Exploiting Rhetorical Relations in Blog Summarization
Lecture notes in computer sciencePublished 1 January 2010
Shamima Mithun
Citations19
SJR quartileQ2
SJR score0.35
SNIP0.55
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 work has utilized rhetorical relations of texts with the help of text schema and Rhetorical Structure Theory (RST) to resolve Question Irrelevancy and Discourse Incoherency problems.
Abstract
With the goal of developing an efficient query-based opinion summarization approach, we have targeted to resolve Question Irrelevancy and Discourse Incoherency problems which have been found to be the most frequently occurring problems for opinion summarization. To address these problems, we have utilized rhetorical relations of texts with the help of text schema and Rhetorical Structure Theory (RST).
Keywords
Computer Science
The PageRank Citation Ranking : Bringing Order to the Web
12,645 Citations1999Lawrence M. Page, Sergey Brin +2 more
This paper describes PageRank, a mathod for rating Web pages objectively and mechanically, effectively measuring the human interest and attention devoted to them, and shows how to efficiently compute PageRank for large numbers of pages.
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.
Mining and summarizing customer reviews
7,714 Citations2004Minqing Hu, Bing Liu
This research aims to mine and to summarize all the customer reviews of a product, and proposes several novel techniques to perform these tasks.
Thumbs up?
6,987 Citations2002Bo Pang, Lillian Lee +1 more
This work considers the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative, and concludes by examining factors that make the sentiment classification problem more challenging.
now publishers, Inc. eBooksOpinion Mining and Sentiment Analysis
6,745 Citations2008Bo Pang, Lillian Lee
Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition
4,165 Citations2000Daniel Jurafsky, James Martin
This book takes an empirical approach to language processing, based on applying statistical and other machine-learning algorithms to large corpora, to demonstrate how the same algorithm can be used for speech recognition and word-sense disambiguation.
IBM Journal of Research and DevelopmentThe Automatic Creation of Literature Abstracts
3,211 Citations1958H. P. Luhn
In the exploratory research described, the complete text of an article in machine-readable form is scanned by an IBM 704 data-processing machine and analyzed in accordance with a standard program.
Computational LinguisticsAttention, intentions, and the structure of discourse
2,606 Citations1986Barbara J. Grosz, Candace L. Sidner
A new theory of discourse structure that stresses the role of purpose and processing in discourse is explored and various properties of discourse are described, and explanations for the behavior of cue phrases, referring expressions, and interruptions are explored.
A Theory of Truth and Semantic Representation
1,516 Citations2013Hans Kamp
The Penn Discourse TreeBank 2.0.
1,130 Citations2008Rashmi Prasad, Nikhil Dinesh +5 more
The second version of the Penn Discourse Treebank, PDTB-2.0, is presented, describing its lexically-grounded annotations of discourse relations and their two abstract object arguments over the 1 million word Wall Street Journal corpus.
Studies in linguistics and philosophyReference to Abstract Objects in Discourse
1,124 Citations1993Nicholas Asher
A tour of Abstract Entities, Eventualities and the Nominals that Denote them and applications of the Theory of Discourse Structure to Concept Anaphora and VP Ellipsis and its Philosophical Implications.
The Stanford typed dependencies representation
922 Citations2008Marie-Catherine de Marneffe, Christopher D. Manning
This paper examines the Stanford typed dependencies representation, which was designed to provide a straightforward description of grammatical relations for any user who could benefit from automatic text understanding, and considers the underlying design principles of the Stanford scheme.
Journal of Emerging Technologies in Web IntelligenceA Survey of Text Summarization Extractive Techniques
606 Citations2010Vishal Gupta, Gurpreet Singh Lehal
A Survey of Text Summarization Extractive techniques has been presented and it is shown that extracting important sentences, paragraphs etc. from the source text and concatenating them into shorter form conveys the most important information from the original text document.
