Towards Universal Dialogue Act Tagging for Task-Oriented Dialogues

@article{Paul2019TowardsUD,
  title={Towards Universal Dialogue Act Tagging for Task-Oriented Dialogues},
  author={Shachi Paul and Rahul Goel and Dilek Z. Hakkani-T{\"u}r},
  journal={ArXiv},
  year={2019},
  volume={abs/1907.03020}
}
Machine learning approaches for building task-oriented dialogue systems require large conversational datasets with labels to train on. We are interested in building task-oriented dialogue systems from human-human conversations, which may be available in ample amounts in existing customer care center logs or can be collected from crowd workers. Annotating these datasets can be prohibitively expensive. Recently multiple annotated task-oriented human-machine dialogue datasets have been released… 

Figures and Tables from this paper

TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue
TLDR
The experimental results show that the pre-trained task- oriented dialogue BERT (ToD-BERT) surpasses BERT and other strong baselines in four downstream task-oriented dialogue applications, including intention detection, dialogue state tracking, dialogue act prediction, and response selection.
Simple Data Augmentation with the Mask Token Improves Domain Adaptation for Dialog Act Tagging
TLDR
MaskAugment, a controllable mechanism that augments text input by leveraging the pre-trained Mask token from BERT model is proposed, and an unsupervised teacher-student learning scheme is introduced to examine the domain adaptation of DA taggers.
Conversation Management in Task-oriented Turkish Dialogue Agents with Dialogue Act Classification
TLDR
This work develops 9 dialogue act classes by observing real-life human conversations from a banking domain Turkish dialogue agent and proposes a dialogue policy based on these classes to correctly direct the users to their goals in a chatbot-human support hybrid dialogue system.
Memory Attention Neural Network for Multi-domain Dialogue State Tracking
TLDR
A novel Memory Attention State Tracker that considers ontologies as prior knowledge and utilizes Memory Network to store such information and achieves a compatible joint accuracy on MultiWoz 2.0 dataset.
GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-supervised Learning and Explicit Policy Injection
TLDR
GALAXY is a novel pre-trained dialog model that explicitly learns dialog policy from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised learning and has a stronger few-shot ability than existing models under various low-resource settings.
Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems
TLDR
A self-training approach that iteratively labels the most confident unlabeled data to train a stronger Student model is proposed and a new text augmentation technique (GradAug) is proposed to better train the Student by replacing non-crucial tokens using a masked language model.
Bridging the Gap between Conversational Reasoning and Interactive Recommendation
TLDR
A novel recommender dialog model that walks on a large-scale knowledge graph to form a reasoning tree at each turn, then mapped to dialog acts to guide response generation and maximizes the mutual benefit between two systems.
Summarizing Behavioral Change Goals from SMS Exchanges to Support Health Coaches
TLDR
It is shown that information captured by dialogue acts can help to improve the goal extraction results and is a step towards building a virtual assistant health coach to promote a healthy lifestyle.
MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation
TLDR
A novel model is proposed, which firstly infers the user’s fine-grained emotional status, and then responds skillfully using a mixture of strategy, which reveals the benefits of fine- grained emotion understanding as well as mixed-up strategy modeling.

References

SHOWING 1-10 OF 25 REFERENCES
ISO-Standard Domain-Independent Dialogue Act Tagging for Conversational Agents
TLDR
This paper proposes a methodology to map several publicly available corpora to a subset of the ISO standard, in order to create a large task-independent training corpus for DA classification, and shows the feasibility of using this corpus to train a domain-independent DA tagger testing it on out-of-domain conversational data.
Bootstrapping a Neural Conversational Agent with Dialogue Self-Play, Crowdsourcing and On-Line Reinforcement Learning
TLDR
This paper discusses the advantages of this approach for industry applications of conversational agents, wherein an agent can be rapidly bootstrapped to deploy in front of users and further optimized via interactive learning from actual users of the system.
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
TLDR
The Multi-Domain Wizard-of-Oz dataset (MultiWOZ), a fully-labeled collection of human-human written conversations spanning over multiple domains and topics is introduced, at a size of 10k dialogues, at least one order of magnitude larger than all previous annotated task-oriented corpora.
Towards an ISO Standard for Dialogue Act Annotation
This paper describes an ISO project which aims at developing a standard for annotating spoken and multimodal dialogue with semantic information concerning the communicative functions of utterances,
Dialogue act modeling for automatic tagging and recognition of conversational speech
TLDR
A probabilistic integration of speech recognition with dialogue modeling is developed, to improve both speech recognition and dialogue act classification accuracy.
Domain Adaptation with Unlabeled Data for Dialog Act Tagging
TLDR
Two feature-based approaches to using unlabeled data in adaptation: restriction to a shared feature set, and an implementation of Blitzer et al.'s Structural Correspondence Learning lead to increased detection of backchannels in the cross-language cases by utilizing correlations between backchannel words and utterance length.
Coding Dialogs with the DAMSL Annotation Scheme
TLDR
The slight revisions to DAMSL discussed here should increase accuracy on the next set of tests and produce a reliable, exible, and comprehensive utterance annotation scheme.
Dialog act tagging using graphical models
  • Gang Ji, J. Bilmes
  • Computer Science
    Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.
  • 2005
TLDR
Tests on the ICSI meeting recorder dialog act (MRDA) corpus show that the factored language model implementations are better than the switching n-gram approach and that by using virtual evidence, the label bias problem in conditional models can be avoided.
Edina: Building an Open Domain Socialbot with Self-dialogues
TLDR
Edina, the University of Edinburgh's social bot, is a conversational agent whose responses utilize data harvested from Amazon Mechanical Turk through an innovative new technique the authors call self-dialogues, which addresses both coverage limitations of a strictly rule-based approach and the lack of guarantees in a strictly machine-learning approach.
Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems
TLDR
Experimental results show that the end-to-end dialogue agent can learn effectively from the mistake it makes via imitation learning from user teaching, and applying reinforcement learning with user feedback after the imitation learning stage further improves the agent’s capability in successfully completing a task.
...
...