Keyphrase Extraction for N-best Reranking in Multi-Sentence Compression
Published 26 August 2015Open access
Florian Boudin, Emmanuel Morin
Citations77
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper presents an N-best reranking method based on keyphrase extraction that significantly improves the informativity of the generated compressions.
Abstract
Multi-Sentence Compression (MSC) is the task of generating a short single sentence sum-mary from a cluster of related sentences. This paper presents an N-best reranking method based on keyphrase extraction. Compression candidates generated by a word graph-based MSC approach are reranked according to the number and relevance of keyphrases they con-tain. Both manual and automatic evaluations were performed using a dataset made of clus-ters of newswire sentences. Results show that the proposed method significantly improves the informativity of the generated compres-sions. 1
Keywords
Computer Science
ROUGE: A Package for Automatic Evaluation of Summaries
8,286 Citations2004Chin-Yew Lin
Four different RouGE measures are introduced: ROUGE-N, ROUge-L, R OUGE-W, and ROUAGE-S included in the Rouge summarization evaluation package and their evaluations.
Empirical Methods in Natural Language ProcessingTextRank: Bringing Order into Text
3,347 Citations2004Rada Mihalcea, Paul Tarau
TextRank, a graph-based ranking model for text processing, is introduced and it is shown how this model can be successfully used in natural language applications.
Computational LinguisticsInter-Coder Agreement for Computational Linguistics
1,604 Citations2008Ron Artstein, Massimo Poesio
It is argued that weighted, alpha-like coefficients, traditionally less used than kappa-like measures in computational linguistics, may be more appropriate for many corpus annotation tasks—but that their use makes the interpretation of the value of the coefficient even harder.
Information RetrievalLearning Algorithms for Keyphrase Extraction
837 Citations2000Peter D. Turney
The experimental results support the claim that a custom-designed algorithm (GenEx), incorporating specialized procedural domain knowledge, can generate better keyphrases than a general-purpose algorithm (C4.5).
Research Commons (University of Waikato)Domain-specific keyphrase extraction
623 Citations1999Eibe Frank, Gordon W. Paynter +3 more
This paper shows that a simple procedure for keyphrase extraction based on the naive Bayes learning scheme performs comparably to the state of the art, and explains how this procedure's performance can be boosted by automatically tailoring the extraction process to the particular document collection at hand.
Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)Opinosis: A Graph Based Approach to Abstractive Summarization of Highly Redundant Opinions
524 Citations2010Kavita Ganesan, ChengXiang Zhai +1 more
A novel graph-based summarization framework (Opinosis) that generates concise abstractive summaries of highly redundant opinions that have better agreement with human summaries compared to the baseline extractive method.
Computational LinguisticsSentence Fusion for Multidocument News Summarization
443 Citations2005Regina Barzilay, Kathleen McKeown
This article introduces sentence fusion, a novel text-to-text generation technique for synthesizing common information across documents that moves the summarization field from the use of purely extractive methods to the generation of abstracts that contain sentences not found in any of the input documents and can synthesize information across sources.
SemEval-2010 Task 5 : Automatic Keyphrase Extraction from Scientific Articles
355 Citations2010Su Nam Kim, Olena Medelyan +2 more
The participating systems were evaluated by matching their extracted keyphrases against manually assigned ones and the overall ranking of the submitted systems is presented.
Clustering to find exemplar terms for keyphrase extraction
302 Citations2009Zhiyuan Liu, Peng Li +2 more
This work proposes an unsupervised method for keyphrase extraction that outperforms sate-of-the-art graph-based ranking methods (TextRank) by 9.5% in F1-measure and guarantees the document to be semantically covered by these exemplar terms.
A language model approach to keyphrase extraction
299 Citations2003Takashi Tomokiyo, Matthew Hurst
A new approach is to use pointwise KL-divergence between multiple language models for scoring both phraseness and informativeness, which can be unified into a single score to rank extracted phrases.
Multi-document summarization via sentence-level semantic analysis and symmetric matrix factorization
294 Citations2008Dingding Wang, Tao Li +2 more
A new multi-document summarization framework based on sentence-level semantic analysis and symmetric non-negative matrix factorization is proposed, which aims to create a compressed summary while retaining the main characteristics of the original set of documents.
Sentence reduction for automatic text summarization
284 Citations2000Hongyan Jing
A novel sentence reduction system for automatically removing extraneous phrases from sentences that are extracted from a document for summarization purpose using multiple sources of knowledge, including syntactic knowledge, context information, and statistics computed from a corpus which consists of examples written by human professionals.
Multi-Sentence Compression: Finding Shortest Paths in Word Graphs
200 Citations2010Katja Filippova
Despite its simplicity, the proposed multi-sentence compression method is capable of generating grammatical and informative summaries as its experiments with English and Spanish data demonstrate.
Summarizing Microblogs Automatically
170 Citations2010Beaux Sharifi, Mark-Anthony Hutton +1 more
An algorithm is developed that takes a trending phrase or any phrase specified by a user, collects a large number of posts containing the phrase, and provides an automatically created summary of the posts related to the term.
CollabRank
146 Citations2008Xiaojun Wan, Jianguo Xiao
This paper proposes a novel approach named CollabRank to collaborative single-document keyphrase extraction by making use of mutual influences of multiple documents within a cluster context, and finds that the system performance relies positively on the quality of document clusters.
Sentence fusion via dependency graph compression
124 Citations2008Katja Filippova, Michael Strube
A novel unsupervised sentence fusion method which is applied to a corpus of biographies in German and outperforms the fusion approach of Barzilay & McKeown (2005) with respect to readability.
Models for sentence compression
103 Citations2006James Clarke, Mirella Lapata
This paper provides a novel comparison between a supervised constituent-based and an weakly supervised word-based compression algorithm and examines how these models port to different domains (written vs. spoken text).
Statistical sentence condensation using ambiguity packing and stochastic disambiguation methods for Lexical-Functional Grammar
79 Citations2003Stefan Riezler, Tracy Holloway King +2 more
Overall summarization quality of the proposed system is state-of-the-art, with guaranteed grammaticality of the system output due to the use of a constraint-based parser/generator.
Evaluating Sentence Compression: Pitfalls and Suggested Remedies
52 Citations2011Courtney Napoles, Benjamin Van Durme +1 more
It is demonstrated that compression rate is a strong predictor of compression quality and that perceived improvement over other models is often a side effect of producing longer output.
Meeting of the Association for Computational LinguisticsLearning to Fuse Disparate Sentences
29 Citations2011Micha Elsner, Deepak Santhanam
Evaluation by human judges shows that the system for fusing sentences which are drawn from the same source document but have different content produces fused sentences that are both informative and readable.
Trimming CFG parse trees for sentence compression using machine learning approaches
22 Citations2006Yuya Unno, Takashi Ninomiya +2 more
A maximum entropy model is applied to the above method and it is found that this method produced more grammatical and informative compressed sentences than other methods.
RWTH Publications (RWTH Aachen)Reranking Translation Hypotheses Using Structural Properties
17 Citations2006Saša Hasan, Oliver Bender +1 more
Improvements are possible by utilizing supertagging, lightweight dependency analysis, a link grammar parser and a maximum-entropy based chunk parser to investigate methods that add syntactically motivated features to a statistical machine translation system in a reranking framework.