The Thread of Discourse
585 Citations1975Joseph E. Grimes
International Conference on Weblogs and Social MediaLarge-Scale Sentiment Analysis for News and Blogs
558 Citations2007Namrata Godbole, Manjunath Srinivasaiah +1 more
Computational LinguisticsIntroduction to the Special Issue on Summarization
533 Citations2002Dragomir Radev, Eduard Hovy +1 more
This work focuses on automatic summarization of open-domain multiparty dialogues in diverse genres, and on the development of a robust practical text summarizer based on rhetorical structure extraction.
Opinion Extraction, Summarization and Tracking in News and Blog Corpora.
477 Citations2006Lun‐Wei Ku, Yuting Liang +1 more
Both news and web blog articles are investigated and algorithms for opinion extraction at word, sentence and document level are proposed, and the issue of relevant sentence selection is discussed, and then topical and opinionated information are summarized.
BiometricsA One-Way Components of Variance Model for Categorical Data
468 Citations1977J. Richard Landis, Gary G. Koch
Center for the Study of Language and Information eBooksOn the coherence and structure of discourse
461 Citations1985Jerry R. Hobbs
Identifying comparative sentences in text documents
445 Citations2006Nitin Jindal, Bing Liu
This paper first categorizes comparative sentences into different types, and then presents a novel integrated pattern discovery and supervised learning approach to identifying comparative sentences from text documents.
Sentence level discourse parsing using syntactic and lexical information
411 Citations2003Radu Soricut, Daniel Marcu
Two probabilistic models that can be used to identify elementary discourse units and build sentence-level discourse parse trees are introduced and shown to be sophisticated enough to yield discourse trees at an accuracy level that matches near-human levels of performance.
An unsupervised approach to recognizing discourse relations
384 Citations2001Daniel Marcu, Abdessamad Echihabi
It is shown that discourse relation classifiers trained on examples that are automatically extracted from massive amounts of text can be used to distinguish between some of these relations with accuracies as high as 93%, even when the relations are not explicitly marked by cue phrases.
Generating natural language summaries from multiple on-line sources
381 Citations1998Dragomir Radev, Kathleen McKeown
Multi-document summarization by sentence extraction
356 Citations2000Jade Goldstein, Vibhu O. Mittal +2 more
This paper discusses a text extraction approach to multi- document summarization that builds on single-document summarization methods by using additional, available information about the document set as a whole and the relationships between the documents.
A Survey on Automatic Text Summarization
350 Citations2007Dipanjan Das Andr
This survey intends to investigate some of the most relevant approaches both in the areas of single-document and multipledocument summarization, giving special emphasis to empirical methods and extractive techniques.
Columbia Academic Commons (Columbia University)MEAD - A Platform for Multidocument Multilingual Text Summarization
347 Citations2004Dragomir Radev, Timothy Allison +15 more
The functionality of MEAD is described, a comprehensive, public domain, open source, multidocument multilingual summarization environment that has been thus far downloaded by more than 500 organizations.
Journal of Artificial Intelligence ResearchInferring Strategies for Sentence Ordering in Multidocument News Summarization
333 Citations2002Regina Barzilay, Noémie Elhadad
A strategy for ordering information that combines constraints from chronological order of events and topical relatedness is implemented and Evaluation of the augmented algorithm shows a significant improvement of the ordering over two baseline strategies.
Predicting Movie Sales from Blogger Sentiment
325 Citations2006Gilad Mishne, Natalie Glance
The main finding is that positive sentiment is indeed a better predictor for movie success when applied to a limited context around references to the movie in weblogs, posted prior to its release.
Artificial IntelligenceAutomated discourse generation using discourse structure relations
308 Citations1993Eduard Hovy
Several facets of discourse structure relations as they are required by and used in text planners are outlined—their nature, number, and extension to associated tasks such as sentence planning and text formatting.
arXiv (Cornell University)Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization
299 Citations2004Regina Barzilay, Lillian Lee
An effective knowledge-lean method for learning content models from unannotated documents is presented, utilizing a novel adaptation of algorithms for Hidden Markov Models and applied to two complementary tasks: information ordering and extractive summarization.
Discourse ProcessesUsing linguistic phenomena to motivate a set of coherence relations
270 Citations1994Alistair Knott, Robert Dale
Artificial IntelligenceDiscourse strategies for generating natural-language text
270 Citations1985Kathleen McKeown
A computational model of discourse strategies is presented that can be used to guide the generation process in its decisions about what to say next and is implemented in text, a system which generates paragraph-length responses to questions about database structure.
