Dialog State Tracking: A Neural Reading Comprehension Approach

Abstract

Dialog state tracking is used to estimate the current belief state of a dialog given all the preceding conversation. Machine reading comprehension, on the other hand, focuses on building systems that read passages of text and answer questions that require some understanding of passages. We formulate dialog state tracking as a reading comprehension task to answer the question what is the state of the current dialog? after reading conversational context. In contrast to traditional state tracking methods where the dialog state is often predicted as a distribution over a closed set of all the possible slot values within an ontology, our method uses a simple attention-based neural network to point to the slot values within the conversation. Experiments on MultiWOZ-2.0 cross-domain dialog dataset show that our simple system can obtain similar accuracies compared to the previous more complex methods. By exploiting recent advances in contextual word embeddings, adding a model that explicitly tracks whether a slot value should be carried over to the next turn, and combining our method with a traditional joint state tracking method that relies on closed set vocabulary, we can obtain a joint-goal accuracy of 47.33% on the standard test split, exceeding current state-of-the-art by 11.75%**.

Recent advances and challenges in task-oriented dialog systems

“…However, this approach falls short when facing previously unseen values at run time. Besides, there are also some works formulating the DST task as a reading comprehension task [28,29].…”

“…The former type does not assume a fixed vocabulary for the slot, which means the model cannot predict the values by classification. For free-form slot, one could generate the value directly [4,31] or predict the span of the value in the utterance [28,32]. In generative methods, they often use a decoder to generate the value of a slot word by word from a large vocabulary.…”

Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation

“…NBT-CNN O(mn) MD-DST (Rastogi et al, 2017) O(n) GLAD O(mn) StateNet PSI (Ren et al, 2018) O(n) TRADE (Wu et al, 2019) O(n) HyST (Goel et al, 2019) O(n) DSTRead (Gao et al, 2019) O(n) domain dialogue state tracking dataset, MultiWoZ , a representation of dialogue state consists of a hierarchical structure of domain, slot, and value is proposed. This is a more practical scenario since dialogues often include multiple domains simultaneously.…”

“…However, TRADE does not report its performance on the WoZ2.0 dataset which does not have the name slot. DSTRead (Gao et al, 2019) formulate the dialogue state tracking task as a reading comprehension problem by asking slot specified questions to the BERT model and find the answer span in the dialogue history for each of the pre-defined combined slot. Thus its inference time complexity is still O(n).…”

Neural Dialogue State Tracking with Temporally Expressive Networks

“…The models used for comparison include NBT-DNN , NBT-CNN (Mrksic et al, 2017), Scalable (Rastogi et al, 2017), MemN2N (Liu and Perez, 2017), PtrNet (Xu andHu, 2018), LargeScale (Ramadan et al, 2018), GLAD (Ramadan et al, 2018), GCE (Nouri and Hosseini-Asl, 2018), StateNetPSI (Ren et al, 2018), SUMBT , HyST (Goel et al, 2019), DSTRead+JST (Gao et al, 2019), TRADE (Wu et al, 2019), COMER (Ren et al, 2019), DSTQA (Zhou and Small, 2019), MERET (Huang et al, 2020) and SST (Chen et al, 2020).…”