Simple Unsupervised Summarization by Contextual Matching
We propose an unsupervised method for sentence summarization using only language modeling. The approach employs two language models, one that is generic (i.e. pretrained), and the other that is specific to the target domain. We show that by using a product-of-experts criteria these are enough for maintaining continuous contextual matching while maintaining output fluency. Experiments on both abstractive and extractive sentence summarization data sets show promising results of our method without being exposed to any paired data.
Code (1)
Tasks
Language ModelingLanguage ModellingSentenceSentence SummarizationText SummarizationUnsupervised Sentence SummarizationSimilar Papers 제목 키워드 기반
Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization
Opinion summarization provides an important solution for summarizing opinions expressed among a large number of reviews. However, generating aspect-specific and general summaries is challenging due to the lack of annotat…
Natural Language InferenceOpinion SummarizationUnsupervised Opinion SummarizationCentrality Meets Centroid: A Graph-based Approach for Unsupervised Document Summarization
Unsupervised document summarization has re-acquired lots of attention in recent years thanks to its simplicity and data independence. In this paper, we propose a graph-based unsupervised approach for extractive document …
Document SummarizationExtractive Document SummarizationSentenceUnsupervised Contextualized Document Representation
Several NLP tasks need the effective representation of text documents. Arora et. al., 2017 demonstrate that simple weighted averaging of word vectors frequently outperforms neural models. SCDV (Mekala et. al., 2017) furt…
ClusteringSentenceSentence SimilarityWord Sense DisambiguationAn Unsupervised Masking Objective for Abstractive Multi-Document News Summarization
We show that a simple unsupervised masking objective can approach near supervised performance on abstractive multi-document news summarization. Our method trains a state-of-the-art neural summarization model to predict t…
Extractive SummarizationNews SummarizationSUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization
We study unsupervised multi-document summarization evaluation metrics, which require neither human-written reference summaries nor human annotations (e.g. preferences, ratings, etc.). We propose SUPERT, which rates the q…
Document SummarizationMulti-Document Summarizationreinforcement-learningReinforcement Learning (RL)+2