paper-with-me

Papers

Diversifying Neural Conversation Model with Maximal Marginal Relevance

2017-11-01 · IJCNLP 2017 11 · Yiping Song, Zhiliang Tian, Dongyan Zhao, Ming Zhang, Rui Yan

Neural conversation systems, typically using sequence-to-sequence (seq2seq) models, are showing promising progress recently. However, traditional seq2seq suffer from a severe weakness: during beam search decoding, they tend to rank universal replies at the top of the candidate list, resulting in the lack of diversity among candidate replies. Maximum Marginal Relevance (MMR) is a ranking algorithm that has been widely used for subset selection. In this paper, we propose the MMR-BS decoding method, which incorporates MMR into the beam search (BS) process of seq2seq. The MMR-BS method improves the diversity of generated replies without sacrificing their high relevance with the user-issued query. Experiments show that our proposed model achieves the best performance among other comparison methods.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityDocument SummarizationInformation RetrievalmodelText Categorization

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Similar Papers 제목 키워드 기반

Generalized People Diversity: Learning a Human Perception-Aligned Diversity Representation for People Images

2024-01-25 · Hansa Srinivasan, Candice Schumann, Aradhana Sinha, David Madras 외

Capturing the diversity of people in images is challenging: recent literature tends to focus on diversifying one or two attributes, requiring expensive attribute labels or building classifiers. We introduce a diverse peo…

AttributeDiversity

Unsupervised Broadcast News Summarization; a comparative study on Maximal Marginal Relevance (MMR) and Latent Semantic Analysis (LSA)

2023-01-05 · Majid Ramezani, Mohammad-Salar Shahryari, Amir-Reza Feizi-Derakhshi, Mohammad-Reza Feizi-Derakhshi

The methods of automatic speech summarization are classified into two groups: supervised and unsupervised methods. Supervised methods are based on a set of features, while unsupervised methods perform summarization based…

News Summarization

Diversifying Reply Suggestions using a Matching-Conditional Variational Autoencoder

2019-03-25 · NAACL 2019 6 · Budhaditya Deb, Peter Bailey, Milad Shokouhi

We consider the problem of diversifying automated reply suggestions for a commercial instant-messaging (IM) system (Skype). Our conversation model is a standard matching based information retrieval architecture, which co…

DiversityInformation RetrievalRetrievalVariational Inference

Diversifying Dialogue Generation with Non-Conversational Text

2020-05-09 · ACL 2020 6 · Hui Su, Xiaoyu Shen, Sanqiang Zhao, Xiao Zhou 외

Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-diversity problem when it comes to open-domain dialogue generation. As bland and generic utterances usually dominate the frequency d…

Dialogue GenerationDiversityTranslation

Combining State-of-the-Art Models with Maximal Marginal Relevance for Few-Shot and Zero-Shot Multi-Document Summarization

2022-11-19 · David Adams, Gandharv Suri, Yllias Chali

In Natural Language Processing, multi-document summarization (MDS) poses many challenges to researchers above those posed by single-document summarization (SDS). These challenges include the increased search space and gr…

DiversityDocument SummarizationMulti-Document Summarization