Toward Scalable Neural Dialogue State Tracking Model

Nouri, Elnaz; Hosseini-Asl, Ehsan

doi:10.48550/arxiv.1812.00899

Cited by 19 publications

(28 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of NBT is much better than previous DST methods. Inspired by this seminal work, a lot of neural DST approaches based on long short-term memory (LSTM) network [34,[40][41][42]59] and bidirectional gated recurrent unit (BiGRU) network [22,31,35,39,55,57] have been proposed for further improvements. These methods define DST as either a classification problem or a generation problem.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Slot Self-Attentive Dialogue State Tracking

Manotumruksa

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

An indispensable component in task-oriented dialogue systems is the dialogue state tracker, which keeps track of users' intentions in the course of conversation. The typical approach towards this goal is to fill in multiple pre-defined slots that are essential to complete the task. Although various dialogue state tracking methods have been proposed in recent years, most of them predict the value of each slot separately and fail to consider the correlations among slots. In this paper, we propose a slot self-attention mechanism that can learn the slot correlations automatically. Specifically, a slottoken attention is first utilized to obtain slot-specific features from the dialogue context. Then a stacked slot self-attention is applied on these features to learn the correlations among slots. We conduct comprehensive experiments on two multi-domain task-oriented dialogue datasets, including MultiWOZ 2.0 and MultiWOZ 2.1. The experimental results demonstrate that our approach achieves stateof-the-art performance on both datasets, verifying the necessity and effectiveness of taking slot correlations into consideration. CCS CONCEPTS• Computing methodologies → Natural language processing; Discourse, dialogue and pragmatics; Machine learning.

show abstract

Section: Related Workmentioning

confidence: 99%

“…We adopt joint goal accuracy [34] as the evaluation metric. Joint goal accuracy is defined as the ratio of dialogue turns for which the value of each slot is correctly predicted.…”

Section: Evaluation Metricmentioning

confidence: 99%

Slot Self-Attentive Dialogue State Tracking

Manotumruksa

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…MultiWOZ2.1 MultiWOZ2.0 MDBT (Ramadan et al, 2018) † -15.57% SpanPtr (Vinyals et al, 2015) -30.28% GLAD (Zhong et al, 2018) † -35.57% GCE (Nouri & Hosseini-Asl, 2018) † -36.27% HJST (Eric et al, 2019) 35.55% 38.40% DST Reader (single) 36.40% 39.41% DST Reader (ensemble) -42.12% TSCP (Lei et al, 2018) 37.12% 39.24% FJST (Eric et al, 2019) 38.00% 40.20% HyST (ensemble) 38.10% 44.24% SUMBT (Lee et al, 2019) † -46.65% TRADE (Wu et al, 2019) 45.60% 48.60% Ours 49.04% 50.52% processing in both encoding and decoding, they require much higher latency. TRADE shortens the latency by separating the decoding process among (domain, slot) pairs.…”

Section: Modelmentioning

confidence: 99%

Non-Autoregressive Dialog State Tracking

Le,

Socher,

Hoi

2020

Preprint

View full text Add to dashboard Cite

Recent efforts in Dialogue State Tracking (DST) for task-oriented dialogues have progressed toward open-vocabulary or generation-based approaches where the models can generate slot value candidates from the dialogue history itself. These approaches have shown good performance gain, especially in complicated dialogue domains with dynamic slot values. However, they fall short in two aspects:(1) they do not allow models to explicitly learn signals across domains and slots to detect potential dependencies among (domain, slot) pairs; and (2) existing models follow auto-regressive approaches which incur high time cost when the dialogue evolves over multiple domains and multiple turns. In this paper, we propose a novel framework of Non-Autoregressive Dialog State Tracking (NADST) which can factor in potential dependencies among domains and slots to optimize the models towards better prediction of dialogue states as a complete set rather than separate slots. In particular, the non-autoregressive nature of our method not only enables decoding in parallel to significantly reduce the latency of DST for realtime dialogue response generation, but also detect dependencies among slots at token level in addition to slot and domain level. Our empirical results show that our model achieves the state-of-the-art joint accuracy across all domains on the MultiWOZ 2.1 corpus, and the latency of our model is an order of magnitude lower than the previous state of the art as the dialogue history extends over time.

show abstract

“…To demonstrate the robustness of our model, we use the similar hyper-parameter settings for both datasets. Following the previous work (Ren et al, 2018;Zhong et al, 2018;Nouri and Hosseini-Asl, 2018), we concatenate the pre-trained GloVe embeddings (Pennington et al, 2014) and the character embeddings (Hashimoto et al, 2017) as the final word embeddings and keep them fixed when training. The epoch number of the alternate learning L, the epoch number of the generator learning N and the sampling times M for each bag are set to 5, 200 and 2 respectively.…”

Section: Implementation Detailsmentioning

confidence: 99%

Dialog State Tracking with Reinforced Data Augmentation

Yin¹,

Shang²,

Jiang³

et al. 2019

Preprint

View full text Add to dashboard Cite

Neural dialog state trackers are generally limited due to the lack of quantity and diversity of annotated training data. In this paper, we address this difficulty by proposing a reinforcement learning (RL) based framework for data augmentation that can generate highquality data to improve the neural state tracker. Specifically, we introduce a novel contextual bandit generator to learn fine-grained augmentation policies that can generate new effective instances by choosing suitable replacements for specific context. Moreover, by alternately learning between the generator and the state tracker, we can keep refining the generative policies to generate more high-quality training data for neural state tracker. Experimental results on the WoZ and MultiWoZ (restaurant) datasets demonstrate that the proposed framework significantly improves the performance over the state-of-the-art models, especially with limited training data.

show abstract

Toward Scalable Neural Dialogue State Tracking Model

Cited by 19 publications

References 0 publications

Slot Self-Attentive Dialogue State Tracking

Slot Self-Attentive Dialogue State Tracking

Non-Autoregressive Dialog State Tracking

Dialog State Tracking with Reinforced Data Augmentation

Contact Info

Product

Resources

About