From discourse structures to text summaries
268 Citations1997Daniel Marcu
Probabilistic text structuring
265 Citations2003Mirella Lapata
An approach to information ordering that is particularly suited for text-to-text generation and the appropriateness of such a model for multidocument summarization is assessed.
Journal of PragmaticsDiscourse markers as signals (or not) of rhetorical relations
255 Citations2005Maite Taboada
The rhetorical parsing, summarization, and generation of natural language texts
243 Citations1998Graeme Hirst, Daniel Marcu
This thesis is an inquiry into the nature of the high-level, rhetorical structure of unrestricted natural language texts, computational means to enable its derivation, and two applications (in automatic summarization and natural language generation) that follow from the ability to build such structures automatically.
Lecture notes in computer scienceAutomatic Text Summarization Using a Machine Learning Approach
236 Citations2002Joel Larocca Neto, Alex A. Freitas +1 more
This paper presents a summarization procedure based on the application of trainable Machine Learning algorithms which employs a set of features extracted directly from the original text, based on statistical and linguistic features extracted from a simplified argumentative structure of the text.
Overview of the TREC-2009 Blog Track
219 Citations2009Craig Macdonald, Iadh Ounis +1 more
This paper has created the first blog test collection, namely the TREC Blog06 collection, for adhoc retrieval and opinion finding, and provides an overview of each task, summarises the obtained results and draws conclusions for the future.
Columbia Academic Commons (Columbia University)Towards multidocument summarization by reformulation: progress and prospects
192 Citations1999Kathleen McKeown, Judith L. Klavans +3 more
The evaluation of system components shows that learning over multiple extracted linguistic features is more effective than information retrieval approaches at identifying similar text units for summarization and that it is possible to generate a fluent summary that conveys similarities among documents even when full semantic interpretations of the input text are not available.
ScholarlyCommons (University of Pennsylvania)The Penn Discourse Treebank 2.0 Annotation Manual
188 Citations2007Rashmi Prasad, Eleni Miltsakaki +4 more
Overview of the TAC 2008 Update Summarization Task.
185 Citations2008Hoa Trang Dang, Karolina Owczarzak
While all of the 71 submitted runs were automatically scored with the ROUGE and BE metrics, NIST assessors manually evaluated only 57 of the submitted runs for readability, content, and overall responsiveness.
Summarizing Contrastive Viewpoints in Opinionated Text
179 Citations2010Michael J. Paul, ChengXiang Zhai +1 more
Experimental results show that the proposed approach can generate informative summaries of viewpoints in opinionatedText, with significant performance gains over bag-of-words feature sets.
When Specialists and Generalists Work Together: Overcoming Domain Dependence in Sentiment Tagging
165 Citations2008Alina Andreevskaia, Sabine Bergler
A sentiment annotation system that integrates a corpus-based classifier trained on a small set of annotated in-domain data and a lexicon-based system trained on WordNet, and a new system consisting of the ensemble of two classifiers with precision-based vote weighting that provides significant gains in accuracy and recall.
Automatically generating Wikipedia articles
138 Citations2009Christina Sauper, Regina Barzilay
An apparatus for carrying out connection and disconnection of circuit member to an electrical connector has an inner frame for regulating a space for a circuit to be mounted, a wedge member disposed between the outer frame and the inner frame in such a fashion as to be movable in a direction normal to the predetermined direction.
Structured use of external knowledge for event-based open domain question answering
107 Citations2003Grace Hui Yang, Tat‐Seng Chua +2 more
The approach to perform event-based QA by uncovering the structure within the external knowledge is extended, and the knowledge structure loosely models different facets of QA events, and is used in conjunction with successive constraint relaxation algorithm to achieve effective QA.
Parsimonious or Profligate: How Many and Which Discourse Structure Relations?
