Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
18625 papers
Cette thèse aborde le problème de la structuration de bases lexicales multilingues (BDLM) en lexies et axies, à partir de ressources existantes. Ce travail est motivé par l'inadéquation des techniques existantes utilisées isolément, pour la structuration de BDLM. Pour résoudre ce problème, la stratégie proposée est de composer des techniques existantes de désambiguïsation pour structurer semi-automatiquement des bases lexicales multilingues à lexies et acceptions interlingues. De plus, cette thèse propose une catégorisation des critères d'évaluation de la qualité des BDLM, ainsi que les mesures correspondantes. Cette stratégie a été implémentée dans Jeminie, un système logiciel adaptable qui permet d'implémenter à la fois des méthodes de structuration de BDLM et des mesures de qualité, sous la forme de modules logiciels réutilisables. Des compositions arbitraires de ces modules peuvent être définies par un lexicologue dans un langage de haut niveau d'abstraction, ce qui permet d'adapter facilement la structuration et l'évaluation de qualité en fonction des objectifs du lexicologue et des ressources disponibles sans nécessiter de connaissances en programmation. L'intérêt de cette approche a été validé expérimentalement: la qualité des BDLM obtenues est meilleure par combinaison de techniques qu'avec chaque technique antérieure utilisée seule.
Preservice and experienced teachers ( N=58, from 7 universities) wrote lesson plans for a hypothetical beginning band lesson, using one page from a band method book as source material. Lesson plans were analyzed for word count, level of detail, and for strategies that appeared most frequently. Experienced teachers used fewer words than undergraduates but revealed the same number of strategies and level of detail, on average. There were institutional differences in the variety of strategies incorporated, indicating certain institutions may value a wider range of strategies and activities in beginning band classes. Participants also compared their written plans to a published lesson plan and rated their familiarity with various approaches, giving another view on strategies considered most common. Familiarity ratings were similar when comparing preservice and experienced teachers and when comparing institutions. Degrees of prevalence of specific strategies, such as decontextualization of material, repetition, and modeling are discussed. May 7, 2004 January 18, 2005.
Great progress has been made in parsing the Wall Street Journal portion of the Penn Treebank. Now parsing languages other than English is an intensive research area. Head-driven model is one of the best English parsing models. It has been successfully applied to Czech but failed to outperform a base-line model in parsing German. This paper attempts to parse Chinese with head-driven model. Promising experimental results demonstrate that head-driven model works well for Chinese. We propose a hybrid parsing strategy, which combines head-driven model with a Chinese base phrases parsing model. The combined model not only improves the performance but also makes the parser space and time efficient. We evaluate our method in PARSEVAL measures, and the combined model performances are at 79.88% precision, 81.97% recall.
We report two studies in which the interplay between stimulus properties and perceiver characteristics in the appreciation car interiors was investigated. In Experiment 1 three design components, complexity, curvature and innovativeness, which are all thought to affect design appreciation were combined in a fully factorial design. All dimensions were confirmed to affect ratings, and curvature and innovativeness particularly affected the attractiveness ratings. Curved and non-innovative designs were generally preferred. Moreover, participants who were particularly interested in art were more sensitive to curvature and innovativeness. In Experiment 2 two dimensions of Experiment 1 were replicated using similar stimuli. Moreover, the specific effects of a design knowledge treatment were investigated. Results replicated the preference for curved and non-innovative (rather classic) designs. The treatment had only small effects, which support a general rather than dimension-specific effects of cognitive pre-information. Copyright © 2005 John Wiley & Sons, Ltd.
