Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
18625 papers
Since 1995, a few statistical parsing algorithms have demonstrated a breakthrough in parsing accuracy, as measured against the UPenn TREEBANK as a gold standard. In this paper we report adapting a lexicalized, probabilistic context-free parser to information extraction and evaluate this new technique on MUC-7 template elements and template relations.
This volume contains the papers presented at the workshop on Recent Advances in Natural Language Processing and Information Retrieval, held on 8 October 2000 in conjunction with the 38 th Annual Meeting of the Association for Computational Linguistics (ACL).The aim of the workshop was to foster the interaction between researchers in the areas of Natural Language Processing (NLP) and Information Retrieval (IR), and furthermore, to promote discussion on the current and potential benefits of common approaches to related research challenges. In putting the workshop together, our goal was to bring these two communities together to establish opportunity for communication. We hope there will be similar workshops at IR related conferences so that a gradual closing of the existing gaps will occur. This workshop is not the first on the topic, but one which reflects what we believe are increasing trends as each field reaches its limits.The growing research and application possibilities provided by the increased amount of networked information have motivated new attempts to explore the relationship between NLP and IR. For researchers in IR, a compelling challenge is to move from (monolingual) document retrieval within controlled text collections, to actually retrieving information, rather than individual documents, from multilingual, heterogeneous and dynamic webs of interlinked documents and online services. The reciprocal challenge for NLP research is to scale up, adapt and possibly reshape techniques and resources to help bridge the gap between document and information retrieval in practical applications.The central topic of the workshop was the application of language technologies to information retrieval, including•the role of lexical-syntactic information in mono- and multilingual IR, including morphology, phrase detection and treatment, word sense disambiguation adapted to IR needs, acquisition and use of lexical resources, etc.•empirical evidence regarding the use of NL techniques in different retrieval scenarios, typification of such scenarios, and the discussion of evaluation measures beyond precision/recall variants.•interaction between NLP and IR techniques in topics related to both areas such as Cross-Language and Interactive Text Retrieval, Question Answering, Information Extraction, Text Summarization, Text Data Mining, etc.The original call for papers resulted in 25 submissions, from which 10 papers were selected on the basis of a thorough reviewing process. A majority of the papers contained in this volume study how to improve retrieval processes using syntactic and semantic information, including lexical expansions for web querying, semantic indexing, phrasal indexing in different languages, acquisition and use of lexical databases, etc. The remaining papers combine NL techniques from related areas - summarization, information extraction - to extend search capabilities and presentation of results, including summarization of search engine hit lists and summarization for text categorization, and a search interface that accepts template-like general constraints and is able to return specific information items such as locations, people or companies that satisfy user's constraints. Although none of these papers deal directly with cross-language issues (well covered in the Cross-Language Evaluation Forum held at Lisbon two weeks earlier), the monolingual systems presented here cover five different languages (English, Japanese, Korean, Italian and Czech).
1.1 Tagging criteria....................................... 4 1.2 POS tagset......................................... 5 1.3 Size of the POS tagset................................... 6
The accuracy of statistical parsing models can be improved with the use of lexical information. Statistical parsing using Lexicalized tree adjoining grammar (LTAG), a kind of lexicalized grammar, has remained relatively unexplored. We believe that is largely in part due to the absence of large corpora accurately bracketed in terms of a perspicuous yet broad coverage LTAG. Our work attempts to alleviate this difficulty. We extract different LTAGs from the Penn Treebank. We show that certain strategies yield an improved extracted LTAG in terms of compactness, broad coverage, and supertagging accuracy. Furthermore, we perform a preliminary investigation in smoothing these grammars by means of an external linguistic resource, namely, the tree families of an XTAG grammar, a hand built grammar of English.
We discuss the advantages of lexicalized tree-adjoining grammar as an alternative to lexicalized PCFG for statistical parsing, describing the induction of a probabilistic LTAG model from the Penn Treebank and evaluating its parsing performance. We find that this induction method is an improvement over the EM-based method of (Hwa, 1998), and that the induced model yields results comparable to lexicalized PCFG.
