- ►psu.edu [PDF] A Budanitsky, G Hirst - Computational Linguistics, 2006 - MIT Press The quantification of lexical semantic relatedness has many applications in NLP, and many different
measures have been proposed. We evaluate five of these measures, all of which use WordNet
as their central resource, by comparing their performance in detecting and correcting real- ... Cited by 213 - Related articles - BL Direct - All 44 versions
- ►psu.edu [PDF] S Padó, M Lapata - Computational Linguistics, 2007 - MIT Press Traditionally, vector-based semantic space models use word co-occurrence counts from large
corpora to represent lexical meaning. In this article we present a novel framework for
construct- ing semantic spaces that takes syntactic relations into account. We introduce a ... Cited by 88 - Related articles - BL Direct - All 14 versions
A Hickl, J Williams, J Bensley, K Roberts, B Rink, … - Proceedings of the …, 2006 - u.cs.biu.ac.il Processing textual entailment, or recognizing whether the information expressed in a textual
hy- pothesis can be inferred from the information ex- pressed in another text, can be performed
in four ways. We can try to (1) derive linguistic informa- tion from the hypothesis-text pair, ... Cited by 63 - Related articles - View as HTML - All 7 versions
- ►psu.edu [PDF] S Nejati, M Sabetzadeh, M Chechik, S … - Proceedings of the 29th …, 2007 - portal.acm.org Model Management addresses the problem of manag- ing an evolving collection of models,
by capturing the re- lationships between models and providing well-defined op- erators to manipulate
them. In this paper, we describe two such operators for manipulating hierarchical ... Cited by 62 - Related articles - All 18 versions
SP Ponzetto, M Strube - Proc. of HLT-NAACL, 2006 - acl.ldc.upenn.edu In this paper we present an extension of a machine learning based coreference res- olution system
which uses features in- duced from different semantic knowledge sources. These features represent
knowl- edge mined from WordNet and Wikipedia, as well as information about semantic ... Cited by 53 - Related articles - View as HTML - All 15 versions
- ►upenn.edu [PDF] S Harabagiu, A Hickl - Proceedings of the 21st International Conference …, 2006 - portal.acm.org Work on the semantics of questions has argued that the relation between a ques- tion and its
answer(s) can be cast in terms of logical entailment. In this paper, we demonstrate how computational
systems designed to recognize textual entailment can be used to enhance the accuracy ... Cited by 45 - Related articles - BL Direct - All 13 versions
R Raina, A Haghighi, C Cox, J Finkel, J Michels, K … - Recognizing Textual … - Citeseer 57 Robust Textual Inference using Diverse Knowledge Sources Rajat Raina, Aria Haghighi,
Christopher Cox, Jenny Finkel, Jeff Michels, Kristina Toutanova Bill MacCartney, Marie-Catherine
de Marneffe, Christopher D. Manning, Andrew Y. Ng Computer Science Department ... Cited by 39 - Related articles - View as HTML - All 17 versions
- ►psu.edu [PDF] R Raina, AY Ng, CD Manning - PROCEEDINGS OF THE NATIONAL …, 2005 - aaai.org Abstract We present a system for textual inference (the task of infer- ring whether a sentence
follows from another text) that uses learning and a logical-formula semantic representation of
the text. More precisely, our system begins by parsing and then transforming sentences ... Cited by 33 - Related articles - BL Direct - All 19 versions
US Kohomban, WS Lee - Ann Arbor, 2005 - acl.ldc.upenn.edu Word Sense Disambiguation suffers from a long-standing problem of knowledge ac- quisition
bottleneck. Although state of the art supervised systems report good accu- racies for selected
words, they have not been shown to be promising in terms of scalability. In this paper, we ... Cited by 35 - Related articles - View as HTML - BL Direct - All 17 versions
