Challenge: Existing approaches to dialogue state tracking are dependent on domain ontology and lack of sharing knowledge across domains.
Approach: They propose a transferable dialogue state generator that generates dialogue states from utterances using copy mechanism.
Outcome: Empirical results show that TRADE achieves state-of-the-art 48.62% joint goal accuracy for the five domains of MultiWOZ.

Similar Papers

Modeling Long Context for Task-Oriented Dialogue State Generation (2020.acl-main)

Copied to clipboard

Challenge: Existing approaches to dialogue state tracking are limited to scenarios with infinite slot values and prediction of unseen slot values.
Approach: They propose a multi-task learning model with a simple yet effective utterance tagging technique and a bidirectional language model as an auxiliary task for task-oriented dialogue state generation.
Outcome: The proposed model achieves state-of-the-art accuracy on the MultiWOZ 2.0 dataset.
Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation (D19-1)

Copied to clipboard

Challenge: Existing approaches to dialogue state tracking rely on pre-defined ontologies . however, these methods suffer from computational complexity that increases proportionally to the number of pre-determined slots.
Approach: They propose a model that generates a sequence of belief states without the pre-defined ontology list.
Outcome: The proposed model scales easily with the increasing number of pre-defined slots and domains and reaches the state-of-the-art performance on the multi-domain and single domain dialogue state tracking datasets.
Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking (2020.acl-main)

Copied to clipboard

Challenge: Existing techniques for zero-shot transfer learning for multi-domain dialogue state tracking are expensive and require human errors, delays in annotation, and normalization issues.
Approach: They propose a zero-shot transfer learning technique where training data are synthesized from an abstract dialogue model and the ontology of the domain.
Outcome: The proposed technique improves the state of the art on the multi-domain dialogue state tracking dataset by 21%.
GCDST: A Graph-based and Copy-augmented Multi-domain Dialogue State Tracking (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to training DST on a single domain ignore information across domains.
Approach: They construct a dialogue state graph to transfer structured features among related domain-slot pairs across domains and encode the graph information of dialogue states by graph convolutional networks.
Outcome: The proposed model improves the performance of the multi-domain DST baseline with the absolute joint accuracy of 2.0% and 1.0% on the MultiWOZ 2.0 and 2.1 dialogue datasets.
Parallel Interactive Networks for Multi-Domain Dialogue State Generation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing models do not account for the dependencies between system and user utterances in the same turn and across different turns.
Approach: They propose to integrate an interactive encoder to jointly model in-turn dependencies and cross-turn dependents.
Outcome: The proposed model is superior to existing models and can be used to selectively copy words from historical system utterances or historical user utterrances.
Zero-Shot Dialogue State Tracking via Cross-Task Transfer (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to training a dialogue state tracking model require extensive annotated dialogue data.
Approach: They propose to transfer cross-task knowledge from general question answering corpora to QA model that can handle zero-shot DST.
Outcome: The proposed model improves existing zero-shot and few-shot results on MultiWoz and shows better generalization ability in unseen domains.
Dialogue State Tracking with Explicit Slot Connection Modeling (2020.acl-main)

Copied to clipboard

Challenge: Existing methods to track dialogue state are lacking in multi-domain scenarios.
Approach: They propose a model that explicitly considers slot correlations across domains . they propose ellipsis and reference to express values that have been mentioned by slots from other domains.
Outcome: The proposed model outperforms existing models on multi-domain datasets and achieves state-of-the-art performance.
Multi-Domain Dialogue State Tracking with Disentangled Domain-Slot Attention (2023.findings-acl)

Copied to clipboard

Challenge: Multi-domain dialogue state tracking is a challenge for task-oriented dialogue systems . domains and slots are aggregated into a single query to generate domain-slot specific representations .
Approach: They propose to disentangle domain-slot attention for multi-domain dialogue state tracking by separating query about domains and slots from the attention component.
Outcome: The proposed approach outperforms the standard multi-head attention with aggregated domain-slot query.
Generation and Extraction Combined Dialogue State Tracking with Hierarchical Ontology Integration (2021.emnlp-main)

Copied to clipboard

Challenge: Current models are not satisfactory for solving out-of-vocabulary problems . current models assume that the task ontology is well defined in advance .
Approach: They propose to enhance the interrelation between slots with masked hierarchical attention.
Outcome: The proposed model yields a significant performance gain over current state-of-the-art model and is more robust to out-ofvocabulary problem compared with other methods.
Slot Dependency Modeling for Zero-Shot Cross-Domain Dialogue State Tracking (2022.coling-1)

Copied to clipboard

Challenge: Existing zero-shot learning methods ignore slot dependencies in a multidomain dialogue . experimental results show the effectiveness of our proposed method over existing state-of-art generation methods .
Approach: They propose to use slot prompts combination, slot values demonstration and slot constraint object to model slot-slot dependency, slot-value dependency and slot-context dependency respectively.
Outcome: The proposed method outperforms state-of-the-art methods under zero-shot/few-shot settings.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations