paper-with-me

홈 › Papers

Probing Task-Oriented Dialogue Representation from Language Models

2020-10-26 · EMNLP 2020 11 · Chien-Sheng Wu, Caiming Xiong

This paper investigates pre-trained language models to find out which model intrinsically carries the most informative representation for task-oriented dialogue tasks. We approach the problem from two aspects: supervised classifier probe and unsupervised mutual information probe. We fine-tune a feed-forward layer as the classifier probe on top of a fixed pre-trained language model with annotated labels in a supervised way. Meanwhile, we propose an unsupervised mutual information probe to evaluate the mutual dependence between a real clustering and a representation clustering. The goals of this empirical paper are to 1) investigate probing techniques, especially from the unsupervised mutual information aspect, 2) provide guidelines of pre-trained language model selection for the dialogue research community, 3) find insights of pre-training factors for dialogue application that may be the key to success.

📄 PDF Abstract BibTeX arXiv:2010.13912

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringLanguage ModelingLanguage ModellingModel Selection

Similar Papers 제목 키워드 기반

DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations

2024-03-31 · Weihao Zeng, Dayuan Fu, Keqing He, Yejie Wang 외

Language models pre-trained on general text have achieved impressive results in diverse fields. Yet, the distinct linguistic characteristics of task-oriented dialogues (TOD) compared to general text limit the practical u…

Diversity

Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive Learning

2023-08-09 · Hoang H. Nguyen, Chenwei Zhang, Ye Liu, Philip S. Yu

Recent advanced methods in Natural Language Understanding for Task-oriented Dialogue (TOD) Systems (e.g., intent detection and slot filling) require a large amount of annotated data to achieve competitive performance. In…

Contrastive LearningIntent DetectionLanguage ModelingLanguage Modelling+4

BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses

2024-03-02 · Weihao Zeng, Keqing He, Yejie Wang, Dayuan Fu 외

Pre-trained language models have been successful in many scenarios. However, their usefulness in task-oriented dialogues is limited due to the intrinsic linguistic differences between general text and task-oriented dialo…

Diversity

DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue

2020-09-28 · Shikib Mehri, Mihail Eric, Dilek Hakkani-Tur

A long-standing goal of task-oriented dialogue research is the ability to flexibly adapt dialogue models to new domains. To progress research in this direction, we introduce DialoGLUE (Dialogue Language Understanding Eva…

Domain AdaptationMulti-domain Dialogue State TrackingNatural Language Understanding

FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue

2023-06-17 · Weihao Zeng, Keqing He, Yejie Wang, Chen Zeng 외

Pre-trained language models based on general text enable huge success in the NLP scenario. But the intrinsical difference of linguistic patterns between general text and task-oriented dialogues makes existing pre-trained…

Language ModelingLanguage Modelling