- ►psu.edu [PDF] I Gurevych - corpora - Springer Abstract. We present a new method for computing semantic relatedness of con- cepts. The method
relies solely on the structure of a conceptual network and eliminates the need for performing
additional corpus analysis. The network struc- ture is employed to generate artificial ... Cited by 26 - Related articles - BL Direct - All 16 versions
- ►upenn.edu [PDF] FM Zanzotto, A Moschitti - … of the 21st International Conference on …, 2006 - portal.acm.org Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual
Meeting of the ACL, pages 401–408, Sydney, July 2006. c 2006 Association for Computational
Linguistics ... Automatic learning of textual entailments with cross-pair similarities Cited by 25 - Related articles - BL Direct - All 13 versions
T Hughes, D Ramage - Proceedings of EMNLP-CoNLL, 2007 - acl.ldc.upenn.edu Many systems for tasks such as question answer- ing, multi-document summarization, and
infor- mation retrieval need robust numerical measures of lexical relatedness. Standard
thesaurus-based measures of word pair similarity are based on only a single path ... Cited by 21 - Related articles - View as HTML - All 14 versions
- ►psu.edu [PDF] AG Maguitman, F Menczer, F Erdinc, H Roinestad, A … - World Wide Web, 2006 - Springer Abstract Automatic extraction of semantic information from text and links in Web pages is key
to improving the quality of search results. However, the assessment of automatic semantic measures
is limited by the coverage of user studies, which do not scale with the size, heterogeneity, ... Cited by 20 - Related articles - BL Direct - All 19 versions
- ►uniroma1.it [PDF] R Navigli - ACM Computing Surveys (CSUR), 2009 - portal.acm.org Word sense disambiguation (WSD) is the ability to identify the meaning of words in context in
a compu- tational manner. WSD is considered an AI-complete problem, that is, a task whose
solution is at least as hard as the most difficult problems in artificial intelligence. We ... Cited by 20 - Related articles - All 3 versions
- ►psu.edu [PDF] SP Ponzetto, M Strube - Journal of Artificial Intelligence Research, 2007 - aaai.org Wikipedia provides a semantic network for computing semantic relatedness in a more structured
fashion than a search engine and with more coverage than WordNet. We present experiments
on using Wikipedia for computing semantic relatedness and compare it to WordNet on ... Cited by 20 - Related articles - All 9 versions
- ►psu.edu [PDF] U Topkara, M Topkara, MJ Atallah - Proceedings of the 8th workshop on …, 2006 - portal.acm.org Page 1. The Hiding Virtues of Ambiguity: Quantifiably Resilient Watermarking of Natural
Language Text through Synonym Substitutions Umut Topkara Mercan Topkara Mikhail
J. Atallah ∗ Department of Computer Sciences Purdue ... Cited by 20 - Related articles - All 9 versions
K Deschacht, M Moens - ANNUAL MEETING-ASSOCIATION FOR …, 2007 - acl.ldc.upenn.edu Our society deals with a growing bulk of un- structured information such as text, images and
video, a situation witnessed in many domains (news, biomedical information, intelligence
information, business documents, etc.). This growth comes along with the demand for ... Cited by 20 - Related articles - View as HTML - BL Direct - All 19 versions
- ►psu.edu [PDF] YS Chan, HT Ng - … OF THE NATIONAL CONFERENCE ON ARTIFICIAL …, 2005 - aaai.org Abstract A critical problem faced by current supervised WSD systems is the lack of manually
annotated training data. Tackling this data acquisition bottleneck is crucial, in order to build
high- accuracy and wide-coverage WSD systems. In this paper, we show that the ... Cited by 17 - Related articles - BL Direct - All 9 versions
P Höfferer - Proceedings of 15th European Conference on …, 2007 - is2.lse.ac.uk Common user- and business-requirements demand an integrated view on the multitude of available
information resources that are processed in a variety of heterogeneous information systems.