106 Citations1992Eduard Hovy, Elisabeth Maier
Information Processing & ManagementQCS: A system for querying, clustering and summarizing documents
86 Citations2007Daniel Dunlavy, Dianne P. O’Leary +2 more
Mind the gap
75 Citations2008John M. Conroy, Hoa Trang Dang
This paper proposes a method to maximize the strength of current automatic evaluations by using the method of canonical correlation, and applies this new evaluation method, which is called ROSE (ROUGE Optimal Summarization Evaluation), to find the optimal linear combination of ROUGE scores to maximize correlation with human responsiveness.
FastSum
75 Citations2008Frank Schilder, Ravikumar Kondadadi
A fast query-based multi-document summarizer based solely on word-frequency features of clusters, documents and topics called FastSum, which can rely on a minimal set of features leading to fast processing times: 1250 news documents in 60 seconds.
Columbia Academic Commons (Columbia University)Applying the Pyramid Method in DUC 2005
66 Citations2005Kathleen McKeown, Rebecca J. Passonneau +2 more
It is found that a modified pyramid score gave good results and would simplify peer annotation in the future and high score correlations between sets from different annotators, and good interannotator agreement, indicate that participants can perform annotation reliably.
QA with Attitude: Exploiting Opinion Type Analysis for Improving Question Answering in On-line Discussions and the News
66 Citations2007Swapna Somasundaran, Theresa Wilson +2 more
This paper presents a set of attitude types developed with an eye toward QA and shows that they can be reliably annotated, and develops automatic classifiers for recognizing two main types of attitudes: sentiment and arguing.
Discourse structure and the proper treatment of interruptions
55 Citations1985Barbara J. Grosz, Candace L. Sidner
The use of a computational theory of discourse based on the thesis that discourse structure is a composite of three structures the structure of the sequence of utterances, theructure of intentions conveyed, and the attentional state is illustrated.
Revisions that improve cohesion in multi-document summaries
50 Citations2002Jahna Otterbacher, Dragomir Radev +1 more
This study presents an analysis of a small corpus of manually revised summaries and presents a taxonomy of the problems that occur in the corpus, as well as the operators which, when applied to the summaries, can address these concerns.
Using Cohesion and Coherence Models for Text Summarization
47 Citations1998Inderjeet Mani, Eric Bloedorn +1 more
The paper compares salience scores produced by the cohesion and coherence methods and compares them with human judgments, and shows that while the coherence method beats the cohesion methods in accuracy of determining clause salience, the best cohesion method can reach 76% of the accuracy levels of the corency method in determining salience.
Answering opinion questions with random walks on graphs
43 Citations2009Fangtao Li, Yang Tang +2 more
An Opinion PageRank model and an Opinion HITS model are proposed to fully explore the information from different relations among questions and answers, answers and Answers, and topics and opinions to extract the opinion oriented answers.
HEXTAC: the Creation of a Manual Extractive Run
38 Citations2009Pierre-Étienne Genest, Guy Lapalme +1 more
An upper bound on purely extractive summarization techniques is established on standard and update summaries of the TAC 2009 competition, with better scores than any automatic summarization system in both linguistic quality and overall responsiveness.
Lecture notes in computer scienceOpinion Summarization of Web Comments
37 Citations2010Martin Potthast, Steffen Becker
OPINIONCLOUD, a technology to summarize and visualize opinions that are expressed in the form of Web comments, is introduced to address the issue of too much comments.
Description of the LIPN Systems at TAC 2008: Summarizing Information and Opinions.
35 Citations2008Aurélien Bossard, Michel Généreux +1 more
This paper gives a technical description of the systems developed for the TAC 2008 Campaign and algorithms and results are briefly discussed for the different tasks.
Description strategies for naive and expert users
34 Citations1985Cécile Paris
This work analyzed texts from adult and junior encyclopedias and found that two different strategies were used in describing complex physical objects to juniors and adults.
National Conference on Artificial IntelligenceNewspapers vs. Blogs: Who Gets the Scoop?
34 Citations2006Levon Lloyd, Prachi Kaulgud +1 more
The correlation between news and blog references proved substantially higher when adjusting for lead/lag shifts, although the direction of these shifts varied for different entities.