Linguistic research and language technology development employ large repositories of ordered trees. XML, a standard ordered tree model, and XPath, its associated language, are natural choices for storing and querying linguistic data. However, several important expressive features required for linguistic queries are missing in XPath. In this paper, we motivate and illustrate these features with a variety of linguistic queries. Then we define extensions to XPath which support linguistic tree queries. We provide a relational representation for trees, and define an SQL translation for queries. Experiments demonstrate that the query system is significantly faster than other linguistic tree query systems for a wide range of queries. 1
During the past few years, the information representation and retrieval sector in the area of Documentation and Biblioteconomy has had to assume the important repercussions of the Internet and its associated technologies, and in particular, the World Wide Web (WWW). Technological modifications arising from these important changes are leading to the gradual digitalisation of the information representation and retrieval sector, affecting information artefacts, representation and retrieval tools and user requirements.\nIn the light of this growing context of digitalisation, diverse information representation and retrieval tools exist, which must be studied in addition to diverse fields of knowledge in which these tools have originated: Linguistics, Artificial Intelligence, Documentation, Linguistic Engineering... Hence, in specialised literature, analyses are performed on information representation and retrieval tools, taxonomies, classification systems, computational lexicons, lexical databases, thesauruses, titles lists, knowledge bases, conceptual maps, ontologies, synonym rings and semantic networks, among others. Among this wide spectrum of information representation and retrieval tools are thesauruses and ontologies, which are most often linked in bibliography, even though they come from completely different disciplinary areas. However, the conceptualisation applied by authors to the terms "thesaurus" and "ontology" is quite diverse, and sometimes authors confuse, oppose, complement or overlap both these concepts.\nThe overall objective of the present article [1] is to establish the relationship between the concepts of thesaurus and ontology in the Documentation and Biblioteconomy field. Two specific objectives have been established for this purpose. Firstly, to make an analysis of the thesaurus-based concept with a view to defining its most important characteristics and to verify the similarities and differences it shares with ontologies. And secondly, to establish a definition for the ontology concept, also for the purpose of verifying its characteristics and analysing the similarities and differences it has with thesauruses.
This research shows a cost-effective approach to simultaneously produce proteases, amylases, and endoglucanases from <i>Stachybotrys microspora</i> that could be considered a compatible detergent additive in the green detergent industry.
Recent years have seen a revived interst in semantic parsing by applying statistical and machinelearning methods to semantically annotated corpora such as the FrameNet and the Proposition Bank. So far much of the research has been focused on English due to the lack of semantically annotated resources in other languages. In this paper, we report first results on semantic role labeling using a pre-release version of the Chinese Proposition Bank. Since the Chinese Proposition Bank is superimposed on top of the Chinese Treebank, i.e., the semantic role labels are assigned to constituents in a treebank parse tree, we start by reporting results on experiments using the handcrafted parses in the treebank. This will give us a measure of the extent to which the semantic role labels can be bootstrapped from the syntactic annotation in the treebank. We will then report experiments using a fully automatic Chinese parser that integrates word segmentation, POS-tagging and parsing. This will gauge how successful semantic role labeling can be done for Chinese in realistic situations. We show that our results using hand-crafted parses are slightly higher than the results reported for the state-of-the-art semantic role labeling systems for English using the Penn English Proposition Bank data, even though the Chinese Proposition Bank is smaller in size. When
In the first part of this technical report we describe our approach to design a new data format, based on XML (Extensible Markup Language) and aimed to provide a better and unifying alternative to various legacy data formats used in various areas of corpus linguistics and specifically in the field of structured annotation. We introduce the first version of the format, called Prague Markup Language (PML). This version has already been employed as the main data format for the upcoming Prague Dependency Treebank 2.0 (PDT). Finally we outline our ideas and proposals for further improvement of PML, based on our current experience with using and processing data in PML format in the PDT 2.0 project. The second part of the technical report contains the state-of-the-art specification of PML. Technicka zprava c. TR-2005-29 Technicka zprava projektu Integrace jazykových zdrojů za ucelem extrakce informaci z přirozených textů Projekt Informacni spolecnosti Grantove agentury Akademie věd CR Registracni cislo GA AV CR: 1ET101120503 Interni kod MFF: 207-14 / 242083