Therefore, the research field of semantic integration which is a prerequisite for the ... Cited by 19 - Related articles - View as HTML
- ►psu.edu [PDF] N Ide - Computational Linguistics and Intelligent Text, 2006 - Springer Abstract. The work described in this paper was originally motivated by the need to map verbs
associated with FrameNet 2.0 frames to appropriate Word- Net 2.0 senses. As the work
evolved, it became apparent that the developed method was applicable for a number of ... Cited by 16 - Related articles - All 7 versions
C Cattuto, D Benz, A Hotho, G Stumme - arXiv - arxiv.org Abstract. Social bookmarking systems allow users to organise col- lections of resources on the
Web in a collaborative fashion. The in- creasing popularity of these systems as well as first insights
into their emergent semantics have made them relevant to disciplines like knowledge ... Cited by 14 - Related articles - View as HTML - All 5 versions
P Spyns, ML Reinberger - Proceedings of the 2nd European Semantic Web …, 2005 - Springer A recent evolution in the areas of artificial intelligence, database semantics and infor- mation
systems is the advent of the Semantic Web [1]. It evokes ”futuristic” visions of intelligent and autonomous
software agents including mobile devices, health-care monitoring, ubiquitous and ... Cited by 12 - Related articles - All 2 versions
A Gordon, R Swanson - ANNUAL MEETING-ASSOCIATION FOR …, 2007 - acl.ldc.upenn.edu Large corpora of parsed sentences with semantic role labels (eg PropBank) pro- vide training
data for use in the creation of high-performance automatic semantic role labeling systems. Despite
the size of these corpora, individual verbs (or role- sets) often have only a handful of in- ... Cited by 12 - Related articles - View as HTML - BL Direct - All 20 versions
H Hassan, A Hassan, O Emam - Proceedings of Empirical Methods …, 2006 - acl.ldc.upenn.edu Information Extraction (IE) is the task of extracting knowledge from unstructured text. We present
a novel unsupervised approach for information extraction based on graph mutual
reinforcement. The proposed approach does not require any seed patterns or examples. ... Cited by 14 - Related articles - View as HTML - All 15 versions
YS Chan, HT Ng - Proc. of IJCAI05, 2005 - Citeseer 1 Introduction Many words have multiple meanings. The process of iden- tifying the sense of
a word in a particular context is known as word sense disambiguation (WSD). WSD is an important
task of natural language processing (NLP), and is important for applications such as ... Cited by 12 - Related articles - View as HTML - All 15 versions
W Li, M Sun - LECTURE NOTES IN COMPUTER SCIENCE, 2006 - Springer Abstract. Automatic image annotation concerns a process of automatically la- beling image contents
with a pre-defined set of keywords, which are regarded as descriptors of image high-level
semantics, so as to enable semantic image re- trieval via keywords. A serious problem in ... Cited by 11 - Related articles - BL Direct - All 6 versions
FM Zanzotto, A Moschitti, M … - Proceedings of the …, 2006 - marcopennacchiotti.com Dermining whether or not a text T entails a hy- pothesis H is quite complex even when all
infor- mation needed to derive such inference is explic- itly asserted (Zaenen et al., 2005). For
example, the sentence T1: “At the end of the year, all solid companies pay dividends.” ... Cited by 11 - Related articles - View as HTML - All 3 versions
- ►psu.edu [PDF] B Jeong, D Lee, H Cho, J Lee - Expert Systems with Applications, 2008 - Elsevier Along with advances in the internet technology, we have been daily facing countless information
over the world, without opportune evaluation of its relevance. Especially, in the context of
business-to-business (B2B) applications integration, XML schema has been used as the ... Cited by 12 - Related articles - All 7 versions
S Pakhomov, T Pedersen, CG … - AMIA Annual Symposium …, 2005 - pubmedcentral.nih.gov Use of abbreviations and acronyms is pervasive in clinical reports despite many efforts to limit
the use of ambiguous and unsanctioned abbreviations and acronyms. Due to the fact that many
abbreviations and acronyms are ambiguous with respect to their sense, complete and ... Cited by 11 - Related articles - All 6 versions
- ►upenn.edu [PDF] SP Ponzetto, M Strube - Proceedings of the 45th Annual Meeting of the …, 2007 - portal.acm.org Page 1. Proceedings of the ACL 2007 Demo and Poster Sessions, pages 49–52,