The popularity of applying machine learning methods to computational linguistics problems has produced a large supply of trainable natural language processing systems. Most problems of interest have an array of off-the-shelf products or downloadable code implementing solutions using various techniques. Where these solutions are developed independently, it is observed that their errors tend to be independently distributed. This thesis is concerned with approaches for capitalizing on this situation in a sample problem domain, Penn Treebank-style parsing. The machine learning community provides techniques for combining outputs of classifiers, but parser output is more structured and interdependent than classifications. To address this discrepancy, two novel strategies for combining parsers are used: learning to control a switch between parsers and constructing a hybrid parse from multiple parsers' outputs. Off-the-shelf parsers are not developed with an intention to perform well in a collaborative ensemble. Two techniques are presented for producing an ensemble of parsers that collaborate. All of the ensemble members are created using the same underlying parser induction algorithm, and the method for producing complementary parsers is only loosely constrained by that chosen algorithm.
In this paper, we propose a new ambiguity representation scheme; Structure Preference Relation (SPR), which consists of useful quantitative distribution information for ambiguous structures. Two automatic acquisition algorithms, the first acquired from a treebank, and the second acquired from raw texts, are introduced, and some experimental results which prove the availability of the algorithms are also given. Finally, we introduce some SPR applications in linguistics and natural language processing, such as preference-based parsing and the discovery of representative ambiguous structures, and propose some future research directions.
This paper describes a specific part of the Prague Dependency Treebank annotation, the step from the surface dependency structure towards the underlying representation of the sentence. The first section explains the theoretical basis of the project. In Section 2 all the procedure of conversion to the tectogrammatical structure is summarized and Section 3 presents in detail the present stage of the automated part of the conversion procedure.
Computers are now widely used in the preparation of dictionaries. There are many advantages in maintaining and updating a dictionary in electronic form, most obviously that printed versions can be typeset directly from the electronic copy. But more than that, electronic dictionaries are beginning to be used by computers in retrieval systems. This chapter looks at electronic dictionaries and examines how lexical databases can help to refine and improve retrieval and analysis programs. It also traces the development of the uses of computers and dictionaries, and assesses various types of resources. Much research still needs to be done on the structure and contents of lexical and linguistic databases, especially for the semantic component, but the examples discussed in this chapter give some idea of the potential.
This paper presents the first-ever results of applying statistical parsing models to the newly-available Chinese Treebank. We have employed two models, one extracted and adapted from BBN's SIFT System (Miller et al., 1998) and a TAG-based parsing model, adapted from (Chiang, 2000). On sentences with ≤40 words, the former model performs at 69% precision, 75% recall, and the latter at 77% precision and 78% recall.
The Verbmobil treebanks of spoken German, English, and Japanese are part of the Verbmobil project, which has the overriding goal to develop a speaker-independent system for the translation of spontaneous speech. In the framework of this language technology project, the treebanks provide training data for a variety of language technology modules. The treebanks consist of annotated syntactic tree structures based on transcribed dialogs in the scenarios of appointment negotiations, travel arrangements, and personal computer maintenance. The annotation schemes of the treebanks have been developed taking into account the specific characteristics of spoken language dialogs: repetitions, hesitations, false starts'', etc. * The work reported here was funded by the German Ministry of Education and Research (BMBF) in the framework of the Verbmobil project under grant FKZ:01 IV 701 M0.
