paper-with-me

홈 › Papers

A scalable framework for learning from implicit user feedback to improve natural language understanding in large-scale conversational AI systems

2020-10-23 · EMNLP 2021 11 · Sunghyun Park, Han Li, Ameen Patel, Sidharth Mudgal, Sungjin Lee, Young-Bum Kim, Spyros Matsoukas, Ruhi Sarikaya

Natural Language Understanding (NLU) is an established component within a conversational AI or digital assistant system, and it is responsible for producing semantic understanding of a user request. We propose a scalable and automatic approach for improving NLU in a large-scale conversational AI system by leveraging implicit user feedback, with an insight that user interaction data and dialog context have rich information embedded from which user satisfaction and intention can be inferred. In particular, we propose a general domain-agnostic framework for curating new supervision data for improving NLU from live production traffic. With an extensive set of experiments, we show the results of applying the framework and improving NLU for a large-scale production system and show its impact across 10 domains.

📄 PDF Abstract BibTeX arXiv:2010.12251

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language Understanding

Similar Papers 제목 키워드 기반

Learning Label Trees for Probabilistic Modelling of Implicit Feedback

2012-12-01 · NeurIPS 2012 12 · Andriy Mnih, Yee W. Teh

User preferences for items can be inferred from either explicit feedback, such as item ratings, or implicit feedback, such as rental histories. Research in collaborative filtering has concentrated on explicit feedback, r…

Collaborative Filtering

Reading Between the Lines: Scalable User Feedback via Implicit Sentiment in Developer Prompts

2025-09-22 · Daye Nam, Malgorzata Salawa, Satish Chandra arxiv

Evaluating developer satisfaction with conversational AI assistants at scale is critical but challenging. User studies provide rich insights, but are unscalable, while large-scale quantitative signals from logs or in-pro…

Sentiment Analysis

FeedRec: News Feed Recommendation with Various User Feedbacks

2021-02-09 · Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang

Accurate user interest modeling is important for news recommendation. Most existing methods for news recommendation rely on implicit feedbacks like click for inferring user interests and model training. However, click be…

News Recommendation

Reinforcement Learning from Implicit Neural Feedback for Human-Aligned Robot Control

2025-11-18 · Suzie Kim arxiv

Conventional reinforcement learning (RL) approaches often struggle to learn effective policies under sparse reward conditions, necessitating the manual design of complex, task-specific reward functions. To address this l…

Reinforcement Learning

Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback

2025-07-17 · Suzie Kim, Hye-Bin Shin, Seong-Whan Lee

Conventional reinforcement learning (RL) ap proaches often struggle to learn effective policies under sparse reward conditions, necessitating the manual design of complex, task-specific reward functions. To address this …

EEGMuJoCoreinforcement-learningReinforcement Learning+1