A Few-Shot Semantic Parser for Wizard-of-Oz Dialogues with the Precise ThingTalk Representation

  title={A Few-Shot Semantic Parser for Wizard-of-Oz Dialogues with the Precise ThingTalk Representation},
  author={Giovanni Campagna and Sina J. Semnani and Ryan Kearns and Lucas Jun Koba Sato and Silei Xu and Monica S. Lam},
Previous attempts to build effective semantic parsers for Wizard-of-Oz (WOZ) conversations suffer from the difficulty in acquiring a high-quality, manually annotated training set. Approaches based only on dialogue synthesis are insufficient, as dialogues generated from state-machine based models are poor approximations of real-life conversations. Furthermore, previously proposed dialogue state representations are ambiguous and lack the precision necessary for building an effective agent.This… 

Figures and Tables from this paper

ThingTalk: An Extensible, Executable Representation Language for Task-Oriented Dialogues

This paper proposes the design and rationale of the ThingTalk formal representation, and how the design improves the development of transactional task-oriented agents.

"Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking

It is argued that some critical aspects of dialogue systems such as generalizability are still underexplored and to motivate future studies, several research avenues are proposed.



Slot Self-Attentive Dialogue State Tracking

This paper proposes a slot self-attention mechanism that can learn the slot correlations automatically, and achieves state-of-the-art performance on both datasets, verifying the necessity and effectiveness of taking slot correlations into consideration.

MultiWOZ 2.3: A multi-domain task-oriented dataset enhanced with annotation corrections and co-reference annotation

This paper introduces MultiWOZ 2.3, in which it differentiate incorrect annotations in dialogue acts from dialogue states, and identifies a lack of co-reference when publishing the updated dataset, to ensure consistency between dialogue acts and dialogue states.

SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking

A new approach to universal and scalable belief tracker, called slot-utterance matching belief tracker (SUMBT), which learns the relations between domain-slot-types and slot-values appearing in utterances through attention mechanisms based on contextual semantic vectors.

Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

A Transferable Dialogue State Generator (TRADE) that generates dialogue states from utterances using copy mechanism, facilitating transfer when predicting (domain, slot, value) triplets not encountered during training.

An iterative design methodology for user-friendly natural language office information applications

A six-step, iterative, empirical human factors design methodology was used to develop CAL, a natural language computer application to help computer-naive business professionals manage their personal

Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking

It is shown that data augmentation through synthesized data can improve the accuracy of zero-shot learning for both the TRADE model and the BERT-based SUMBT model on the MultiWOZ 2.1 dataset.

MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines

This work identifies and fixes dialogue state annotation errors across 17.3% of the utterances on top of MultiWOZ 2.1, and redefines the ontology by disallowing vocabularies of slots with a large number of possible values to help avoid annotation errors.

MultiWOZ 2.1: Multi-Domain Dialogue State Corrections and State Tracking Baselines

This work uses crowdsourced workers to fix the state annotations and utterances in the original version of the MultiWOZ data, hoping that this dataset resource will allow for more effective dialogue state tracking models to be built in the future.

Key-Value Retrieval Networks for Task-Oriented Dialogue

This work proposes a new neural dialogue agent that is able to effectively sustain grounded, multi-domain discourse through a novel key-value retrieval mechanism and significantly outperforms a competitive rule-based system and other existing neural dialogue architectures on the provided domains according to both automatic and human evaluation metrics.