The existence of a large body of literature in the Tyneside and Northumbrian dialects, dating from the late 18th century and continuing to the present day, testifies to a strong and enduring sense of regional identity closely associated with an acute sense of the differences between these dialects and Standard English/RP. Although much of this literature is conservative in nature and conservationist in intent, more recent examples in the local and popular press attempt to represent the salient features of the modern urban dialect (Geordie). This article examines extracts from a selection of texts, dating from George (Geordie) Ridley’s The Blaydon Races (1862) to cartoons in the Newcastle local newspaper, The Evening Chronicle(1996-7) and from Viz comic (1998). In the texts examined, semi-phonetic spelling is used to represent features of the Geordie accent. This article demonstrates that, whilst some features of the traditional dialect have been dropped by the more recent writers, others, such as the monophthongal/u:/in words such as ‘ town’, ‘brown’, spelt <toon, broon> are retained, notably in lexical items having referents which are closely bound up with local identity. Features found only in 20th-century texts often indicate very localized shibboleths, distinguishing Geordies from ‘Makkems’ (citizens of Sunderland, about 15 miles south-east of Newcastle). Recent sociolinguistic research points to a tendency for supra-local norms to replace the more traditional forms indicated by the spellings in dialect literature. This article argues that the prominence of local forms in dialect literature may represent an assertion of local identity in the face of the perceived threat of cultural and linguistic homogenization.
An architecture for federating heterogeneousdictionary databases is described. It proposes acommon description language and query language toprovide for the exchange of information betweendatabases with different organizations, on differentplatforms and in different DBMSs. The common querylanguage has an SQL like structure. The first versionof the description language follows the TEI standardtag definitions for dictionaries with the expectationthat the description language will be expanded in thefuture. A practical implementation of the proposalsusing WWW technology for two multi-lingualdictionaries is described.
This paper describes a supervised algorithm for word sensedisambiguation based on hierarchies of decision lists. This algorithmsupports a useful degree of conditional branching while minimizing thetraining data fragmentation typical of decision trees. Classificationsare based on a rich set of collocational, morphological and syntacticcontextual features, extracted automatically from training data andweighted sensitive to the nature of the feature and feature class. Thealgorithm is evaluated comprehensively in the SENSEVAL framework,achieving the top performance of all participating supervised systems onthe 36 test words where training data is available.
Two studies examined the relationship between self-monitoring and factors influencing romantic attraction to others. In Study 1, participants completed an Internet-mediated version of the Self-Monitoring Scale (Gangestad & Snyder, 1985) and indicated which of two people (one physically attractive, one with a more desirable personality) they found most attractive. Results matched previous findings (Snyder, Berscheid, & Glick, 1985), but the effect was smaller. Study 2, a paper-and-pencil replication of Study 1, examined whether the weaker effect was due to Internet mediation and found no differences in the choices made by high and low self-monitors. Results suggested that while determinants of attraction may vary for different populations, Internet research methods can tap the same phenomena as traditional laboratory studies.
The paper examines the task of Word Sense Disambiguation (WSD) criticallyand compares it with Part of Speech (POS) tagging, arguing that the abilityof a writer to create new senses distinguishes the tasks and makes it moreproblematic to test WSD by the mark-up-and-model paradigm, because newsenses cannot be marked up against dictionaries. This serves to set WSDapart and puts limits on its effectiveness as an independent NLP task.Moreover, it is argued that current WSD methods based on very small wordsamples are also potentially misleading because they may or may not scaleup. Since all-word WSD methods are now available and are producing figurescomparable to the smaller scale tasks, it is argued that we shouldconcentrate on the former and find ways of bootstrapping test materialsfor such tests in the future.
Senseval was the first open, community-based evaluation exercise for WordSense Disambiguation programs. It took place in the summer of 1998,with tasks for English, French and Italian. There were participating systems from 23 researchgroups. This special issueis an account of the exercise. In addition to describing the contentsof the volume, this introduction considers how the exercise has shedlight on some general questions about wordsenses and evaluation.
Web-accessible conferencing softwareand ``conversational ethics'' drawn from Habermas andRawls have successfully brought together on-lineparticipants separated by geography and viewpoint, andoccasionally resulted in consensus regarding otherwisedivisive issues such as abortion. The author describessuccesses, limitations, and costs of incorporatingthese technologies and discourse ethics in a religiousstudies class. Results are striking, but thepedagogical benefits involve technical risks and highlabor and time costs. This experience, coupled withrecent research, suggests that electronic pedagogies,like other teaching strategies, work for some, but notall students: this argues that we take up electronicteaching as one approach among many.