By Stéphane Chaudier. (Recherches proustiennes, 2). Paris, Champion, 2003. 549 pp. Hb €85.00. A reservoir of potent symbolic referents, religious vocabulary is deflected by Proust onto such secular contexts as society, love, sexuality, and literary creation. The tensions born of this juxtaposition of sacred and profane lie at the heart of Stéphane Chaudier's far-reaching analysis. Sensitive close textual readings illuminate the mechanisms of this ‘détournement’ of religious terms in the first part of the study. Playing with the hierarchy of sublime and trivial, high and low styles, Proust's often ludic handling of this intertext is interpreted as a means of transcending one's own universe, of perceiving its comic strangeness. Yet Chaudier rightly detects no anti-religious philosophical system in Proust's work, discovering instead, in his desacralization of religious terms, a stylistic transgression of social and linguistic norms and, more generally, an ironic perspective on all forms of cultural domination, whether organized religion or, as Chaudier persuasively discusses, a social orthodoxy. Examining the beliefs — akin to, but prevailing over religious convictions — that support the shifting edifice of social hierarchies, the study demonstrates how social power, in Proust, is based on ‘la gestion de biens symboliques’ (pp. 14–15) such as aristocratic prestige, wit, or the expression of avant-garde aesthetic opinions. Proust's presentation of this socio-religious hegemony is ambivalent, however, for, as Chaudier's analysis shows, Proust both recognizes, even admires, the strength of social groupings and simultaneously reveals social power to be hollow. Ontologically ‘empty’ signs such as Mme Verdurin's laugh are revealingly examined here. Reflecting the subtleties of Proust's position, Chaudier ultimately defines society as a ‘néant’, but a captivating one, and if idealization is followed by reality, ‘croyance’ by ‘savoir’, the former is not entirely negated by the latter — poetic truth remains. The study consistently foregrounds the material world, recognizing that the body is the conduit for experience. The role of religious metaphor in conceptualizing the erotic thus provides the focus of one part of the analysis. Presented in these terms, the erotic also becomes a metaphor for knowledge and creativity: Sodom, for example, offers a vision of fruitful union in terms of aesthetic — if not physical — creation, whilst Gomorrah, as the epitome of alterity, is the poetic principle that threatens language with extinction, that assigns its limits. Chaudier's subsequent examination of the function of Judaeo-Christian references within aesthetic reflections identifies the body as the artist's means of encountering the world rather than as an obstacle to the act of creation. Sensual and spiritual are thus reconciled: the artist-demiurge creates matter from nothing by an act of the spirit. The metaphor of the novel as cathedral is also teased out in all its intricacy — at times stable and coherent, at others vacillating and contradictory. Like the work of art, it is the incarnation of the infinite within the finite; ultimately, however, Proust's profane cathedral is a godless one. The study ends with a series of useful indexes and an extensive bibliography of French-language criticism. Opening up many new perspectives, it represents a valuable addition to recent English-language scholarship in this field.
The annotations of the Penn Discourse Treebank (PDTB) include (1) discourse connectives and their arguments, and (2) attribution of each argument of each connective and of the relation it denotes. Because the PDTB covers the same text as the Penn TreeBank WSJ corpus, syntactic and discourse annotation can be compared. This has revealed significant differences between syntactic structure and discourse structure, in terms of the arguments of connectives, due in large part to attribution. We describe these differences, an algorithm for detecting them, and finally some experimental results. These results have implications for automating discourse annotation based on syntactic annotation.
All studies that examined the co-occurrence of pleasure and displeasure revealed at least some reports of mixed feelings (i.e., reports of concurrent pleasure and displeasure). Some researchers attribute these reports to measurement error, whereas others regard them as valid. This article examined response latencies of affect ratings to test the validity of reported mixed feelings. First, I demonstrate that respondents need more time to indicate the presence of an affect than the absence of an affect on unipolar response formats. Then, I demonstrate that mixed feelings are reported even when response latencies show a unipolar pattern for displeasure ratings, while the results for pleasure ratings were more mixed, but additional evidence suggests that they also are valid reflections of pleasure. In addition, I demonstrate that pleasure and displeasure ratings are independent of item-order and item-spacing. These results provide further support for the validity of reported mixed feelings and two-dimensional representations of pleasure and displeasure.