Prague, June 2007. c 2007 Association for Computational Linguistics An API for
Measuring the Relatedness of Words in Wikipedia Simone Paolo ... Cited by 10 - Related articles - BL Direct - All 12 versions
D Laniado, D Eynard, M Colombetti - SEMANTIC WEB APPLICATIONS AND … - Citeseer Using WordNet to turn a folksonomy into a hierarchy of concepts David Laniado, Davide
Eynard, and Marco Colombetti Politecnico di Milano Dipartimento di Elettronica e Informazione
Via Ponzio 34/5, 20133 Milano, Italy {david. laniado, eynard, colombet}@ elet. polimi. it ... Cited by 10 - Related articles - View as HTML - All 9 versions
J Mitchell, M Lapata - Proceedings of ACL, 2008 - aclweb.org Vector-based models of word meaning (Lund and Burgess, 1996; Landauer and Dumais,
1997) have become increasingly popular in natural language processing (NLP) and cognitive
science. The ap- peal of these models lies in their ability to rep- resent meaning simply by ... Cited by 10 - Related articles - View as HTML - All 5 versions
C Reynaud, B Safar - International ISWC, 2007 - dit.unitn.it In order to identify mappings between the concepts of an ontology, called the source ontology
(OSrc), with concepts of another one, called the target ontology (OTar), a lot of recent works use
additional descriptions, called background knowledge, represented by a third ontology ... Cited by 10 - Related articles - View as HTML - All 8 versions
J De Bo, P Spyns, R Meersman - LECTURE NOTES IN COMPUTER SCIENCE, 2004 - Springer Abstract. In this paper a stepwise methodology for ontology align- ment and merging is
proposed. The knowledge model underlying this methodology is based on an extended version
of the initial Dogma frame- work that is a database inspired approach to ontology ... Cited by 8 - Related articles - BL Direct
B Dorow - Citeseer Page 1. A Graph Model for Words and their Meanings Von der Philosophisch-Historischen
Fakultat der Universitat Stuttgart zur Erlangung der Wurde eines Doktors der Philosophie (Dr.
phil.) genehmigte Abhandlung vorgelegt von Beate Dorow aus Albstadt ... Cited by 9 - Related articles - View as HTML - All 3 versions
- ►tiera.ru [PDF] E Blanchard, P Kuntz, M Harzallah, H Briand - Proc. 10th conference of the … - Springer Abstract. The problem of evaluating semantic similarity in a network structure knows a noticeable
renewal of interest linked to the importance of the ontologies in the semantic Web. Different semantic
measures have been proposed in the lit- erature to evaluate the strength of the semantic ... Cited by 7 - Related articles - All 3 versions
- ►psu.edu [PDF] MJ Nelson, M Mateas - Lecture Notes in Computer Science, 2007 - Springer Abstract. Game generation systems perform automated, intelligent de- sign of games (ie
videogames, boardgames), reasoning about both the abstract rule system of the game and the
visual realization of these rules. Although, as an instance of the problem of creative ... Cited by 9 - Related articles - BL Direct - All 10 versions
O Ferrández, RM Terol, R Munoz, P Martınez- … - Proceedings of the …, 2006 - u.cs.biu.ac.il This paper outlines the approach adopted by the PLSI research group at Univer- sity of Alicante
in the PASCAL-2006 sec- ond Recognising Textual Entailment chal- lenge. Our system is composed
of sev- eral components. On the one hand, the first component performs the derivation of ... Cited by 7 - Related articles - View as HTML - All 3 versions
T Van de Cruys - Proceedings of the Sixteenth Computational Linguistics …, 2005 - let.rug.nl Handcrafting semantic classes is a difficult and time-consuming job, and depends on hu- man
interpretation. Possible machine learning techniques would be much faster, and do not rely on
interpretation, because they stick to the data. The goal of this research is to present some ... Cited by 7 - Related articles - View as HTML - All 3 versions
R Johansson, P Nugues - Proc. of the Workshop on Building Frame-semantic …, 2007 - Citeseer We present two methods to address the prob- lem of sparsity in the FrameNet lexical
database. The first method is based on the idea that a word that belongs to a frame is
“similar” to the other words in that frame. We measure the similarity using a WordNet- ... Cited by 8 - Related articles - View as HTML - All 7 versions
R Higashinaka, H Isozaki - Proc. of IJCNLP, 2008 - aclweb.org This paper proposes a corpus-based ap- proach for answering why-questions. Con- ventional
systems use hand-crafted patterns to extract and evaluate answer candidates. However, such
