Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems

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.

[1]  Huang He,et al.  Learning to Select External Knowledge With Multi-Scale Negative Sampling , 2021, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[2]  Dilek Z. Hakkani-Tür,et al.  From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap , 2020, NLP4CONVAI.

[3]  Geoffrey Zweig,et al.  Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning , 2017, ACL.

[4]  Di Jin,et al.  Hooks in the Headline: Learning to Generate Headlines with Controlled Styles , 2020, ACL.

[5]  Di Jin,et al.  Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering , 2020, ACL.

[6]  Jiarun Cao,et al.  Whitening Sentence Representations for Better Semantics and Faster Retrieval , 2021, ArXiv.

[7]  Iryna Gurevych,et al.  Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks , 2019, EMNLP.

[8]  Noah A. Smith,et al.  Evaluating Models’ Local Decision Boundaries via Contrast Sets , 2020, FINDINGS.

[9]  Dilek Z. Hakkani-Tür,et al.  Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access , 2020, SIGDIAL.

[10]  Christopher D. Manning,et al.  Key-Value Retrieval Networks for Task-Oriented Dialogue , 2017, SIGDIAL Conference.

[11]  Arash Einolghozati,et al.  Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialog , 2019, AAAI.

[12]  Rick Siow Mong Goh,et al.  Dual Adversarial Neural Transfer for Low-Resource Named Entity Recognition , 2019, ACL.

[13]  Peter Szolovits,et al.  A Simple Baseline to Semi-Supervised Domain Adaptation for Machine Translation , 2020 .

[14]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[15]  Tianyu Gao,et al.  SimCSE: Simple Contrastive Learning of Sentence Embeddings , 2021, EMNLP.

[16]  Dilek Z. Hakkani-Tür,et al.  Overview of the Ninth Dialog System Technology Challenge: DSTC9 , 2020, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[17]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

[18]  Ramit Sawhney,et al.  SpeechMix - Augmenting Deep Sound Recognition Using Hidden Space Interpolations , 2020, INTERSPEECH.

[19]  Chun-Liang Li,et al.  Learning and Evaluating Representations for Deep One-class Classification , 2020, ICLR.

[20]  Dilek Z. Hakkani-Tür,et al.  MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension , 2020, AAAI.

[21]  Ramit Sawhney,et al.  Augmenting NLP models using Latent Feature Interpolations , 2020, COLING.

[22]  Mihail Eric,et al.  MultiWOZ 2. , 2019 .

[23]  Thomas G. Dietterich,et al.  Deep Anomaly Detection with Outlier Exposure , 2018, ICLR.

[24]  Dilek Z. Hakkani-Tür,et al.  Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling , 2021, DIALDOC.

[25]  Zhiguo Cao,et al.  RoSeq: Robust Sequence Labeling , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[26]  Hao Zhang,et al.  Dual Adversarial Transfer for Sequence Labeling , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.