NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation

Kim, Sungdong; Chang, Minsuk; Lee, Sang‐Woo

doi:10.18653/v1/2021.acl-long.287

Cited by 10 publications

(12 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare against recent systems that can perform zero-shot DST: TRADE , MA-DST , SUMBT (Lee et al, 2019), and GPT2-DST . Our method is complementary to systems for creating synthetic in-domain dialogs (Kim et al, 2021).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Instilling Type Knowledge in Language Models via Multi-Task QA

Li¹,

Sridhar²,

Prakash³

et al. 2022

Preprint

View full text Add to dashboard Cite

Understanding human language often necessitates understanding entities and their place in a taxonomy of knowledge-their types. Previous methods to learn entity types rely on training classifiers on datasets with coarse, noisy, and incomplete labels. We introduce a method to instill fine-grained type knowledge in language models with text-to-text pre-training on type-centric questions leveraging knowledge base documents and knowledge graphs. We create the WikiWiki dataset: entities and passages from 10M Wikipedia articles linked to the Wikidata knowledge graph with 41K types. Models trained on WikiWiki achieve state-ofthe-art performance in zero-shot dialog state tracking benchmarks, accurately infer entity types in Wikipedia articles, and can discover new types deemed useful by human judges.

show abstract

Section: Methodsmentioning

confidence: 99%

“…As discussed in Section 4, our method is orthogonal to and thus can be used simultaneously with techniques for creating synthetic in-domain training data for DST (Campagna et al, 2020;Kim et al, 2021). For slot queries, we use templated questions of the form:…”

Section: Dialog State Tracking Notesmentioning

confidence: 99%

Instilling Type Knowledge in Language Models via Multi-Task QA

Li¹,

Sridhar²,

Prakash³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Improvements in these simulators contribute to overall enhancements in dialogue system performance and their ability to handle diverse user inputs and scenarios. Lastly, we explore end-to-end approaches that aim to directly generate dialogue without explicitly defining intermediate steps or modules [4,19,28,32,58]. End-to-end models offer the advantage of encapsulating the entire dialogue generation process within a single model, simplifying both training and inference procedures.…”

Section: Contentmentioning

confidence: 99%

Data Augmentation for Conversational AI

Soudani,

Kanoulas,

Hasibi

2023

Proceedings of the 32nd ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

Advancements in conversational systems have revolutionized information access, surpassing the limitations of single queries. However, developing dialogue systems requires a large amount of training data, which is a challenge in low-resource domains and languages. Traditional data collection methods like crowd-sourcing are labor-intensive and time-consuming, making them ineffective in this context. Data augmentation (DA) is an affective approach to alleviate the data scarcity problem in conversational systems. This tutorial provides a comprehensive and up-to-date overview of DA approaches in the context of conversational systems. It highlights recent advances in conversation augmentation, open domain and task-oriented conversation generation, and different paradigms of evaluating these models. We also discuss current challenges and future directions in order to help researchers and practitioners to further advance the field in this area. CCS CONCEPTS• Information systems → Recommender systems; • Computing methodologies → Discourse, dialogue and pragmatics.

show abstract

“…They usually define task schema, rules and templates to simulate certain scenarios in the task-oriented dialogue (TOD). Kim et al (2021b) proposed neural simulation approach using pre-trained LMs for a fast domain adaptation in the TOD. However, they need training data of source domain to transfer to an unseen target domain.…”

Section: Synthetic Dialogue Generationmentioning

confidence: 99%

Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models

Bae¹,

Kwak²,

Kim³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Recent open-domain dialogue models have brought numerous breakthroughs. However, building a chat system is not scalable since it often requires a considerable volume of human-human dialogue data, especially when enforcing features such as persona, style, or safety. In this work, we study the challenge of imposing roles on open-domain dialogue systems, with the goal of making the systems maintain consistent roles while conversing naturally with humans. To accomplish this, the system must satisfy a role specification that includes certain conditions on the stated features as well as a system policy on whether or not certain types of utterances are allowed. For this, we propose an efficient data collection framework leveraging in-context few-shot learning of large-scale language models for building role-satisfying dialogue dataset from scratch. We then compare various architectures for open-domain dialogue systems in terms of meeting role specifications while maintaining conversational abilities. Automatic and human evaluations show that our models return few out-of-bounds utterances, keeping competitive performance on general metrics. We release a Korean dialogue dataset we built for further research 1 .

show abstract

NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation

Cited by 10 publications

References 28 publications

Instilling Type Knowledge in Language Models via Multi-Task QA

Instilling Type Knowledge in Language Models via Multi-Task QA

Data Augmentation for Conversational AI

Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models

Contact Info

Product

Resources

About