paper-with-me

Papers

Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization

2023-05-22 · Liang Chen, Hongru Wang, Yang Deng, Wai-Chung Kwan, Zezhong Wang, Kam-Fai Wong

Generating persona consistent dialogue response is important for developing an intelligent conversational agent. Recent works typically fine-tune large-scale pre-trained models on this task by concatenating persona texts and dialogue history as a single input sequence to generate the target response. While simple and effective, our analysis shows that this popular practice is seriously affected by order sensitivity where different input orders of persona sentences significantly impact the quality and consistency of generated response, resulting in severe performance fluctuations (i.e., 29.4% on GPT2 and 83.2% on BART). To mitigate the order sensitivity problem, we propose a model-agnostic framework, ORder Insensitive Generation (ORIG), which enables dialogue models to learn robust representation under different persona orders and improve the consistency of response generation. Experiments on the Persona-Chat dataset justify the effectiveness and superiority of our method with two dominant pre-trained models (GPT2 and BART).

📄 PDF Abstract BibTeX arXiv:2305.12782

Code (1)

chanliang/orig 공식 구현 pytorch

Tasks

Dialogue GenerationResponse GenerationSensitivity

Similar Papers 제목 키워드 기반

DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation

2021-11-22 · Jing Yang Lee, Kong Aik Lee, Woon Seng Gan

The generation of personalized dialogue is vital to natural and human-like conversation. Typically, personalized dialogue generation models involve conditioning the generated response on the dialogue history and a repres…

DecoderDialogue Generation

Exploring Persona Sentiment Sensitivity in Personalized Dialogue Generation

2025-02-17 · Yonghyun Jun, Hwanhee Lee

Personalized dialogue systems have advanced considerably with the integration of user-specific personas into large language models (LLMs). However, while LLMs can effectively generate personalized responses, the influenc…

Dialogue GenerationSensitivity

Ranking Enhanced Dialogue Generation

2020-08-13 · Changying Hao, Liang Pang, Yanyan Lan, Fei Sun 외

How to effectively utilize the dialogue history is a crucial problem in multi-turn dialogue generation. Previous works usually employ various neural network architectures (e.g., recurrent neural networks, attention mecha…

Dialogue GenerationResponse Generation

Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation

2022-04-18 · NAACL 2022 7 · Hanxun Zhong, Zhicheng Dou, Yutao Zhu, Hongjin Qian 외

Personalized dialogue systems explore the problem of generating responses that are consistent with the user's personality, which has raised much attention in recent years. Existing personalized dialogue systems have trie…

Dialogue GenerationResponse Generation

Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Personalized dialogue systems explore the problem of generating responses that are consistent with the user's personality, which have raised much attention in recent years. Existing personalized dialogue systems have tri…

Dialogue GenerationResponse Generation