Joint semantic discourse models for automatic multi-document summarization
نویسندگان
چکیده
Automatic multi-document summarization aims at selecting the essential content of related documents and presenting it in a summary. In this paper, we propose some methods for automatic summarization based on Rhetorical Structure Theory and Cross-document Structure Theory. They are chosen in order to properly address the relevance of information, multidocument phenomena and subtopical distribution in the source texts. The results show that using semantic discourse knowledge in strategies for content selection produces summaries that are more informative. Resumo. Sumarização automática multidocumento visa à seleção das informações mais importantes de um conjunto de documentos para produzir um sumário. Neste artigo, propõem-se métodos para sumarização automática baseando-se em conhecimento semântico-discursivo das teorias Rhetorical Structure Theory e Cross-document Structure Theory. Tais teorias foram escolhidas para tratar adequadamente a relevância das informações, os fenômenos multidocumento e a distribuição de subtópicos dos documentos. Os resultados mostram que o uso de conhecimento semântico-discursivo para selecionar conteúdo produz sumários mais informativos.
منابع مشابه
Towards Coherent Multi-Document Summarization
This paper presents G-FLOW, a novel system for coherent extractive multi-document summarization (MDS).1 Where previous work on MDS considered sentence selection and ordering separately, G-FLOW introduces a joint model for selection and ordering that balances coherence and salience. G-FLOW’s core representation is a graph that approximates the discourse relations across sentences based on indica...
متن کاملA survey on Automatic Text Summarization
Text summarization endeavors to produce a summary version of a text, while maintaining the original ideas. The textual content on the web, in particular, is growing at an exponential rate. The ability to decipher through such massive amount of data, in order to extract the useful information, is a major undertaking and requires an automatic mechanism to aid with the extant repository of informa...
متن کاملA Generative Approach for Multi-Document Summarization using Semantic-Discursive information
Multi-document summarization is the automatic production of a unique summary from a collection of texts. In this paper, we propose a statistical generative approach for multi-document summarization that combines simple information such as sentence position in the text and semantic-discursive information from CST (Cross-Document Structure Theory). In particular, we formulate the multi-document s...
متن کاملReducing Redundancy in Multi-document Summarization Using Lexical Semantic Similarity
We present an automatic multi-document summarization system for Dutch based on the MEAD system. We focus on redundancy detection, an essential ingredient of multi-document summarization. We introduce a semantic overlap detection tool, which goes beyond simple string matching. Our results so far do not confirm our expectation that this tool would outperform the other tested methods.
متن کاملOn the Effectiveness of using Sentence Compression Models for Query-Focused Multi-Document Summarization
This paper applies sentence compression models for the task of query-focused multi-document summarization in order to investigate if sentence compression improves the overall summarization performance. Both compression and summarization are considered as global optimization problems and solved using integer linear programming (ILP). Three different models are built depending on the order in whi...
متن کامل