Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
18625 papers
A small subset of PDT 2.0 made available under a permissive license. Prague Dependency Treebank 2.0 (PDT 2.0) contains a large amount of Czech texts with complex and interlinked morphological (2 million words), syntactic (1.5 MW) and complex semantic annotation (0.8 MW); in addition, certain properties of sentence information structure and coreference relations are annotated at the semantic level. PDT 2.0 is based on the long-standing Praguian linguistic tradition, adapted for the current Computational Linguistics research needs. The corpus itself uses the latest annotation technology. Software tools for corpus search, annotation and language analysis are included. Extensive documentation (in English) is provided as well.
The last decade has seen a large increase in the number of available corpus query systems. Some of these are optimized for a particular kind of linguistic annotation (e.g., time-aligned, treebank, word-oriented, etc.). In this paper, we report on our own corpus query system, called Emdros. Emdros is very generic, and can be applied to almost any kind of linguistic annotation using almost any linguistic theory. We describe Emdros and its query language, showing some of the benefits that linguists can derive from using Emdros for their corpora. We then describe the underlying database model of Emdros, and show how two corpora can be imported into the system. One of the two is a parallel corpus of Hungarian and English (the Hunglish corpus), while the other is a treebank of German (the TIGER Corpus). In order to evaluate the performance of Emdros, we then run some performance tests. It is shown that Emdros has extremely good performance on “small ” corpora (less than 1 million words), and that it scales well to corpora of many millions of words. 1.
The Prague Dependency Treebank 2.0 (PDT 2.0) contains a large amount of Czech texts with complex and interlinked morphological (two million words), syntactic (1.5 MW) and complex semantic annotation (0.8 MW); in addition, certain properties of sentence information structure and coreference relations are annotated at the semantic level. PDT 2.0 is based on the long-standing Praguian linguistic tradition, adapted for the current Computational Linguistics research needs. The corpus itself uses the latest annotation technology. Software tools for corpus search, annotation and language analysis are included. Extensive documentation (in English) is provided as well.
Summary form only given. We present first some general remarks on challenges faced by modern information technology, notably when a human being is a relevant factor. These challenges are mainly related to inherent difficulties in solving some "meta-problems", in particular broadly perceived decision making. We assume, on the one hand, business intelligence related perspective, augmented with elements of Web intelligence, to fully use all available tools and resources. On the other hand, we assume a human centric computing perspective in the spirit of, for instance, Dertouzos's ideas. First, we present a brief account of modem approaches to real world decision making, emphasize the concept of a decision making process that involves more factors and aspects like: the use of own and external knowledge, involvement of various,actors, aspects, etc., individual habitual domains, non-trivial rationality, different paradigms. As an example we mention Checkland's deliberative decision making (which is an important elements of his soft approach to systems analysis). After an analysis of specifics and difficulties encountered in many real world decision-making situations, we strongly advocate the use of computer based decision support systems. First, we briefly review the history of decision support systems, and then present a popular classification, starting from data driven to Web based and inter-organizational. We indicate that decision support systems should incorporate some sort of "intelligence", and we first briefly mention some views of what intelligence may mean in this concept, and then assume some more pragmatic, though limited, view of intelligent decision support systems. We indicate possible advantages of using elements of fuzzy logic and soft computing, notably, Zadeh's computing with words to be able to somehow merge the ideas presented like: human centric computing, decision making processes, intelligent decision support, etc. Finally, we present an example of implementation in which the above-mentioned ideas have been to some extent implemented. This concern a data and document driven decision support system for a small to medium company in which, first, Zadeh's computing with words and perceptions paradigm is employed via linguistic database summaries, elements of Web intelligence are used to derive additional information, and the ideas of an intelligent decision support and human centric computing are shown to be synergistically combined. We finish with some general remarks emphasizing that fuzzy logic and soft computing, notably as exemplified by Zadeh's computing with words and perceptions may be viewed as providing just the right tools to solve the problems considered
