Why Do Neural Response Generation Models Prefer Universal Replies?
Recent advances in sequence-to-sequence learning reveal a purely data-driven approach to the response generation task. Despite its diverse applications, existing neural models are prone to producing short and generic replies, making it infeasible to tackle open-domain challenges. In this research, we analyze this critical issue in light of the model's optimization goal and the specific characteristics of the human-to-human dialog corpus. By decomposing the black box into parts, a detailed analysis of the probability limit was conducted to reveal the reason behind these universal replies. Based on these analyses, we propose a max-margin ranking regularization term to avoid the models leaning to these replies. Finally, empirical experiments on case studies and benchmarks with several metrics validate this approach.
Code (0)
등록된 구현이 없습니다.
Tasks
Response GenerationSimilar Papers 제목 키워드 기반
Towards Boosting the Open-Domain Chatbot with Human Feedback
Many open-domain dialogue models pre-trained with social media comments can generate coherent replies but have difficulties producing engaging responses when interacting with real users. This phenomenon might mainly resu…
ChatbotImpersonation: Modeling Persona in Smart Responses to Email
In this paper, we present design, implementation, and effectiveness of generating personalized suggestions for email replies. To personalize email responses based on users style and personality, we model the users person…
PARAN: Persona-Augmented Review ANswering system on Food Delivery Review Dataset
Personalized review response generation presents a significant challenge in domains where user information is limited, such as food delivery platforms. While large language models (LLMs) offer powerful text generation ca…
Response GenerationText GenerationResponsive and Self-Expressive Dialogue Generation
A neural conversation model is a promising approach to develop dialogue systems with the ability of chit-chat. It allows training a model in an end-to-end manner without complex rule design nor feature engineering. Howev…
Dialogue GenerationFeature EngineeringAn animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog
Online conversations include more than just text. Increasingly, image-based responses such as memes and animated gifs serve as culturally recognized and often humorous responses in conversation. However, while NLP has br…
Multimodal GIF Dialog