A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking

• URL: http://arxiv.org/abs/2006.01554v2
• Date: Mon, 21 Dec 2020 02:03:40 GMT
• Title: A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking
• Authors: Yong Shan, Zekang Li, Jinchao Zhang, Fandong Meng, Yang Feng, Cheng Niu, Jie Zhou
• Abstract summary: We propose to enhance the dialogue state tracking (DST) through employing a contextual hierarchical attention network. We also propose an adaptive objective to alleviate the slot imbalance problem by dynamically adjusting weights of different slots during training. Experimental results show that our approach reaches 52.68% and 58.55% joint accuracy on MultiWOZ 2.0 and MultiWOZ 2.1 datasets.
• Score: 63.94927237189888
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent studies in dialogue state tracking (DST) leverage historical information to determine states which are generally represented as slot-value pairs. However, most of them have limitations to efficiently exploit relevant context due to the lack of a powerful mechanism for modeling interactions between the slot and the dialogue history. Besides, existing methods usually ignore the slot imbalance problem and treat all slots indiscriminately, which limits the learning of hard slots and eventually hurts overall performance. In this paper, we propose to enhance the DST through employing a contextual hierarchical attention network to not only discern relevant information at both word level and turn level but also learn contextual representations. We further propose an adaptive objective to alleviate the slot imbalance problem by dynamically adjust weights of different slots during training. Experimental results show that our approach reaches 52.68% and 58.55% joint accuracy on MultiWOZ 2.0 and MultiWOZ 2.1 datasets respectively and achieves new state-of-the-art performance with considerable improvements (+1.24% and +5.98%).

Related papers

• Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition [92.6211155264297]
  Vision models have gained increasing attention due to their simplicity and efficiency in Scene Text Recognition (STR) task. Recent vision models suffer from two problems: (1) the pure vision-based query results in attention drift, which usually causes poor recognition and is summarized as linguistic insensitive drift (LID) problem in this paper. We propose a $textbfL$inguistic $textbfP$erception $textbfV$ision model (LPV) which explores the linguistic capability of vision model for accurate text recognition.
  arXiv  Detail & Related papers  (2023-05-09T02:52:47Z)
• Dialogue State Distillation Network with Inter-Slot Contrastive Learning for Dialogue State Tracking [25.722458066685046]
  Dialogue State Tracking (DST) aims to extract users' intentions from the dialogue history. Currently, most existing approaches suffer from error propagation and are unable to dynamically select relevant information. We propose a Dialogue State Distillation Network (DSDN) to utilize relevant information of previous dialogue states.
  arXiv  Detail & Related papers  (2023-02-16T11:05:24Z)
• Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding [103.94325597273316]
  We present a novel approach that iterates on augmentation quality by applying weakly-supervised filters. We evaluate our methods on the emotion and act classification tasks in DailyDialog and the intent classification task in Facebook Multilingual Task-Oriented Dialogue. For DailyDialog specifically, using 10% of the ground truth data we outperform the current state-of-the-art model which uses 100% of the data.
  arXiv  Detail & Related papers  (2022-10-25T17:01:30Z)
• LUNA: Learning Slot-Turn Alignment for Dialogue State Tracking [21.80577241399013]
  Dialogue state tracking (DST) aims to predict the current dialogue state given the dialogue history. Existing methods generally exploit the utterances of all dialogue turns to assign value for each slot. We propose LUNA, a sLot-tUrN Alignment enhanced approach. It first explicitly aligns each slot with its most relevant utterance, then further predicts the corresponding value based on this aligned utterance instead of all dialogue utterances.
  arXiv  Detail & Related papers  (2022-05-05T10:18:23Z)
• Slot Self-Attentive Dialogue State Tracking [22.187581131353948]
  We propose a slot self-attention mechanism that can learn the slot correlations automatically. We conduct comprehensive experiments on two multi-domain task-oriented dialogue datasets.
  arXiv  Detail & Related papers  (2021-01-22T22:48:51Z)
• Improving Limited Labeled Dialogue State Tracking with Self-Supervision [91.68515201803986]
  Existing dialogue state tracking (DST) models require plenty of labeled data. We present and investigate two self-supervised objectives: preserving latent consistency and modeling conversational behavior. Our proposed self-supervised signals can improve joint goal accuracy by 8.95% when only 1% labeled data is used.
  arXiv  Detail & Related papers  (2020-10-26T21:57:42Z)
• CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers [92.5628632009802]
  We propose controllable counterfactuals (CoCo) to bridge the gap and evaluate dialogue state tracking (DST) models on novel scenarios. CoCo generates novel conversation scenarios in two steps: (i) counterfactual goal generation at turn-level by dropping and adding slots followed by replacing slot values, and (ii) counterfactual conversation generation that is conditioned on (i) and consistent with the dialogue flow. Human evaluations show that COCO-generated conversations perfectly reflect the underlying user goal with more than 95% accuracy and are as human-like as the original conversations.
  arXiv  Detail & Related papers  (2020-10-24T09:39:35Z)
• From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap [41.577548543163196]
  We propose using machine reading comprehension (RC) in state tracking from two perspectives: model architectures and datasets. Our method achieves near the current state-of-the-art in joint goal accuracy on MultiWOZ 2.1 given full training data.
  arXiv  Detail & Related papers  (2020-04-13T09:00:03Z)
• Non-Autoregressive Dialog State Tracking [122.2328875457225]
  We propose a novel framework of Non-Autoregressive Dialog State Tracking (NADST) NADST 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. Our results show that our model achieves the state-of-the-art joint accuracy across all domains on the MultiWOZ 2.1 corpus.
  arXiv  Detail & Related papers  (2020-02-19T06:39:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.