This paper specifically addresses the question of polysemy with respect toverbs, and whether or not the sense distinctions that are made in on-linelexical resources such as WordNet are appropriate for computational lexicons.The use of sets of related syntactic frames and verb classes are examined as ameans of simplifying the task of defining different senses, and the importanceof concrete criteria such as different predicate argument structures, semanticclass constraints and lexical co-occurrences is emphasized.
The paper describes SENSE, a word sense disambiguation system thatmakes use of different types of cues to infer the most likelysense of a word given its context. Architecture and functioning ofthe system are briefly illustrated. Results are given for theROMANSEVAL Italian test corpus of verbs.
TLC is a supervised training (S) system that uses a Bayesianstatistical model and features of a word's context to identifyword sense. We describe the classifier's operation and how itcan be configured to use only topical context cues, only localcues, or a combination of both. Our results on Senseval'sfinal run are presented along with a comparison to theperformance of the best S system and the average for S systems.We discuss ways to improve TLC by enriching its featureset and by substituting other decision procedures for the Bayesianmodel. Future development of supervised training classifiers willdepend on the availability of tagged training data. TLC canassist in the hand-tagging effort by helping human taggers locateinfrequent senses of polysemous words.
We present methods for evaluating human and automatictaggers that extend current practice in three ways. First, we show howto evaluate taggers that assign multiple tags to each test instance,even if they do not assign probabilities. Second, we show how toaccommodate a common property of manually constructed ``gold standards''that are typically used for objective evaluation, namely that there isoften more than one correct answer. Third, we show how to measureperformance when the set of possible tags is tree-structured in an IS-Ahierarchy. To illustrate how our methods can be used to measureinter-annotator agreement, we show how to compute the kappa coefficientover hierarchical tag sets.
The selectional preferences of verbal predicates are an importantcomponent of a computational lexicon. They have frequently been citedas being useful for WSD, alongside other sources ofknowledge. We evaluate automatically acquired selectional preferenceson the level playing field provided by SENSEVAL to examine towhat extent they help in WSD.
Senseval was the first open, community-based evaluation exercisefor Word Sense Disambiguation programs. It adopted the quantitativeapproach to evaluation developed in MUC and other ARPA evaluationexercises. It took place in 1998. In this paper we describe thestructure, organisation and results of the SENSEVAL exercise forEnglish. We present and defend various design choices for theexercise, describe the data and gold-standard preparation, considerissues of scoring strategies and baselines, and present the resultsfor the 18 participating systems. The exercise identifies thestate-of-the-art for fine-grained word sense disambiguation, wheretraining data is available, as 74–78% correct, with a number ofalgorithms approaching this level of performance. For systems thatdid not assume the availability of training data, performance wasmarkedly lower and also more variable. Human inter-tagger agreementwas high, with the gold standard taggings being around 95%replicable.
In recent years, researchers in computer science and human-computer interaction have become increasingly interested in characterizing perception of facial affect. Ironically, this applied interest comes at a time when the classic findings on perception of human facial affect are being challenged in the psychological research literature, largely on methodological grounds. This paper first describes two experiments that empirically address Russell’s methodological criticisms of the classic work on measuring “basic emotions,” as well as his alternative approach toward modeling “facial affect space.” Finally, a user study on affect in a prototype model of a robot face is reported; these results are compared with the human findings from Experiment 1. This work provides new data on measuring facial affect, while also demonstrating how basic and more applied research can mutually inform one another.
This paper reports the results of a vignette- and questionnaire-based research project over the World-Wide Web investigating the influence of moral intensity (MI) on decision making in a business context. A qualitative analysis of the feedback in terms of e-mail communications was used to provide insights into the reactions and responses of participants to both the research method and the topic of research. Implications are discussed, and some methodological recommendations are derived. Second, analysis of the quantitative results of the Web-based questionnaire administration indicated that three of the six MI components were particularly important determinants of several outcome variables. This pattern of results essentially replicated findings yielded by a previous mail administration of the survey, even though a smaller amount of variation in the outcome variables was accounted for. Neither occupational background nor the region of origin of participants measurably influenced the results.
