... defined a lexical chain within Roget’s very gen-eral hierarchy, in which lexical relationships are traced through a common category. Hirst and St-Onge (1997) define a lexical chain using the ... Electronic Lexical Database. Cambridge MA, USA, The MIT Press. Halliday, M. A. K. and R. Hasan (1976). Cohesion in English. London, London:Longman. Hirst, G. and D. St-Onge (1997). Lexical Chains ... of reference and lexical semantic relations (superordinate and subordinate). Morris and Hirst (1991) suggested building lexical chains is important in the resolu-tion of lexical ambiguity...
... links between lexical items create cohesion. In response to Halliday & Hasan (1976)’s initiation of cohesion, other researchers have discussed lexical cohesion. However, cohesion can be ... and comprehensive description of lexicalcohesion features in English- figure out how these devices are used in texts - make comparative analysis of lexicalcohesion between English and Vietnamese ... surmount difficulties in using and understanding the lexical cohesive devices.3. Scope of the studyWithin the framework of a minor M. A thesis, we only study on lexicalcohesion in the corporate...
... 621–629,Athens, Greece, 30 March – 3 April 2009.c2009 Association for Computational Linguistics Using lexical and relational similarity to classify semantic relationsDiarmuid´O S´eaghdhaComputer ... similarity: lexical similarityand relational similarity. We present anefficient and flexible technique for imple-menting relational similarity and show theeffectiveness of combining lexical and ... 58.1Table 2: Results for set kernel and lexical kernel combination. */** indicate significant improvement atthe 0.05/0.01 level over the corresponding lexical kernel alone, estimated by paired...
... improvement throughquery expansion using information only from man-ually created lexical resources.In this paper, we re-examine the problem of queryexpansion usinglexical resources in recently ... whether queryexpansion using only manually created lexical re-sources could lead to the performance improve-ment. The main contribution of our work is toshow query expansion using only hand-crafted ... Section 2, and briefly re-view the studies of query expansion using axiomaticapproaches in Section 3. We then present our studyof usinglexical resources, such as WordNet, forquery expansion in...
... Sessions, pages 215–222,Sydney, July 2006.c2006 Association for Computational Linguistics Using Lexical Dependency and Ontological Knowledge to Improve aDetailed Syntactic and Semantic Tagger ... (in our case,the uniform distribution, since all of the in-formation in the model is specified using MEconstraints).Our baseline model contains the following fea-ture predecate set:w0t−1pos0pref1(w0)w−1t−2pos−1pref2(w0)w−2pos−2pref3(w0)w+1pos+1suff1(w0)w+2pos+2suff2(w0)suff3(w0)where:- ... whereasin (Black et al., 1998) both syntax and semanticswere predicted together in one step. In using syn-tactic tags as features, we take a softer approachto the two-stage process. The tagger...
... In this section, we define comparative keywords and extract comparative-sentence candidates by using those keywords. 3.1 Comparative keyword First of all, we classify comparative sentences ... 2009.c2009 ACL and AFNLPExtracting Comparative Sentences from Korean Text Documents Us-ing Comparative Lexical Patterns and Machine Learning Techniques Seon Yang Department of Computer Engineering, ... As a result, we achieved signifi-cant performance, an F1-score of 88.54%, in our experiments using various web documents. 1 Introduction Comparing one entity with other entities is one...
... labeling Database template fillup Mining metalinguistic activity in corpora to create lexical resources using Information Extraction techniques: the MOP system Carlos Rodríguez Penagos Language ... and guerrilla attacks, while the ACQUILEX pro-ject used similar methods for creating lexical da-tabases using the highly structured environment of machine-readable dictionary entries and other ... non -lexical markers included quota-tion marks, apposition and text formatting. A collection of potential metalinguistic patterns identified in the exploratory Sociology corpus was expanded (using...
... Number of target different content words (Japanese) 6,686 Table 3 Corpus statistics Lexical transfer using a vector-space model Eiichiro SUMITA ATR Spoken Language Translation Research ... overcome a bottleneck in building a bilingual dictionary, we proposed a simple mechanism for lexical transfer using a vector space. A preliminary computational experiment showed that our basic proposal ... is very time-consuming. In order to overcome this bottleneck, we propose a new mechanism for lexical transfer, which is simple and suitable for learning from bilingual corpora. It exploits...
... Machine Translation, pages 114 121, Stanford, CA, March. Elhadad, Michael. 1992. Using Argumentation to Control Lexical Choice: A Functional Unification Implementation. Ph.D. thesis, Columbia ... Hirst, Graeme. 1995. Near-synonymy and the structure of lexical knowledge. In AAAI Symposium on Representation and Acquisition of Lexical Knowledge: Polysemy, Ambiguity, and Generativity, ... 1996. Lexical Semantics and Knowledge Rep- resentation in Multilingual Sentence Generation. Ph.D. the- sis, University of Toronto. Yarowsky, David. 1992. Word-sense disambiguation using statistical...
... Lexical Disambiguation Using Constraint Handling In Prolog (CHIP) * George C. Demetriou Centre for Computer ... defined by a set of these primitives. Several researchers have been experimented with lexical disambiguation using MRDs, including [Lesk, 1986; Wilks et al., 1989; McDonald et al., 1990; Veronis ... Homo- graph Disambiguation Using Local Context in Large Text Corpora. In Proceedings of the 7th Annual Conference of the UW Centre for the New OED and TEXT Research, Using Corpora, pages 1-22,...
... M13.4 ConclusionIn this paper we described a genetic programmingapproach for evolving new lexical association mea-sures in order to extract collocations.The evolved association measure ... lexicog-raphy. Computational Linguistics, 16(1):22–29.Stephan Evert and Brigitte Krenn. 2005. Using smallrandom samples for the manual evaluation of statisti-cal evaluation measures. Computer ... its tree representation in postorder.Figure 1 shows the representation of the Dice co-efficient using our representation.2.2 Genetic operatorsThe crossover operator combines two parent solu-tions...
... forcomputational models of lexical cohesion: any goodmodel should at least get the core part right. Muchof the existing applied research on lexical cohesion uses WordNet-based (Miller, 1990) lexical chains ... textual cohesion. They identified a number of cohesive constructions:repetition (using the same words, or via repeatedreference, substitution and ellipsis), conjunction and lexical cohesion. Some ... on lexical cohesion, detailing thetask given to readers and the analysis ofthe experimental data. We conclude withdiscussion of the usefulness of the data infuture research on lexical cohesion. 1...
... improves the prediction of section breaks, hence, under common assumptions, the measure- ment of lexical cohesion. It is likely that these en- couraging results can be further improved. Follow- ing ... 1991. Patterns of Lexis in Text. Ox- ford University Press. Hideki Kozima. 1994. Computing LexicalCohesion as a Tool for Text Analysis. Ph.D. thesis, Univer- sity of Electro-Communications. ... between the win- dows in the text. High values indicate lexical close- ness. Troughs in the resulting similarity'curve mark spots with low cohesion. 3.3 Text Segmentation To evaluate the performance...