按年被提到
20152015 · 1 次2026
大模型与语言模型›对话式大模型·arXiv:1510.03055 · cs.CL

A Diversity-Promoting Objective Function for Neural Conversation Models

Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, Bill Dolan · 2015
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2015-11-24 · 最近 2022-06-10
2不同的人
2活跃月份
2讨论串
242被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Sequence-to-sequence neural network models for generation of conversational responses tend to generate safe, commonplace responses (e.g., "I don't know") regardless of the input. We suggest that the traditional objective function, i.e., the likelihood of output (response) given input (message) is unsuited to response generation tasks. Instead we propose using Maximum Mutual Information (MMI) as the objective function in neural models. Experimental results demonstrate that the proposed MMI models produce more diverse, interesting, and appropriate responses, yielding substantive gains in BLEU scores on two conversational datasets and in human evaluations.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论ram21 · 2015-11

“Thank you. You mentioned that you plan on adding a re-ranker. Is that a re-ranker that encourages diversity? Just like what is done in this paper: http://arxiv.org/pdf/1510.03055.pdf”

NeuralTalk2: Efficient Image Captioning code in Torch, runs on GPU原评论 ↗
评论Imnimo · 2022-06

“It wasn't so long ago that researchers were worried their chatbots said "I don't know" too much: https://arxiv.org/pdf/1510.03055.pdf >Sequence-to-sequence neural network models for generation of conversational responses tend to generate safe, commonplace responses (e.g., I don’t know) regardless of the input. We suggest that the traditional objective f…”

Artificial neural networks today are not conscious (Douglas Hofstadter)原评论 ↗