论文信息 - Microblog Contextualization using Continuous Space Vectors: Multi-Sentence Compression of Cultural Documents

Microblog Contextualization using Continuous Space Vectors: Multi-Sentence Compression of Cultural Documents

In this paper we describe our work for the MC2 CLEF 2017 lab. We participated in the content analysis task that involves filtering, language recognition and summarization. We combine Information Retrieval with Multi-Sentence Compression methods to contextualize microblogs using Wikipedia’s pages.

Stéphane Huet | Elvys Linhares Pontes | Andréa Carneiro Linhares | Juan-Manuel Torres-Moreno

[1] Katja Filippova,et al. Multi-Sentence Compression: Finding Shortest Paths in Word Graphs , 2010, COLING.

[2] Michael I. Jordan,et al. Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[3] Juan-Manuel Torres-Moreno,et al. Métodos de Otimização Combinatória Aplicados ao Problema de Compressão MultiFrases , 2017, ArXiv.

[4] Tomas Mikolov,et al. Enriching Word Vectors with Subword Information , 2016, TACL.

[5] Yitong Li,et al. Graph-Based Multi-Tweet Summarization using Social Signals , 2012, COLING.

[6] Deepayan Chakrabarti,et al. Event Summarization Using Tweets , 2011, ICWSM.

[7] Stéphane Huet,et al. Tweet Contextualization using Continuous Space Vectors: Automatic Summarization of Cultural Documents , 2016, CLEF.