Structural ambiguity, particularly attachment of prepositional phrases, is a serious type of global ambiguity in Natural Language. The disambiguation becomes crucial when a syntactic analyzer must make the correct decision among at least two equally grammatical parse-trees for the same sentence. This paper attempts to find answers to the problem of how attachment ambiguity can be resolved by utilizing Machine Learning (ML) techniques. ML is founded on the assumption that the performance in cognitive tasks is based on the similarity of new situations (testing) to stored representations of earlier experiences (training). Therefore, a large amount of training data is an important prerequisite for providing a solution to the problem. A combination of unsupervised and restricted supervised acquisition of such data will be reported. Training is performed both on a subset of the content of the Gothenburg Lexical Database (GLDB), and on instances of large corpora annotated with coarse-grained semantic information. Testing is performed on corpora instances using a range of different algorithms and metrics. The application language is written Swedish.
This paper presents a novel methodology of disambiguating prepositional phrase attachments. We create patterns of attachments by classifying a collection of prepositional relations derived from Treebank parses. As a by-product, the arguments of every prepositional relation are semantically disambiguated. Attachment decisions are generated as the result of a learning process, that builds upon some of the most popular current statistical and machine learning techniques. We have tested this methodology on (1) Wall Street Journal articles, (2) textual definitions of concepts from a dictionary and (3) an ad hoc corpus of Web documents, used for conceptual indexing and information extraction.
Lexical functions (LFs), as developed by I. Mel'icuk in the Meaning-Text Theory are a formal means for the representation of collocations. LFs allow for a fine-grained description of collocations with respect to their syntactic and semantic characteristics. However, it has repeatedly been pointed out that the definition of LFs is far from being transparent for linguists and lexicographers not trained in this theoretical framework. Especially problematic from this perspective is the combinatorial capacity of LFs. In this paper, we suggest some criteria for the encoding of collocations in terms of LFs. These criteria draw on LF definitions, i.e., both the syntactic and semantic properties of LFs. The research reported on in the paper is part of an ongoing project within which an on-line collocational dictionary of Spanish is compiled. Our objective is to incorporate a heuristic model the backbone of which are the criteria for the encoding of LFs into an interface of the lexical database. The interface will support the identification of (combinations of) LFs and permit the verification of proposed formulations.
This research was designed to contribute to the development of new training systems to convey shape to the visually impaired. This dissertation consisted of two experiments which addressed the similarities and differences of visually impaired persons' and sighted persons' impressions of outlines of real objects perceived under auditory and touch display conditions, as well as tactile impressions of actual real objects, wood cutouts of those objects, tactor-pin diagrams of those objects, and raised-line drawings of those objects. Experiment 1 examined auditory and tactile perceptual equivalence, as well as sighted and visually impaired perceptual equivalence. Within each sight level group, Experiment 1 demonstrated a lack of equivalence for auditory and tactile perceptual structures. Experiment 1 demonstrated both similarities and differences in the perceptual structure comparisons between the sighted and the visually impaired. Experiment 2 examined the impact of sight level and four stimulus types on tactile percent correct identifications, response latencies, and familiarity ratings. Experiment 2 demonstrated sighted and visually impaired participants performed equally on a percent correct identification task. This Experiment also revealed the best performances were exhibited when real objects were presented, followed by wood cutouts, followed by tactor-pins, and performance with raised-line drawing (RLD) presentation was poorest. Experiment 2 also examined the exploratory procedures utilized during tactile identification of the four stimulus types. Experiment 2 revealed wood cutout presentation was associated with the largest percentage of different exploratory procedures being utilized, followed by real objects and tactor-pins which were equivalent, but utilized a larger percentage than the RLDs. Wood cutouts were the only other objects beside the real objects to use all exploratory procedures. The results of Experiment 1 and Experiment 2 indicate the utility of changing current industry standards for displaying shape information.