Contemporary neuropsychological studies have stressed the widely distributed and multicomponential nature of human affective processes. Here, we examined facial electromyographic (EMG) (zygomaticus and corrugator muscle activity), autonomic (skin conductance and heart rate) and subjective measures of affective valence and arousal in patient TG, a 30 year-old man with left anterior mediotemporal and left orbitofrontal lesions resulting from a traumatic brain injury. Both TG and a normal control group were exposed to hedonically valenced visual and olfactory stimuli. In contrast with control subjects, facial EMG and electrodermal activity in TG did not differentiate among pleasant, unpleasant and neutral pictures. In addition, the controls reacted spontaneously with larger corrugator EMG activity and higher skin conductance to unpleasant odors. By contrast, the subjective feeling states (pleasure and arousal ratings) remained preserved in TG. The covariation between facial and self-report measures of negative valence was also a function of the nature of the olfactory task in the patient only. Taken together, the data suggest a functional dissociation between brain substrates supporting generation of emotion and those supporting representation of emotion.
Annotated linguistic databases are widely used in linguistic research and in language technology development. These annotations are typically hierarchical, and represent the nested structure of syntactic and prosodic constituents. Recently, the LPath language has been proposed as a convenient path-based language for querying linguistic trees. We establish the formal expressiveness of LPath relative to the XPath family of languages. We also extend LPath to permit simple closures, resulting in a first-order complete language which we believe is sufficiently expressive for the majority of linguistic tree query needs. 1.
We describe a method of constructing Thai WordNet, a lexical database in which Thai words are organized by their meanings. Our methodology takes WordNet and LEXiTRON machine-readable dictionaries into account. The semantic relations between English words in WordNet and the translation relations between English and Thai words in LEXiTRON are considered. Our methodology is operated via WordNet Builder system. This paper provides an overview of the WordNet Builder architecture and reports on some of our experience with the prototype implementation.
The acquisition of grammar from a corpus is a challenging task in the preparation of a knowledge bank. In this paper, we discuss the extraction of Chinese grammar oriented to a restricted corpus. First, probabilistic context-free grammars (PCFG) are extracted automatically from the Penn Chinese Treebank and are regarded as the baseline rules. Then a corpusoriented grammar is developed by adding specific information including head information from the restricted corpus. Then, we describe the peculiarities and ambiguities, particularly between the phrases “PP” and “VP” in the extracted grammar. Finally, the parsing results of the utterances are used to evaluate the extracted grammar.
Development and testing of a large range of NLP applications presuppose corpora annotated at levels more advanced than those of part–of–speech and shallow syntax. Therefore, multi–layered annotation schemes have been designed in order to provide deeper representations of intra – and inter–sentential structure and meaning.