Approximately 60 kinds of lexical relations have been recognized in languages of the world (Grimes & Grimes, 1993). In this paper, I present evidence for a wide range of lexical relations in the Ilokano language. Grimes explains the meaning of lexical relations in terms of the way two words are related but differ in meaning, giving examples such as write and writer, row and rower. I will exemplify some of the types of lexical relations attested in Ilokano: 1) Verbs with an incorporated nominal, e.g. ag-diram'os 'to wash one's face' where the implied noun is 'face'; aginnaw 'wash dishes', implied noun, 'dishes'. There is no word for 'face' in agdiram'os, nor word for 'dishes' in aginnaw. 2) Derived nouns expressing an agentive relation, e.g. from the verb agsugal 'to gamble' the derived noun is mannugal 'gambler', agsurat 'to write', mannurat 'writer'. 3) Reduplication of a noun describing a condition of that noun, e.g. saka 'foot', saka-saka 'barefoot'; ima 'hand', ima-ima 'emptyhanded'. 4) Derived verbs denoting animal vocalization, e.g. aso 'dog', agtaol (phonation) 'to bark', ul'ul'ol (onomatopoeia); 5) Derived verbs denoting a quantum, e.g. sangalilig a sua 'one section of a pomelo'; 6) Complements, e.g. biag ken patay 'life and death'; 7) Derived verbs denoting function, e.g. karayan 'river', agayos 'to flow', sabong flower', agukrad 'to bloom'. I will then show how these derivations are handled in the Ilokano Lexical Database where they are listed making use of the band format.
Abstract Understanding and modeling human experience and emotional response when listening to music are important for better understanding of the stylistic choices in musical composition. In this work, we explore the relation of audio signal structure to human perceptual and emotional reactions. Memory, repetition, and anticipatory structure have been suggested as some of the major factors in music that might influence and possibly shape these responses. The audio analysis was conducted on two recordings of an extended contemporary musical composition by one of the authors. Signal properties were analyzed using statistical analyses of signal similarities over time and information theoretic measures of signal redundancy. They were then compared to Familiarity Rating and Emotional Force profiles, as recorded continually by listeners hearing the two versions of the piece in a live‐concert setting. The analysis shows strong evidence that signal properties and human reactions are related, suggesting applications of these techniques to music understanding and music information‐retrieval systems.
WordNet, a lexical database for English that is extensively used by computational linguists, has not previously distinguished hyponyms that are classes from hyponyms that are instances. This work describes an attempt to draw this distinction and reports the way in which the results were incorporated in the last version (2.1) of WordNet.
Since the beginning of psychology as a scientific endeavour, the question of whether the body plays a role in how a person experiences emotion has been the centre of emotion research. Patients with structural gastrointestinal disorders, such as Crohn's disease, provide an intriguing opportunity to study the influence of body signals on emotions and feelings. In the present study, emotionally salient films were presented to participants with Crohn's disease in either the active state (Crohn's-active, CA) or silent state (Crohn's-silent, CS), and to normal comparison (NC) participants. We hypothesized that CA participants would have increased feelings, compared with CS and NC participants, when viewing emotional films designed to elicit happiness, disgust, sadness and fear. Gastric myoelectrical activity (electrogastrogram, or EGG) was measured during the films, and after each film was presented, participants rated emotion intensity (arousal) and pleasantness (valence). All groups labelled the emotions similarly. In support of the hypothesis, CA participants showed an increase in subjective arousal for negative emotions compared with CS and NC participants. The CA participants also showed increased EGG during emotional film viewing, as well as a strong positive correlation of EGG with arousal ratings. Together, these findings can be taken as evidence that aberrant feedback from the gastrointestinal system up-regulates the intensity of feelings of negative emotions.
