our method sets the new state of the art in the noisy setting, while performing more robustly than the best model in the cleaner setting. We also conduct a comprehensive error analysis on the dataset, including the effects of the dual strategy for each slot, to facilitate future research. 1 Introduction ∗Work done while the first author was an intern at Sales- force Research. †Corresponding author. This work is licensed under a Creative Commons At- tribution 4.0 International License. License details: http: //creativecommons.org/licenses/by/4.0/. I am looking for a place to stay that has cheap price range and it should be in a type of hotel. User System Okay, do you have a specific area you want to stay in? No, I just need to make sure it’s cheap. Oh, and I need parking. I found 1 cheap hotel for you that includes parking. Do you like me to book it? Yes, please. 6 people 3 nights starting on Tuesday. Booking was successful. Reference number is: 7gawk763. Anything else I can do for you? I also need to book an expensive restaurant with Japanese food. Dialog State Tracking (hotel, price range, cheap), (hotel, type hotel) (hotel, price range, cheap), (hotel, type, hotel), (hotel, parking, yes) (hotel, price range, cheap), (hotel, type, hotel), (hotel, parking, yes), (hotel, book day, Tuesday), (hotel, book people, 6), (hotel, book stay, 3) (hotel, price range, cheap), (hotel, type, hotel), (hotel, parking, …

Content truncated to 500 words