Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems
Not on the map. Why?
Abstract (arXiv)
Most prior work on task-oriented dialogue systems is restricted to supporting domain APIs. However, users may have requests that are out of the scope of these APIs. This work focuses on identifying such user requests. Existing methods for this task mainly rely on fine-tuning pre-trained models on large annotated data. We propose a novel method, REDE, based on adaptive representation learning and density estimation. REDE can be applied to zero-shot cases, and quickly learns a high-performing detector with only a few shots by updating less than 3K parameters. We demonstrate REDE's competitive performance on DSTC9 data and our newly collected test set.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 17 of its 28 references that are in the map. First posted on arXiv 18 Sep 2021.
Builds on
17 of 28 references.
References · 17
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
- 2018Deep Anomaly Detection with Outlier Exposurecited by 939
- 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
- 2021Whitening Sentence Representations for Better Semantics and Faster Retrievalcited by 198
- 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 137
- 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
- 2020Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Accesscited by 58
- 2020Hooks in the Headline: Learning to Generate Headlines with Controlled Stylescited by 46
- 2020From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gapcited by 40
5 more
- 2019Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialogcited by 33
- 2017Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learningcited by 31
- 2019MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehensioncited by 20
- 2021Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access Track in DSTC9cited by 10
- 2021Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modelingcited by 8
Built on by
Citing papers per year: 2022: 2; 2023: 0; 2024: 1.
3 papers.