We present the Heart of Gold middleware by demonstrating three XML-based integration scenarios where multi-dimensional markup produced online by multilingual natural language processing (NLP) components is combined to deliver rich, robust linguistic markup for use in NLP-based applications like information extraction, question answering and semantic web. The scenarios include (1) robust deep-shallow integration, (2) shallow processing cascades, and (3) treebank storage of multi-dimensionally annotated texts.
Internet has opened the access to an overwhelming amount of data, requiring the development of new applications to automatically recognize, process and manage informationavailable in web sites or web-based applications. The standardSemantic Web architecture exploits ontologies to give a shared(and known) meaning to each web source elements.In this context, we developed MELIS (Meaning Elicitation and Lexical Integration System). MELIS couples the lexical annotation module of the MOMIS system with some components from CTXMATCH2.0, a tool for eliciting meaning from severaltypes of schemas and match them. MELIS uses the MOMIS WNEditor and CTXMATCH2.0 to support two main tasks in theMOMIS ontology generation methodology: the source annotationprocess, i.e. the operation of associating an element of a lexicaldatabase to each source element, and the extraction of lexicalrelationships among elements of different data sources.
Based on the analysis of the usage and the syntactic function of Chinese punctuations,this paper proposes a new hierarchical approach to parse the long Chinese sentences.In traditional parsing approaches,the parsing procedure is performed in an one-level way and the punctuation marks are not specially treated.Correspondingly,in our approach,the complex long Chinese sentences are broken into sub-sentences or units(say 'units' hereafter) by using punctuation marks with special functions,so that the original whole sentence is parsed unit by unit.This idea of 'divide-and-conquer' greatly reduces the difficulty in the traditional parsing approaches to recognize the syntactic relationship between the sub-sentences and phrases or inside the sub-sentences or phrases.And also,in our approach,the grammatical rules with punctuation marks and their probabilities are extracted from the large scale treebank,which are very beneficial to the syntactic disambiguation.Our experimental results have shown that comparing with the traditional Chart parsing algorithm,our approach can significantly reduce the time consumption and the numbers of ambiguous edges,and get about 7% of the correct rate and the recall rate increasing while parsing long Chinese sentences.
With the advancement of natural language understanding (NLU), coreference resolution, as a main part of information extraction (IE), has received much more attention. For this task, either rule-based or statistics-based methods cannot meet the needs of large-scale text processing. An integrated method based on decision tree for Chinese pronominal coreference is proposed. The basic idea is filter rules could, to some degree compensate the drawback of decision tree that ignoring the relationship between attributes. The performance of the proposed method is evaluated on Chinese Treebank. In our experiments, the attributes and coreferences are manually labeled, and then the filter rules are utilized to feature vectors following the decision tree of C4.5 algorithm. The success rate is 82.59%, in which the rate of personal pronouns and demonstrative pronouns are 87.60% and 75.21% respectively.
While syntactically annotated corpora known as treebanks have been available for many years, along with a variety of customized tools for querying these annota-
We describe experiments in parsing the German TIGER Treebank. In parsing the complete treebank, 86.44 % of the sentences receive full parses; 13.56 % receive fragment parses. We discuss the methods used to enhance coverage and parsing quality and we present an evaluation on a gold standard, to our knowledge the first one for a deep grammar of German. Considering the selection performed by our current version of a stochastic disambiguation component, we achieve an f-score of 84.2%, the upper and lower bounds being 87.4% and 82.3 % respectively. 1.
The paper presents new lexicon of verb valencies for the Czech language named VerbaLex. VerbaLex is based on three valuable language resources for Czech, three independent electronic dictionaries of verb valency frames. The first resource, Czech WordNet valency frames dictionary, was created during the Balkanet project and contains semantic roles and links to the Czech WordNet semantic network. The other resource, VALLEX 1.0, is a lexicon based on the formalism of the Functional Generative Description (FGD) and was developed during the Prague Dependency Treebank (PDT) project. The third source of information for VerbaLex is the syntactic lexicon of verb valencies denoted as BRIEF, which originated at FI MU Brno in 1996. The resulting lexicon, VerbaLex, comprehends all the information found in these resources plus additional relevant information such as verb aspect, verb synonymity, types of use and semantic verb classes based on the VerbNet project.