Modern day lexical databases are not constructive, but differential (Miller et al 1990).We outline the logical structure of the task of a conceptual analyst who wishes to construct a constructive lexicon based on a Universal Theory Model of Concepts.Elementary notions of descriptive and explanatory adequacy are developed within this model.The diverse streams of evidence available for the conceptual analyst to engage in empirical inquiry are reviewed in the domains of light and perception. Theories for Constructive LexiconsMajor projects have been conducted for centuries to record, in one form or another, representations of word meanings.This has been in the form of the lexicographer's dictionary or the more modern computational linguist's electronic databases (WordNet, FrameNet, Verb-Net) e.g. last year's symposium (Miller, Fillmore, Palmer, Lenat and Hayes 2004).The degree to which computational linguists and cognitive scientists draw upon these resources as accurate descriptions of lexical knowledge is astonishing.Researchers speak of "putting meaning in your trees", providing "deep semantics", automatically labeling "semantic roles", or using Word-Net as the authority for word sense disambiguation, to name some key projects.(Palmer et al 2002, Fillmore et al 2001, Gildea and Jurafsky 2002) Given the increasing reliance to these databases, it may appear that the terms meaning and semantic are not being used glibly and that the theoretical foundations of these databases were sound.Even the most cursory analysis shows that this is not so.Consider the distinction made by the originators of WordNet between a constructive vs. differential lexicon: In a differential theory of the lexicon, meanings can be represented by any symbols that enable a theorist to distinguish among them; In a constructive theory of the lexicon, the representation should "contain sufficient information to support an accurate construction of the concept (by either a person or a machine)" (Miller et al 1990).Today's dictionaries and all of today's lexical databases are differential: the intension of synsets of WordNet are just sufficient so that someone who already knows English can distinguish among synsets, while the thematic roles used in VerbNet and FrameNet are notoriously difficult to define: primitive terms such as Agent,
We formalize weighted dependency parsing as searching for maximum spanning trees (MSTs) in directed graphs. Using this representation, the parsing algorithm of Eisner (1996) is sufficient for searching over all projective trees in O(n3) time. More surprisingly, the representation is extended naturally to non-projective parsing using Chu-Liu-Edmonds (Chu and Liu, 1965; Edmonds, 1967) MST algorithm, yielding an O(n2) parsing algorithm. We evaluate these methods on the Prague Dependency Treebank using online large-margin learning techniques (Crammer et al., 2003; McDonald et al., 2005) and show that MST parsing increases efficiency and accuracy for languages with non-projective dependencies.
Discourse connectives can be analyzed as discourse level predicates which projectpredicate-argument structure on a par with verbs at the sentence level. The PennDiscourse Treebank (PDTB) reflects this view in its design providing annotation ofthe discourse connectives and their arguments. Like verbs, discourse connectiveshave multiple senses. We present a set of manual sense annotation studies for threeconnectives whose arguments have been annotated in the PDTB. Using syntacticfeatures computed from the Penn Treebank and a simple MaxEnt model, we haveachieved some success in automatically disambiguating among their senses.
Abstract. The present paper focuses on representation of morphological meanings on the underlying syntactic level. The concept of semantic counterparts of morphological meanings, the so-called grammatemes, was introduced in Functional Generative Description in the 1960’s. We suggest an elaborated system of these grammatemes, which have become a part of the tectogrammatical level of the Prague Dependency Treebank.
In this paper we examine the issues that arise from the annotation of the discourse connectives for the Chinese Discourse Treebank Project. This project is based on the same principles as the PDTB, a project that annotates the English discourse connectives in the Perm Treebank. The paper begins by outlining range of discourse connectives under consideration in this project and examines the distribution of the explicit discourse connectives. We then examine the types of syntactic units that can be arguments to the discourse connectives. We show that one of the most challenging issues in this type of discourse annotation is determining the textual spans of the arguments and this is partly due to the hierarchical nature of discourse relations. Finally, we discuss sense discrimination of the discourse connectives, which involves separating discourse connective from non-discourse connective senses and teasing apart the different discourse connective senses, and discourse connective variation, the use of different connectives to represent the same discourse relation.
This article is devoted to the problem of quantifying noun groups in German. After a thorough description of the phenom ena, the results of corpus-based investigations are described. Moreover, some examples are given that underline the necessity of integrating some kind of information other than grammar sensu stricto into the treebank. We argue that a more sophisticated and fine-grained annotation in the treebank would have very positve effects on stochastic parsers trained on the treebank and on grammars induced from the treebank, and it would make the treebank more valuable as a source of data for theoretical linguistic investigations. The information gained from corpus research and the analyses that are proposed are realized in the framework of SILVA, a parsing and extraction tool for German text corpora.
