mlsanityData to 7 Oct 2026

External Knowledge Selection with Weighted Negative Sampling in Knowledge-grounded Task-oriented Dialogue Systems

arXiv 2209.02251 ↗First posted 6 Sep 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Constructing a robust dialogue system on spoken conversations bring more challenge than written conversation. In this respect, DSTC10-Track2-Task2 is proposed, which aims to build a task-oriented dialogue (TOD) system incorporating unstructured external knowledge on a spoken conversation, extending DSTC9-Track1. This paper introduces our system containing four advanced methods: data construction, weighted negative sampling, post-training, and style transfer. We first automatically construct a large training data because DSTC10-Track2 does not release the official training set. For the knowledge selection task, we propose weighted negative sampling to train the model more fine-grained manner. We also employ post-training and style transfer for the response generation task to generate an appropriate response with a similar style to the target response. In the experiment, we investigate the effect of weighted negative sampling, post-training, and style transfer. Our model ranked 7 out of 16 teams in the objective evaluation and 6 in human evaluation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 33 references that are in the map. First posted on arXiv 6 Sep 2022.

Builds on

20 of 33 references.

References · 20

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  6. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  7. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  8. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  9. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  10. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  11. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  12. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
8 more
  1. 2017A Survey on Dialogue Systems: Recent Advances and New Frontierscited by 162
  2. 2018Style Transfer Through Back-Translationcited by 124
  3. 2020UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2cited by 111
  4. 2020Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Accesscited by 58
  5. 2021"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversationscited by 30
  6. 2018Back-Translation-Style Data Augmentation for End-to-End ASRcited by 28
  7. 2018Sentiment Adaptive End-to-End Dialog Systemscited by 17
  8. 2021Learning to Select External Knowledge with Multi-Scale Negative Samplingcited by 16

Built on by

Not cited yet.