This paper demonstrates that machine learning is a suitable approach for rapid parser development. From 1000 newly treebanked Korean sentences we generate a deterministic shift-reduce parser. The quality of the treebank, particularly crucial given its small size, is supported by a consistency checker. 1 Introduction Given the enormous complexity of natural language, parsing is hard enough as it is, but often unforeseen events like the crises in Bosnia or East-Timor create a sudden demand for parsers and machine translation systems for languages that have not benefited from major attention of the computational linguistics community up to that point. Good machine translation relies strongly on the context of the words to be translated, a context that often goes well beyond neighboring surface words. Often basic relationships, like that between a verb and its direct object, provide crucial support for translation. Such relationships are usually provided by parsers. The NLP resources f...
International audience
No language in the world is homogeneous, or ever will be. Whereas earlier forms of English were characterised by extreme variation on all levels and Middle English is in fact best described as a loose conglomerate of unstable varieties, we usually lack any more detailed insight into what functions this variation had for the individual speaker. The social correlates so well known from modern sociolinguistics, such as age, sex, education, religion, can normally not be applied to the existing texts, nor can even the geographical range of recorded forms be determined with any degree of certainty. Finally, if modern dialect or other non-standard features are contrasted with (as the term non-standard implies) an accepted standard form of a language, this method would necessarily fail with Middle English even if we knew more about it than we do and, in view of the state of surviving documents, ever will. It is safe to assume that for its speakers the linguistic heterogeneity of Middle English was ordered in some way, but it was so only for continually shifting speech communities, whose number and individual geographical spread we know very little about. The scene changed dramatically in the fifteenth century: the emergence of a new standard language began to re-institute a linguistic norm for written supraregional English. This development was a natural consequence of the acceptance of English in public domains, and was speeded up by the change-over to English as the Chancery language in 1430.
The characterization of the Aragonese used in the Heredia's works has met with surprise almost always on account of its heterogeneity, accountable by the different models used and the diverse people that have played a role in his scriptorium. To this should be added the different peculiarities of the language itself used by his patron, a language that has never been taken into account up to now. In order to fill this gap this paper presents an edition and a study of a letter from Castellan de Amposta, kept in the Archivo de la Corona de Aragon. This analysis reveals the use of a variety of linguistic norms: forms habitually found in Aragonese are to be found side by side in the letter with forms usual in Catalan. There are also forms that coincide with Castilian usage.
The purpose of this article is to analyze the presence of traces of what will call a sacerdotal dimension, which is related to the theme of hermaphroditism, in Savinio's novel, as well as to verify what cultural implications are suggested by this sacerdotal dimension. Its traces will be found in the development of the young protagonist's (Nivasio's) thoughts and discoveries, which make up the book's plot, and which are surrounded by a mythic halo. Infanzia di Nivasio Dolcemare (1941) (2) should not be considered as merely an autobiographical work, but as an autobiography made dreamlike and strange, exclusively dedicated to a lost age, that of and puberty, up to the moment of the discovery of sex, after which childhood is over, in fact, and the narrative closes. (3) would like to propose a preliminary reflection: although much has been said of the linguistic techniques employed by Savinio, such as pastiche, plurilinguism, and others, one must always keep in mind that the author's linguistic stratagems were all used to promote a peculiar autobiographical dimension. (4) Throughout his literary career, which cannot be analyzed here in its entirety, Savinio often seems to have been concerned with representing the formation and the expression of subjectivity in relation with the world. The textual I of this subjectivity never assumes traditional forms, however, but constantly seeks to deviate from linguistic norms, to transgress in its formation of images and characters. Yet its goal is always also to reconstruct the sense of a subjective progression, of the journey of an individual ego through the things of the world. The story of Infanzia di Nivasio Dolcemare is set in Greece, as is frequent in Savinio, but it is a Greece relived through the memory of the domestic situations of