Query-Based Summarization using Rhetorical Structure Theory
33 Citations2005Wauter Bosma
Existing question answering systems—which aim at finding precise answers to questions—can be improved by exploiting summarization techniques to extract more than just the answer from the document in which the answer resides.
A Pilot Study of Opinion Summarization in Conversations
33 Citations2011Dong Wang, Yang Liu
This paper creates a corpus containing extractive and abstractive summaries of speaker's opinion towards a given topic using 88 telephone conversations and adopts two methods to perform extractive summarization, which significantly outperform the baseline approach that extracts the longest utterances.
Improving Query-Based Summarization Using Document Graphs
32 Citations2006Ahmed A. Mohamed, Sanguthevar Rajasekaran
A new approach that tackles the most challenging problems in the field of text summarization is generating a user-focused summary based on a query using document graphs.
Natural Language GenerationDISCOURSE MARKER CHOICE IN SENTENCE PLANNING
32 Citations1998Brigitte Grote, Manfred Stede
BK and its metabolite, des‐Arg9‐BK act as vasoconstrictor agents following balloon catheter injury and appear to be mediated by activation of B1 receptors.
All Blogs Are Not Made Equal: Exploring Genre Differences in Sentiment Tagging of Blogs.
30 Citations2007Alina Andreevskaia, Sabine Bergler +1 more
This paper explores the properties of two most common subgenres of blogs – personal diaries and “notebooks” – and the effects that these properties have on performance of an automatic sentiment annotation system, which was developed for binary and ternary classification of sentiment at the sentence level.
Automatic Summary Evaluation without Human Models.
27 Citations2008Annie Louis, Ani Nenkova
These results on a large scale evaluation from the Text Analysis Conference show that input-summary comparisons can be very effective and can be used to rank participating systems very similarly to manual model-based evaluations as well as to manual human judgments of summary quality without reference to a model.
Lecture notes in computer scienceChoosing a set of coherence relations for text generation: A data-driven approach
22 Citations1996Alistair Knott, Robert Dale
An active research programme in Natural Language Generation has grown up around the notion of ‘coherence relations’, where a confusing diversity exists between systems with respect to the particular relations they use.
Lecture notes in computer scienceMulti-document Summarization Using Link Analysis Based on Rhetorical Relations between Sentences
20 Citations2011Nik Adilah Hanin Zahri, Fumiyo Fukumoto
This paper proposes a link analysis incorporated with rhetorical relations between sentences to perform extractive summarization for multiple-documents and shows that the combination of PageRank along with rhetorical Relations among sentences does help to improve the quality of extractives summarization.
Columbia Academic Commons (Columbia University)Integrating Rhetorical-Semantic Relation Models for Query-Focused Summarization
19 Citations2006Kathleen McKeown, Sasha Blair-Goldensohn
This work describes a system for query-focused summarization, focusing on an enhanced, feature-based framework, and presents results of experiments to measure the impact of both RSR and other features on selection and ordering of summary content.
Theory and applications of categoriesCCNU at TAC 2008:Proceeding on Using Semantic Method for Automated Summarization Yield
18 Citations2008Tingting He, Jinguang Chen +2 more
The CCNU summarization system, PUSMS (Proceeding to Using Semantic Method for Summarization), join in TAC (formerly DUC) for the first time, using syntacticbased anaphora resolution and sentence compression algorithms in the authors' system.
Summarizing Blog Entries versus News Texts
16 Citations2009Shamima Mithun, Leila Kosseim
This paper identifies and categorize errors which typically occur in opinion summarization from blog entries and compares blog entry summaries with traditional news text summaries based on these error types to quantify the differences between these two genres of texts for the purpose of summarization.
Query-focused Supervised Sentence Ranking for Update Summaries.
15 Citations2008Seeger Fisher, Brian Roark
A supervised sentence ranking approach for use in extractive update summarization using the same general machine learning approach described in earlier DUC papers, which proves adaptable enough to be effective at queryfocused update summaries.
Theory and applications of categoriesPolyU at TAC 2008
15 Citations2008Wenjie Li, You Ouyang +2 more
The participation of the Hong Kong Polytechnic University in the TAC 2008 competition is presented and the systems for the participated tracks are introduced respectively.
