paper-with-me

홈 › Papers

Pretrained Language Models for Dialogue Generation with Multiple Input Sources

2020-10-15 · Findings of the Association for Computational Linguistics 2020 · Yu Cao, Wei Bi, Meng Fang, DaCheng Tao

Large-scale pretrained language models have achieved outstanding performance on natural language understanding tasks. However, it is still under investigating how to apply them to dialogue generation tasks, especially those with responses conditioned on multiple sources. Previous work simply concatenates all input sources or averages information from different input sources. In this work, we study dialogue models with multiple input sources adapted from the pretrained language model GPT2. We explore various methods to fuse multiple separate attention information corresponding to different sources. Our experimental results show that proper fusion methods deliver higher relevance with dialogue history than simple fusion baselines.

📄 PDF Abstract BibTeX arXiv:2010.07576

Code (1)

caoyu-noob/Multi-GPT2 공식 구현 pytorch

Tasks

Dialogue GenerationLanguage ModelingLanguage ModellingNatural Language Understanding

Similar Papers 제목 키워드 기반

Hello, It's GPT-2 - How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems

2019-11-01 · WS 2019 11 · Pawe{\l} Budzianowski, Ivan Vuli{\'c}

Data scarcity is a long-standing and crucial challenge that hinders quick development of task-oriented dialogue systems across multiple domains: task-oriented dialogue models are expected to learn grammar, syntax, dialog…

Decision MakingLanguage ModelingLanguage ModellingTask-Oriented Dialogue Systems+2

Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems

2019-07-12 · Paweł Budzianowski, Ivan Vulić

Data scarcity is a long-standing and crucial challenge that hinders quick development of task-oriented dialogue systems across multiple domains: task-oriented dialogue models are expected to learn grammar, syntax, dialog…

Decision MakingLanguage ModelingLanguage ModellingTask-Oriented Dialogue Systems+2

Attribute Controlled Dialogue Prompting

2023-07-11 · Runcheng Liu, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh 외

Prompt-tuning has become an increasingly popular parameter-efficient method for adapting large pretrained language models to downstream tasks. However, both discrete prompting and continuous prompting assume fixed prompt…

AttributeDialogue Generation

Video-Grounded Dialogues with Pretrained Generation Language Models

2020-06-27 · ACL 2020 6 · Hung Le, Steven C. H. Hoi

Pre-trained language models have shown remarkable success in improving various downstream NLP tasks due to their ability to capture dependencies in textual data and generate natural responses. In this paper, we leverage …

Sentence

OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue

2022-09-10 · Zhi Chen, Yuncong Liu, Lu Chen, Su Zhu 외

This paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD). Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modul…

Language ModelingLanguage ModellingText Generation