childhood. This re-evocation is founded on deformed obsessions and presences. The deformation already begins in the very names of the protagonists, which were created according to an anagrammatic logic. Nivasio's father's name is Visanio, for instance, but even the name Nivasio itself is an anagram of Savinio. The complexity of this is amplified even more if one considers that the name Savinio is, in its turn, not the anagram, but the pseudonym of Andrea De Chirico. This mechanism of transformation and concealment constantly reopens the problem oft he writer's autobiographical intentions. In the anagram, as in the pseudonym. Savinio tries to evade what we might call linear biography, so as to complicate or to metamorphose it by the use of linguistic means, or by the evocation of mythic figures such as the Hermaphrodite and the Argonaut. Yet one also constantly has the impression that all of Savinio's experiments are intended to communicate something other than mere deformation or surrealism; to communicate, rather, the peculiar progression of a subject that elaborates various self-representations on a number of different levels and according to diverse strategies. At the beginning of the novel. Nivasio conjures up the initial moment of every autobiography: that of his own birth. The complexity of the situation consists in the fact that Savinio immediately projects this event into a descriptive sphere in which all the external objects and circumstances surrounding the birth scene appear. The effect is that of estrangement: Il giorno in cui Nivasio usci dal grembo materno, ii sole picchiava a martello sulla citta della civetta. Cinque da una parte e cinque dall'altra, le lunghe steariche colorate sorgevano agli angoli del caminetto, si piegavano sui candelabri di bronzo, piangevano lunghi lacrimoni. La culla spumeggiava. in un angolo. Di minuto in minuto un rapido fruscio d'acqua rameggiava nei muri passava sulle finestre che opponevano le loro persiane chiuse all'assalto del caldo portentoso. (19) The very tears, rather than being attributed to the newborn baby, are produced by the steariche, or tallow candles. …
In this paper we present the results of a quantitative evaluation of the discrepancies between the Italian and English lexica in terms of lexical gaps. This evaluation has been carried out in the context of MultiWordNet, an ongoing project that aims at building a multilingual lexical database. The quantitative evaluation of the English-to-Italian lexical gaps shows that the English and Italian lexica are highly comparable and gives empirical support to the MultiWordNet model. 1.
The question of whether to adapt the language and style of opera librettos to current linguistic norms is proposed to be similar to the problem of whether to perform an opera in the original language or in translation. It is argued that any adjustment or modernization is inappropriate, and that original language and diction should be preserved. DvoÅák's tragic opera Vanda to a libretto by Václav BeneÅ¡-Å umavský and FrantiÅ¡ek Zákrejs is considered as an example.
We present a treebank project for French. We have annotated a newspaper corpus of 1 Million words with part of speech, inflection, compounds, lemmas and constituency. We describe the tagging and parsing phases of the project, and for each, the automatic tools, the guidelines and the validation process. We then present some uses of the corpus as well as some directions for future work.
The purpose of this article is to briefly introduce an interactive POS tagging system developed as a project at the Institute for Humanities and Cultural Studies in Tehran, Iran. The system is designed as part of the annotation procedure for a Persian corpus called The Farsi Linguistic Database (FLDB) (a project at the Institute for Humanities and Cultural Studies in Tehran which comprises a selection of contemporary Modern Persian literature, formal and informal spoken varieties of the language, and a series of dictionary entries and word lists [Assi 1997: 5]) and is the first attempt ever to tag a Persian corpus. In Section 1, the project itself will be introduced; Section 2 presents an evaluation of the project, and Section 3 is allocated to some suggestions for future work.
The paper asks how much structural detail it is reasonable to include in a detailed general-purpose grammar annotation scheme. I argue that there is no principled answer to that question; even grammatical distinctions which in general are clear and linguistically central will often be “distinctions without a difference ” in particular examples. The discipline which offers the closest intellectual precedent for linguistic treebank-compilation activity, biological systematics, is disanalogous from our work in that respect. * Detailed v. skeleton analytic schemes Any scheme for structural annotation of corpora must embody decisions about how much detail to include. Some groups explicitly aim at “skeleton parsing”, marking much less grammatical detail than linguists recognize a language as containing. In many circumstances, this will be a sensible