A query-specific opinion summarization system
13 Citations2009Feng Jin, Minlie Huang +1 more
This paper introduces a query-specific opinion summarization system: QOS, which returns a summary with relevance to the opinions and target described by the question with some competence in this new field.
Mining the Relation between Sentiment Expression and Target Using Dependency of Words
13 Citations2006Zhongchao Fei, Jimmy Xiangji Huang +1 more
A novel method based on dependency grammars to mine the relation between sentiment expression and target is proposed, which shows that word dependency relation based methods is more flexible and effective than some previous surface patterns based methods.
Lecture notes in computer scienceImitating Human Literature Review Writing: An Approach to Multi-document Summarization
12 Citations2010Kokil Jaidka, Christopher S. G. Khoo +1 more
This study identifies the key features of natural literature reviews through a macro-level and clause-level discourse analysis and identifies human information selection strategies by mapping referenced information to source documents.
Theory and applications of categoriesCLASSY and TAC 2008 Metrics.
12 Citations2008John M. Conroy, Judith D. Schlesinger
The results of CLASSY’s submissions to TAC 2008 update and blog opinion summarization tasks are presented and many of the results for all of the systems participating in each of these tasks are evaluated.
Theory and applications of categoriesUsing coreference links and sentence compression in graph-based summarization
11 Citations2008Iris Hendrickx, Wauter Bosma
This work extended the graph-based summarization system with coreference relations and sentence compression for this years TAC update summarization challenge, and results show that using coreference Relations did not result in a significant performance gain; sentence compression had a negative effect on performance.
Long-answer question answering and rhetorical-semantic relations
10 Citations2007Sasha Blair-Goldensohn
DefScriber is presented, a system for answering definitional, biographical and other long-answer questions using a hybrid of goaland data-driven methods, motivated by a set of definitional predicates which capture information types commonly useful in definitions.
Update Summary Update.
10 Citations2008Terry Copeck, Anna Kazantseva +4 more
Runs from two different systems for the update summary task at TAC 2008 used Roget’s Thesaurus to determine semantic relatedness for the purpose of summary construction and an innovative use of the topic headline in the assessment of semantic similarity among sentences was submitted.
The University of British Columbia at TAC 2008
9 Citations2008Gabriel Murray, Shafiq Joty +2 more
This work represents the University of British Columbia's first submission to the DUC/TAC series of conferences, and it participated in both the summarization tasks: the main update task as well as the pilot task on summarizing blog opinions.
Discourse Structures to Reduce Discourse Incoherence in Blog Summarization
8 Citations2011Shamima Mithun, Leila Kosseim
This work has developed a schema-based summarization approach for query-based blog summaries that utilizes discourse structures and has significantly improved summary coherence compared to the summaries with no discourse structuring without compromising on content evaluation.
IIIT Hyderabad at TAC 2009
8 Citations2009Vasudeva Varma, Prasad Pingali +7 more
This paper describes the participation at TAC 2008 in all the three tracks and introduces two major features, a feature based on Information Loss if the authors don’t pick a particular sentence and a language modeling extension that boosts novel terms and penalizes stale terms.
Lecture notes in computer scienceComparing Approaches to Tag Discourse Relations
7 Citations2011Shamima Mithun, Leila Kosseim
This paper analyzes existing approaches to identify five discourse relations automatically, and proposes a new approach to identify attributive relations, and evaluates the accuracy of each approach with respect to the discourse relations it can identify and compares it to a human gold standard.
MADOC (University of Mannheim)Generating Update Summaries with Spreading Activation.
7 Citations2008Vivi Năstase, Katja Filippova +1 more
A novel summarization technique based on query expansion with encyclopedic knowledge and activation spreading in a large document graph is implemented for the update summaries task of the Text Analysis Conference 2008.
Opinion Summarization Using Entity Features and Probabilistic Sentence Coherence Optimization: UIUC at TAC 2008 Opinion Summarization Pilot.
