paper-with-me

홈 › Papers

Relevant and Informative Response Generation using Pointwise Mutual Information

2019-08-01 · WS 2019 8 · Junya Takayama, Yuki Arase

A sequence-to-sequence model tends to generate generic responses with little information for input utterances. To solve this problem, we propose a neural model that generates relevant and informative responses. Our model has simple architecture to enable easy application to existing neural dialogue models. Specifically, using positive pointwise mutual information, it first identifies keywords that frequently co-occur in responses given an utterance. Then, the model encourages the decoder to use the keywords for response generation. Experiment results demonstrate that our model successfully diversifies responses relative to previous models.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderResponse Generation

Similar Papers 제목 키워드 기반

Human-like informative conversations: Better acknowledgements using conditional mutual information

2021-04-16 · NAACL 2021 4 · Ashwin Paranjape, Christopher D. Manning

This work aims to build a dialogue agent that can weave new factual content into conversations as naturally as humans. We draw insights from linguistic principles of conversational analysis and annotate human-human conve…

Specificity

Peer-Predictive Self-Training for Language Model Reasoning

2026-04-14 · Shi Feng, Hanlin Zhang, Fan Nie, Sham Kakade 외 arxiv

Mechanisms for continued self-improvement of language models without external supervision remain an open challenge. We propose Peer-Predictive Self-Training (PST), a label-free fine-tuning framework in which multiple lan…

Mathematical Reasoning

Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogs

2023-05-20 · Yatin Nandwani, Vineet Kumar, Dinesh Raghu, Sachindra Joshi 외

A major concern in using deep learning based generative models for document-grounded dialogs is the potential generation of responses that are not \textit{faithful} to the underlying document. Existing automated metrics …

Response Generation

Consistent Response Generation with Controlled Specificity

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Junya Takayama, Yuki Arase

We propose a method to control the specificity of responses while maintaining the consistency with the utterances. We first design a metric based on pointwise mutual information, which measures the co-occurrence degree b…

Response GenerationSpecificity

Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs

2025-05-26 · Hao Fang, Changle Zhou, Jiawei Kong, Kuofeng Gao 외

Large Vision-Language Models (LVLMs) are susceptible to hallucinations, where generated responses seem semantically plausible yet exhibit little or no relevance to the input image. Previous studies reveal that this issue…

Hallucination