hand-crafted patterns are likely to have low coverage of causal expres- sions, and it is ... Cited by 7 - Related articles - View as HTML - All 5 versions
- ►psu.edu [PDF] X Zhu, AB Goldberg, M Eldawy, CR Dyer, B Strock - PROCEEDINGS OF THE …, 2007 - aaai.org We present a novel Text-to-Picture system that synthe- sizes a picture from general, unrestricted
natural lan- guage text. The process is analogous to Text-to-Speech synthesis, but with pictorial
output that conveys the gist of the text. Our system integrates multiple AI compo- nents, ... Cited by 10 - Related articles - BL Direct - All 11 versions
A Bossard, M Généreux, T Poibeau - Proceedings of the Text Analysis …, 2008 - 194.254.163.25 The Text Analysis Conferences (TAC) offer a unique occasion to show innovative approaches
to text summa- rization. As a first incursion into this new research area, LIPN participated in the
following tasks of TAC 2008: the Update Summarization task and the Opinion Sum- ... Cited by 8 - Related articles - View as HTML - All 10 versions
A Koschmider, E Blanchard - First IEEE International Conference …, 2007 - aifb.uni-karlsruhe.de Abstract—Petri nets are a suitable language for modeling business processes with complex
flow structures. Processes with a number of alternative, concurrent or sequential flow structures
on the same process abstraction level may result in complex pro- cesses. Such complex ... Cited by 6 - Related articles - View as HTML - All 2 versions
I Gurevych, H Niederlich - Proceedings of” OntoLex, 2005 - acl.ldc.upenn.edu Computing Semantic Relatedness in German with Revised Information Content Metrics Iryna
Gurevych and Hendrik Niederlich EML Research gGmbH Schloss-Wolfsbrunnenweg 33 69118
Heidelberg, Germany http://www.eml-research.de/~gurevych Abstract The paper presents ... Cited by 6 - Related articles - All 15 versions
G Carenini, R Ng, X Zhou - Proc. of ACL 2008, Columbus, Ohio, USA, 2008 - aclweb.org In this paper, we study the problem of sum- marizing email conversations. We first build a sentence
quotation graph that captures the conversation structure among emails. We adopt three cohesion
measures: clue words, semantic similarity and cosine similarity as the weight of the ... Cited by 6 - Related articles - View as HTML - All 7 versions
R Knappe - Citeseer The work presented here has been done within the framework of the inter- disciplinary research
project OntoQuery and the Ph.D. programme Design and Management of Information
Technology, here at Roskilde University. I would first of all like to thank my supervisor ... Cited by 6 - Related articles - View as HTML - All 4 versions
- ►psu.edu [PDF] Y Marom, I Zukerman - IJCAI'07–Proceedings of the 20th International Joint …, 2007 - aaai.org We are developing a corpus-based approach for the prediction of help-desk responses from
features in customers' emails, where responses are repre- sented at two levels of
granularity: document and sentence. We present an automatic and human- based ... Cited by 6 - Related articles - All 12 versions
J Michelizzi - 2005 - Citeseer Page 1. Semantic Relatedness Applied to All Words Sense Disambiguation A THESIS
SUBMITTED TO THE FACULTY OF THE GRADUATE SCHOOL OF THE UNIVERSITY OF
MINNESOTA BY Jason Michelizzi IN PARTIAL FULFILLMENT OF THE REQUIREMENTS ... Cited by 6 - Related articles - View as HTML - All 3 versions
L Kosseim, R Siblini, CJO Baker, S Bergler - Frontiers in Artificial Intelligence …, 2006 - Citeseer Abstract. This paper discusses the linguistic module of an Ontology Natural Lan- guage Interaction
System that is based on semantic restrictions. The system, called ONLI , takes as input questions
in unrestricted natural language, translates them into nRQL, an extension to the RACER ... Cited by 7 - Related articles - View as HTML - BL Direct - All 7 versions
- ►aquaphoenix.com [PDF] A Haubold, A Natsev - Proceedings of the 2008 international conference …, 2008 - portal.acm.org ABSTRACT Semantic similarity between words or phrases is frequently used to find matching
correlations between search queries and documents when straightforward matching of terms
fails. This is particularly important for searching in visual databases, where pictures or ... Cited by 6 - Related articles - All 5 versions
N Tintarev, J Masthoff - Proceedings of the AH - Citeseer Recommender systems using content-based filtering suggest items according to a similarity measure