In this article, I explore the ways in which ethnic identity is expressed by following the formulaic socio-linguistic norm, the very method of which defies the authenticity of identity itself, thereby asserting the identity's multi-facetedness as sustained in performative linguistic practice. I look at multi-sited socio-linguistic interactions among Koreans in Japan, who claim their primary identity to be that of North Korea's overseas citizens even though none of them have North Korean passport or nationality. Their identity, in other words, is based on ideological commitment, which is in reality supported by their ongoing linguistic practice. A close look at their socio-linguistic life reveals their ethnicity's dual or multiple ontology, which challenges among other things the currently dominant assertion of Japanese self in the western academic discourse.
In this paper we discuss the application of semi-supervised machine learning method-co-training on Chinese Text Chunking. Firstly, we give the definition of Chinese chunk,then the formalized definition of co-training algorithm.We proposed a example selection method based on the consistence, using two classifiers: Transductive HMM and fnTBL to combine a classification system to perform the Chinese text chunking task with the small-scale labled Chinese treebank and large-scale unlabled Chinese corpus. The result were compared with the self-training result and the result of the non co-training experiment in which we only used the small-scale Chinese treebank as training data and use one classifier(Transductive HMM or fnTBL) to recognize the Chinese chunk. The improvement is significant, the F value of the two classifiers reached 83.41%,85.34%, get a improvement of 2.13 points and 7.21 points respectively.
In this paper, we extend an existing parser to produce richer output annotated with function labels. We obtain state-of-the-art results both in function labelling and in parsing, by automatically relabelling the Penn Treebank trees. In particular, we obtain the best published results on semantic function labels. This suggests that current statistical parsing methods are sufficiently general to produce accurate shallow semantic annotation.
Toempower thegeneral massthrough access toinformation andknowledge, organized efforts arebeing madetodevelop relevant content inlocallanguages andprovide local language capabilities toutility software. Wehavedeveloped a Question Answering (QA)System forHindidocuments that wouldberelevant formassesusingHindiasprimary language ofeducation. Theusershould beabletoaccess information fromE-learning documents ina userfriendly way,that isbyquestioning thesystem intheir native language Hindi andthesystem will return theintended answer (also in Hindi) bysearching incontext fromtherepository ofHindi documents. Thelanguage constructs, querystructure, commonwords, etc.arecompletely different inHindias compared toEnglish. A novelstrategy, inaddition to conventional search andNLP techniques, wasusedto construct theHindi QAsystem. Thefocus isoncontext based retrieval ofinformation. Forthis purpose weimplemented a Hindi search engine that works onlocality-based similarity heuristics toretrieve relevant passages fromthecollection. It alsoincorporates language analysis modules like stemmer andmorphological analyzer aswellasself constructed lexical database ofsynonyms. Theexperimental results over corpus oftwoimportant domains ofagriculture andscience showeffectiveness ofourapproach.
Three studies demonstrate the warm glow heuristic (Monin, 2003) without relying on aggregated ratings, and illustrate the important distinction between correlating average ratings versus averaging individual correlations. In Study 1, we re-analyze previous data correlating individual ratings with aggregates from another small sample of raters. In Study 2, we correlate individual familiarity ratings with normed attractiveness from a large sample of raters (n > 2,500). Study 3 bypasses the issue of aggregates altogether by having participants provide both attractiveness and familiarity ratings and computing correlations within participants. Despite this more conservative approach, the results of all three studies support the existence of the beautiful–is–familiar phenomenon.