In this paper, we construct a biomedical semantic role labeling (SRL) system that can be used to facilitate relation extraction. First, we construct a proposition bank on top of the popular biomedical GENIA treebank following the PropBank annotation scheme. We only annotate the predicate-argument structures (PAS's) of thirty frequently used biomedical predicates and their corresponding arguments. Second, we use our proposition bank to train a biomedical SRL system, which uses a maximum entropy (ME) model. Thirdly, we automatically generate argument-type templates which can be used to improve classification of biomedical argument types. Our experimental results show that a newswire SRL system that achieves an F-score of 86.29% in the newswire domain can maintain an F-score of 64.64% when ported to the biomedical domain. By using our annotated biomedical corpus, we can increase that F-score by 22.9%. Adding automatically generated template features further increases overall F-score by 0.47% and adjunct arguments (AM) F-score by 1.57%, respectively.
The Russian language of the end of the twentieth century and the beginning of the twenty-first century attracts the attention of scholars due to its changes, which are determined by the overall economic and social changes in the country. The most significant and characteristic transformations in the language are the following: the increase of the volume and the rate of words borrowed from other languages, the loss of certain words denoting Soviet realia and the loss of ideological flavor of certain words, innovations and massive deviations from the linguistic norms, and the "criminalization" of the lexicon. This article focuses on one of the above-mentioned phenomena of the contemporary Russian, that is, borrowings as a reflection of the influence of other cultures and languages on Russian. New words that enter Russian from other languages signify changes in the way of life, thinking and behaving. The most revealing in this sense are emotion and value terms because their meanings are reflective of cultural beliefs, assumptions and understandings. Therefore, the approach implemented in this article is that language, and its lexicon in particular, can be considered a gateway into a people's culture. Moreover, changes in a language are indicative of cultural changes.
The trees in the Penn Treebank have a standard representation that involves complete balanced bracketing. In this article, an alternative for this standard representation of the tree bank is proposed. The proposed representation for the trees is loss-less, but it reduces the total number of brackets by 28%. This is possible by omitting the redundant pairs of special brackets that encode initial and final embedding, using a technique proposed by Krauwer and des Tombe (1981). In terms of the paired brackets, the maximum nesting depth in sentences decreases by 78%. The 99.9% coverage is achieved with only five non-top levels of paired brackets. The observed shallowness of the reduced bracketing suggests that finite-state based methods for parsing and searching could be a feasible option for tree bank processing.
This paper presents a comparative study of probabilistic treebank parsing of German, using the Negra and TüBa-D/Z tree-banks. Experiments with the Stanford parser, which uses a factored PCFG and dependency model, show that, contrary to previous claims for other parsers, lexicalization of PCFG models boosts parsing performance for both treebanks. The experiments also show that there is a big difference in parsing performance, when trained on the Negra and on the TüBa-D/Z treebanks. Parser performance for the models trained on TüBa-D/Z are comparable to parsing results for English with the Stanford parser, when trained on the Penn treebank. This comparison at least suggests that German is not harder to parse than its West-Germanic neighbor language English.
The Leximancer system is a relatively new method for transforming lexical co-occurrence information from natural language into semantic patterns in an unsupervised manner. It employs two stages of co-occurrence information extraction—semantic andrelational—using a different algorithm for each stage. The algorithms used are statistical, but they employ nonlinear dynamics and machine learning. This article is an attempt to validate the output of Leximancer, using a set of evaluation criteria taken from content analysis that are appropriate for knowledge discovery tasks.