7 Citations2008Hyun Duk Kim, Dae Hoon Park +2 more
It was showed that use of entity recognition during retrieval led to mixed results and re-ordering with coherence language model was not as good as heuristic polarity-based ordering using guiding phrases and the performance of coherencelanguage model can be different depending on probability function and word selection.
A Symbolic Summarizer for the Update Task of TAC 2008
7 Citations2008Pierre-Étienne Genest, Guy Lapalme +2 more
NESS, RALI's summarization system for the TAC 2008’s update task, brings improvements and continuation to the last year's “all-symbolic” approach, and ranked well in the competition, obtaining excellent scores in linguistic quality and overall responsiveness.
Event-Based Extractive Summarization Using Event Semantic Relevance from External Linguistic Resource
6 Citations2007Maofu Liu, Wenjie Li +2 more
This paper defines an event as one or more event terms along with the named entities associated, and applies PageRank ranking algorithm to estimate the significance of an event for inclusion in a summary based on the event semantic relevance derived.
Exploiting text generation techniques in the provision of help
6 Citations2002Colin Tattersall
The work exploits schema of rhetorical predicates to guide the generation process, introducing a novel, object-oriented architecture for text generation through a marriage of techniques from the fields of text generation and intelligent help systems research.
National Conference on Artificial IntelligenceKalos – a system for natural language generation with revision
6 Citations1994Ben E. Cline, J. Terry Nutter
Kalos is a natural language generation system that produces advanced draft quality text for a microprocessor users' guide from a knowledge base describing the microprocessor that uses revision iteratively to polish its initial generation.
From Extracting to Abstracting: Generating Quasi-abstractive Summaries
5 Citations2008Zhuli Xie, Barbara Di Eugenio +1 more
This paper investigates quasi-abstractive summaries, a new type of machine-generated summaries that do not use whole sentences, but only fragments from the source, and presents an approach that learns how to identify sets of sentences, where each set contains fragments that can be used to produce one sentence in the abstract.
Data Archiving and Networked Services (DANS)Contextual Salience in Query-based Summarization
4 Citations2009Wauter Bosma
A framework for graph-based summarization in order to model relations in text, so that the passages can be viewed in a broader context and significantly outperforms a competitive baseline (and participant systems) on the DUC 2005 evaluation set.
Theory and applications of categoriesERSS at TAC 2008
4 Citations2008Sylvain Bellemare, Sabine Bergler +1 more
Improvements to readability in ERSS 2008 do not reflect in significant score increases, and in fact the system fell in overall ranking.
IIT Kharagpur at TAC 2008: Statistical Model for Opinion Summarization
4 Citations2008Sushant Kumar, Diptesh Chatterjee
A statistical model is made use for opinion extraction and the subsequent summarization of the extracted opinions and its performance as per the official TAC 2008 evaluation results is presented.
A Hybrid Approach to Utilize Rhetorical Relations for Blog Summarization
3 Citations2010Shamima Mithun, Leila Kosseim
Evaluation results show that the hybrid approach introduced by combining text schema and rhetorical relations to exploit intra-sentential rhetorical relations improves summary contents by reducing question irrelevant sentences.
Summarization Focusing on Polarity or Opinion Fragments in Blogs
3 Citations2008Yohei Seki
The evaluation results showed that the polarity annotation is effective to improve the redundancy elimination and coherence in opinion summarization.
Concordia University at the TAC-2008 QA Track
2 Citations2008Majid Razmara, Leila Kosseim
To answer Squishy types of questions, the Rigid question answerer uses a classification method to group candidate answers into relevant and irrelevant classes based on the co-occurrence information of each pair of candidate answers.
Spectrum Research Repository (Concordia University)Sentence-level sentiment tagging across different domains and genres
2 Citations2009Alina Andreevskaia
This dissertation is motivated by an unmet need for high-performance domain-independent sentiment taggers and by pressing theoretical questions in NLP, where the exploration of limitations of specific approaches, as well as synergies between them, remain practically unaddressed.
UofL at TAC 2008 Update Summarization and Question Answering
1 Citations2008Yllias Chali, Sadid A. Hasan +1 more
This paper describes the update summarization and question answering systems participated in the TAC 2008 competition and presents the preliminary evaluation results of these systems.
…