between items already known to be preferred by users, and new prospective items (eg Pazzani
& Billsus, 1997). This similarity measure needs to be chosen with care (Ziegler et al., ... Cited by 5 - Related articles - View as HTML - All 8 versions
R Ozcan, YA Aslandogan - Information Technology: Coding and …, 2005 - ieeexplore.ieee.org Abstract Concept-based access to information promises important benefits over keyword-based
access. One of these benefits is the ability to take advantage of semantic relationships among
concepts in finding relevant documents. Another benefit is the elimination of irrelevant ... Cited by 5 - Related articles - All 3 versions
L Specia, C Baldassarre, E Motta - 2006 - Citeseer We present an approach for ontology driven extraction of relations from texts aimed mainly to
produce enriched semantic annotations for the Semantic Web. The approach exploits linguistic
and empirical strategies, by means of a pipeline method involving processes such as a ... Cited by 4 - Related articles - View as HTML - All 3 versions
H Hassan, A Hassan, S Noeman - … of the TextGraphs Workshop in the …, 2006 - acl.ldc.upenn.edu Classification techniques deploy supervised labeled instances to train classifiers for various
classification problems. However labeled instances are limited, expensive, and time consuming
to obtain, due to the need of experienced human annotators. Meanwhile large amount of ... Cited by 5 - Related articles - View as HTML - All 10 versions
A Gatt, K van Deemter - Proceedings of the 6th International Workshop …, 2005 - staff.um.edu.mt The past decade1, has witnessed renewed interest in the Generation of Referring Expressions
(GRE) [23, 24, 8, 9, 10, 12, 22]. Broadening the scope beyond earlier work [3, 4, 5], recent proposals
involve algorithms that refer to sets as well as individuals, using operations such as set ... Cited by 4 - Related articles - View as HTML - All 2 versions
Y Wang - 2005 - gradworks.umi.com Document clustering is a widely used strategy for information retrieval and text data mining. In
traditional document clustering systems, documents are represented as a bag of independent
words. In this project, we propose to enrich the representation of a document by ... Cited by 5 - Related articles - Cached - All 2 versions
B Zimmermann, M Meyer, C Rensing, R … - Proceedings of the First …, 2007 - Citeseer Abstract. Due to slightly changed scenarios of usage a one-to-one reuse of existing E-Learning
resource often is not possible. Actual approaches for retrieving existing E-Learning resources
for reuse mostly do not take this into account. But to achieve a high quality often it is ... Cited by 4 - Related articles - View as HTML - All 5 versions
M Warin - Retrieved January, 2004 - Citeseer Abstract In this work I have used a number of different semantic similarity measures and WordNet
to enrich an ontology (the Common Procurement Vocabulary) with infor- mation about its
leaf-nodes. Nouns are extracted from the leaf-nodes, and compared for semantic ... Cited by 4 - Related articles - View as HTML - All 2 versions
- ►upenn.edu [PDF] I Gurevych, H Niederlich - Proceedings of the ACL 2005 on Interactive …, 2005 - portal.acm.org We present an API developed to access GermaNet, a lexical semantic database for German
represented in XML. The API provides a set of software functions for parsing and retrieving information
from GermaNet. Then, we present a case study which builds upon the GermaNet API and ... Cited by 5 - Related articles - BL Direct - All 28 versions
M Stevenson, MA Greenwood - Proc. of the Third Intl. WordNet Conf, 2006 - Citeseer Abstract Information Extraction (IE) systems often use pat- terns to identify relevant information
in text but these are difficult and time-consuming to generate manually. This paper presents a
new approach to the automatic learning of IE patterns which uses WordNet to judge the ... Cited by 6 - Related articles - View as HTML - All 6 versions
Y Wang, J Hodges - HAWAII INTERNATIONAL CONFERENCE ON …, 2006 - Citeseer Document clustering generates clusters from the whole document collection automatically and
is used in many fields, including data mining and information retrieval. In the traditional vector
space model, the unique words occurring in the document set are used as the features. ... Cited by 4 - Related articles - View as HTML - BL Direct - All 5 versions