In trying to understand the dynamics of dialect convergence and divergence, we are faced with two sets of problems that are rarely reconciled. One set pertains to the social factors that operate in the initiation, actuation, and diffusion of linguistic variation and change. Viewed as social processes, dialect convergence and divergence can easily be understood as the outcome of speakers' activity, either in the short term as the result of variations which arise in direct, face-to-face communication, or in the long term as the outcome of a process in which patterns of social interaction lead to changes in the linguistic norms of the entire speech community (but cf. Auer and Hinskens, this volume). Viewed in this way, changes in the linguistic system arise from changes in the speech patterns of speakers (see Milroy and Milroy 1985 for further discussion). A second set of factors, however, can also be compelling. If we assume that knowledge of a language is knowledge of an abstract system of rules which operates irrespective of the context of performance, it should equally be possible to bracket out the social dimension and understand dialect convergence and divergence as internally motivated processes that stem from deep-seated general principles such as universal constraints on markedness.
Building on work showing the harmfulness of annotation errors for both the training and evaluation of natural language processing technologies, this thesis develops a method for detecting and correcting errors in corpora with linguistic annotation. The so-called variation n-gram method relies on the recurrence of identical strings with varying annotation to find erroneous mark-up. We show that the method is applicable for varying complexities of annotation. The method is most readily applied to positional annotation, such as part-of-speech annotation, but can be extended to structural annotation, both for tree structures— as with syntactic annotation—and for graph structures—as with syntactic annotation allowing discontinuous constituents, or crossing branches. Furthermore, we demonstrate that the notion of variation for detecting errors is a powerful one, by searching for grammar rules in a treebank which have the same daughters but different mothers. We also show that such errors impact the effectiveness of a grammar induction algorithm and subsequent parsing. After detecting errors in the different corpora, we turn to correcting such errors, through the use of more general classification techniques. Our results indicate that the particular classification algorithm is less important than understanding the nature of the errors and altering the classifiers to deal with these errors. With such alterations, we can automatically correct errors with 85% accuracy. By sorting the errors, we can
We propose a framework that enables the acquisition of annotation-heavy resources such as syntacfic dependency tree corpora for low-resource languages by importing linguistic annotations from high-quality English resources. We present a large-scale experiment showing that Chinese dependency trees can be induced by using an English parser, a word alignment package, and a large corpus of sentence-aligned bilingual text. As a part of the experiment, we evaluate the quality of a Chinese parser trained on the induced dependency treebank. We find that a parser trained in this manner out-performs some simple baselines inspite of the noise in the induced treebank. The results suggest that projecting syntactic structures from English is a viable option for acquiring annotated syntactic structures quickly and cheaply. We expect the quality of the induced treebank to improve when more sophisticated filtering and error-correction techniques are applied.
Traditional Chinese text chunking approach is to identify phrases using only one model and same features. It is shown that one model couldn't comprise each phrase's characteristics, and same features are not suitable to all phrases, data sparseness also appears. Multi-agent strategy uses several model and sensitive features of each phrase to identify different phrases. This paper describes the multi-agent strategy applied in the identification of Chinese phrases whose main features are: 1) easy and quick communication between phrases; 2) avoidance of data sparseness. Through testing on Chinese Penn Treebank, F score of Chinese text chunking using multi-agent strategy achieves to 95.82%, which is higher than the best result that has been reported.
Chunk parsing is conceptually appealing but its performance has not been satisfactory for practical use. In this paper we show that chunk parsing can perform significantly better than previously reported by using a simple sliding-window method and maximum entropy classifiers for phrase recognition in each level of chunking. Experimental results with the Penn Treebank corpus show that our chunk parser can give high-precision parsing outputs with very high speed (14 msec/sentence). We also present a parsing method for searching the best parse by considering the probabilities output by the maximum entropy classifiers, and show that the search method can further improve the parsing accuracy.
We present a heuristic technique for converting a constituency treebank into a dependency treebank. In particular, we comment on our experience in converting the Spanish treebank Cast3LB. We extract a context-free grammar from the treebank, automatically identify the head in each rule, and use this information for constructing the dependency tree. Our heuristics have 99 % precision and 80 % recall in identifying the head in the rules, which gives 92% accuracy in identifying dependencies between words.