Relevant and Informative Response Generation using Pointwise Mutual Information
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.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderResponse GenerationSimilar Papers 제목 키워드 기반
Human-like informative conversations: Better acknowledgements using conditional mutual information
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…
SpecificityPeer-Predictive Self-Training for Language Model Reasoning
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 ReasoningPointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogs
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 GenerationConsistent Response Generation with Controlled Specificity
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 GenerationSpecificityGrounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
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