S Mithun, L Kosseim, V Haarslev - … of The First International Workshop on …, 2007 - Citeseer This paper describes an approach to resolve quanti- fiers and number restrictions in natural language
ques- tions to query ontologies. Incorporating this feature enables natural language query interfaces
to capture a wider range of user queries. To deal with quantifiers and number restrictions, ... Cited by 5 - Related articles - View as HTML - All 7 versions
- ►psu.edu [PDF] I Zukerman, Y Marom - LECTURE NOTES IN COMPUTER SCIENCE, 2006 - Springer Abstract. We present a comparative study of corpus-based methods for the au- tomatic synthesis
of email responses to help-desk requests. Our methods were developed by considering two
operational dimensions: (1) information-gathering technique, and (2) granularity of the ... Cited by 4 - Related articles - BL Direct - All 5 versions
A Islam, D Inkpen - Proceedings of the International Conference on …, 2006 - Citeseer This paper presents a new corpus-based method for calculating the semantic similarity of two
target words. Our method, called Second Order Co-occurrence PMI (SOC-PMI), uses Pointwise
Mutual Information to sort lists of important neighbor words of the two target words. Then ... Cited by 4 - Related articles - View as HTML - All 8 versions
PY Liu, TJ Zhao, XF Yu - Machine Learning and Cybernetics, 2006 …, 2006 - ieeexplore.ieee.org Abstract In the task of auto-building a Chinese-English semantic lexicon for translation
selection, this research presents a method, which introduces WordNet similarity measures to
wash out misaligned Chinese-English word pairs. Six different proposed measures of ... Cited by 4 - Related articles
M Kouylekov, B Magnini - Lecture Notes in Computer Science, 2006 - Springer Abstract. This paper addresses Textual Entailment (ie recognizing that the meaning of a text
entails the meaning of another text) using a Tree Edit Distance algorithm between the syntactic
trees of the two texts. A key aspect of the approach is the estimation of the cost for the ... Cited by 4 - Related articles - BL Direct
Z Zhang, H Che, P Shi, Y Sun, J Gu - IBIS, 2006 - dit.unitn.it Abstract: Schema matching is the task of finding semantic correspondences between elements
of two schemas, which plays a key role in many database applications. In this paper, we cast
the schema matching problem (SMP) into a multi-labeled graph matching problem. First, ... Cited by 4 - Related articles - View as HTML - All 2 versions
- ►psu.edu [PDF] U Topkara, MJ Atallah, M Topkara - … of the 2007 ACM symposium on …, 2007 - portal.acm.org ABSTRACT Research on password authentication systems has repeat- edly shown that people
choose weak passwords because of the difficulty of remembering random passwords.
Moreover, users with multiple passwords for unrelated activities tend to choose almost ... Cited by 4 - Related articles - All 9 versions
- ►aclweb.org [PDF] A Gledson, J Keane - Proceedings of the 22nd International Conference …, 2008 - portal.acm.org Semantic relatedness between words is important to many NLP tasks, and nu- merous measures
exist which use a vari- ety of resources. Thus far, such work is confined to measuring similarity
between two words (or two texts), and only a handful utilize the web as a corpus. This ... Cited by 5 - Related articles - All 7 versions
- ►irisa.fr [PDF] F Moreau, V Claveau, P Sébillot - Coria 2007, 2007 - books.google.com 223 Intégrer plus de connaissances linguistiques en recherche d'information peut-il augmenter
les performances des systèmes? Fabienne Moreau*—Vincent Claveau*—Pascale Sébillot*
* IRISA Campus universitaire de Beaulieu 35042 Rennes cedex, France {Fabienne. ... Cited by 7 - Related articles - All 3 versions
- ►aclweb.org [PDF] HA Schwartz, F Gomez - Proceedings of the Twelfth Conference on …, 2008 - portal.acm.org This paper presents a method of acquiring knowledge from the Web for noun sense
disambiguation. Words, called selectors, are acquired which take the place of an instance of
a target word in its local con- text. The selectors serve for the system to essentially learn ... Cited by 3 - Related articles - All 10 versions
- ►psu.edu [PDF] D Sanchez, A Moreno - Lecture Notes in Computer Science, 2006 - Springer The Web is an invaluable repository of knowledge. It has been considered that the num- ber
of resources available in the Web is so vast and the amount of people generating web pages
is so enormous, that the Web information distribution approximates the ac- tual real ... Cited by 3 - Related articles - BL Direct - All 4 versions
