资源分类
》 资源 》论文》Pretraining Methods for Dialog Context Representation Learning

Pretraining Methods for Dialog Context Representation Learning

2019-09-23 | |  185 |   104 |   0 0 0
Abstract This paper examines various unsupervised pretraining objectives for learning dialog context representations. Two novel methods of pretraining dialog context encoders are proposed, and a total of four methods are examined. Each pretraining objective is fine-tuned and evaluated on a set of downstream dialog tasks using the MultiWoz dataset and strong performance improvement is observed. Further evaluation shows that our pretraining objectives result in not only better performance, but also better convergence, models that are less data hungry and have better domain generalizability

上一篇：Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good

下一篇：Proactive Human-Machine Conversation with Explicit Conversation Goals

用户评价
全部评价

热门资源

  • Deep Cross-media ...

    Cross-media retrieval is a research hotspot in ...

  • Regularizing RNNs...

    Recently, caption generation with an encoder-de...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Visual Reinforcem...

    For an autonomous agent to fulfill a wide range...

  • Joint Pose and Ex...

    Facial expression recognition (FER) is a challe...