S Brody - ANNUAL MEETING-ASSOCIATION FOR …, 2007 - acl.ldc.upenn.edu Recently, there has been a rise of in- terest in unsupervised detection of high- level semantic
relations involving com- plex units, such as phrases and whole sentences. Typically such approaches
are faced with two main obstacles: data sparseness and correctly generalizing from the ... Cited by 3 - Related articles - View as HTML - BL Direct - All 13 versions
- ►psu.edu [PDF] N Tansalarak, KT Claypool - Data & Knowledge Engineering, 2007 - Elsevier Integration of multiple heterogeneous data sources continues to be a critical problem for many
application domains and a challenge for researchers world-wide. With the increasing popularity
of the XML model and the proliferation of XML documents on-line, automated matching of ... Cited by 4 - Related articles - All 7 versions
E Cabrio, M Kouylekovand, B Magnini - Proceedings of TAC08, 4th PASCAL …, 2008 - nist.gov The main goal of FBK-irst participation at RTE-4 was to experiment the use of com- bined specialized
entailment engines, each addressing a specific phenomena relevant to entailment. The approach
is motivated since textual entailment is due to the combination of several linguistic ... Cited by 5 - Related articles - View as HTML - All 2 versions
L Kosseim, A Beaudoin, A Keighbadi, M Razmara - Fifteenth Text REtrieval …, 2006 - Citeseer This is the first year in a while that Concordia University participated in TREC- QA. We only participated
in the main task, which consisted in three types of questions: factoid, list and other. Although
all three question types contributed equally in the final system score, we put most of our ... Cited by 3 - Related articles - View as HTML - All 7 versions
D Portnoy - 2006 - student.seas.gwu.edu Page 1. UNSUPERVISED DISCOVERY OF THE MULTIPLE SENSES OF WORDS
AND THEIR PARTS OF SPEECH by David Portnoy BS in Ocean Engineering,
December 1993, The Florida Institute of Technology MS in Computer ... Cited by 4 - Related articles - View as HTML - All 2 versions
- ►ubc.ca [PDF] E Santos-Neto, D Condon, N Andrade, A … - Proceedings of the 20th …, 2009 - portal.acm.org Elizeu Santos-Neto § ,David Condon ⊕ ,Nazareno Andrade +§ ,Adriana Iamnitchi ⊕ ,Matei Ripeanu
§ ... Electrical & Computer Engineer § University of British Columbia 2332 Mail Mall – KAIS 4075
Vancouver, BC, Canada +1.604.827.4270 {elizeus,matei}@ece.ubc.ca Cited by 5 - Related articles - All 5 versions
M OUEDERNI, G SALAÜN, C CANAL, E PIMENTEL - lcc.uma.es Composition of components or services is a crucial issue in Software Engineering. However,
direct reuse and composition of existing services is in most of cases impossible because their
interfaces present some incompatibilities. Here, we assume service interfaces described ... Cited by 3 - Related articles - View as HTML
- ►psu.edu [PDF] IC Chow, JJ Webster - LECTURE NOTES IN COMPUTER SCIENCE, 2007 - Springer Abstract. The work described in this paper was originally motivated by the construction of a lexical
semantic knowledge base for analysis of Ideational Metafunction of language in Systemic Functional
Grammar and the Generalized Upper Model ontology. The work involves mapping ... Cited by 3 - Related articles - BL Direct - All 7 versions
- ►psu.edu [PDF] CS Miller - Lecture Notes in Computer Science, 2005 - Springer Abstract. A computational cognitive model of Web navigation is a working computer system that
simulates human users searching for items in a Web site. A fully working model must automate
aspects of human perception, decision making and physical control. To successfully ... Cited by 3 - Related articles - BL Direct - All 7 versions
A Kennedy, S Szpakowicz, P Warsaw - Paragraph - aclweb.org Roget's Thesaurus has gone through many re- visions since it was first published 150 years
ago. But how do these revisions affect Ro- get's usefulness for NLP? We examine the differences
in content between the 1911 and 1987 versions of Roget's, and we test both ver- sions ... Cited by 3 - Related articles - View as HTML - All 5 versions
- ►uottawa.ca [PDF] A Islam, D Inkpen, I Kiringa - The VLDB Journal, 2008 - Springer Abstract In this paper, we present a method for database schema matching: the problem of identifying
elements of two given schemas that correspond to each other. Schema matching is useful in
e-commerce exchanges, in data inte- gration/warehousing, and in semantic web ... Cited by 2 - Related articles - All 4 versions