Quantitative modeling of psychological data is both technically and mathematically challenging. The present article introduces a user friendly and flexible program package that enables quantitative fits of Bundesen’s (1990) theory of visual attention to behavioral data from whole and partial report experiments. The program package is based on new computational formulas that are more general than previous ones and has already been used successfully in a number of neuropsychological investigations of attentional disorders, such as visual neglect and simultanagnosia. A clinical version of the program package is currently under development.
The paper focuses on the description of the process of “mining” lexical semantic information from published dictionaries of Brazilian Portuguese language. Specifically, it is described the manual approach of compiling and filtering hyperonymy/hyponymy and holonymy/meronym logic-conceptual relations of concrete nouns. These relations, filtering from the dictionaries, will be use to organize part of the nouns of Wordnet.Br lexical database.
Ambulatory accelerometry is a technique that allows objective measurement of aspects of everyday human behavior. The aim of our research has been to develop, validate, and apply this technique, which recently resulted in an upper limb activity monitor (ULAM). The ULAM consists of body-mounted acceleration sensors connected to a waist-worn data recorder and allows valid and objective assessment of activity of both upper limbsduring performance of also automatically detected mobility-related activities: lying, sitting, standing, walking, cycling, and general movement. The ULAM can be used to determine (limitations of) upper limb activity and mobility in freely moving subjects with upper limb disorders. This article provides a detailed description of its characteristics, summarizes the results of a feasibility study and four application studies in subjects having upper limb complex regional pain syndrome, discusses the most important practical, technical, and methodological issues that were encountered, and describes current and future research projects related to measuring (limitations of) upper limb activity.
Abstract We present a new method for learning to parse a bilingual sentence using Inversion Transduction Grammar trained on a parallel corpus and a monolingual treebank. The method produces a parse tree for a bilingual sentence, showing the shared syntactic structures of individual sentence and the differences of word order within a syntactic structure. The method involves estimating lexical translation probability based on a word-aligning strategy and inferring probabilities for CFG rules. At runtime, a bottom-up CYK-styled parser is employed to construct the most probable bilingual parse tree for any given sentence pair. We also describe an implementation of the proposed method. The experimental results indicate the proposed model produces word alignments better than those produced by Giza++, a state-of-the-art word alignment system, in terms of alignment error rate and F-measure. The bilingual parse trees produced for the parallel corpus can be exploited to extract bilingual phrases and train a decoder for statistical machine translation.
In this paper, we present an alternative approach to the problem of contextual relevance feedback in web-based information retrieval. Our approach utilises a rich contextual model that exploits a user's implicit and explicit data. Each user's implicit data are gathered from their Internet search histories on their local machine. The user's explicit data are captured from a lexical database, a shared contextual knowledge base and domain-specific concepts using data mining techniques and a relevance feedback approach. This data is later used by our approach to modify queries to more accurately reflect the user's interests as well as to continually build the user's contextual profile and a shared contextual knowledge base. Finally, the approach retrieves personalised or contextual search results from the search engine using the modified/expanded query. Preliminary experiments indicate that our approach has the potential to not only aid in the contextual relevance feedback but also contribute towards the long term goal of intelligent relevance feedback in web-based information retrieval.
Existing mechanisms for concept discovery tend to pick up all possible relationships between terms in a document based on roles of terms identified. The proposed work aims to enhance this discovery process by employing machine learning and semantic modelling. We explore a framework for automatically discovering labeled clusters from a large collection of documents. The aim of this framework is to enable the extraction of concepts and to structure these into labeled concepts for use by text processing applications such as text summarization and text categorization. We have developed a mechanism for automatically inducing a set of words that captures the meaning of a collection of documents. The WordNet lexical database is used to extract root meanings and to determine relationships amongst these terms
Recently the rational principle and the customary principle have been regarded as the main judging basis for linguistic norm.But the practice proves that the rational principle is hard to conduct and the customary principle less popularized.The establishment of the judging basis for linguistic norm should take the consideration of those target's characteristics.Langue and parole must be divided and ruled by their dissimilarity.Stability,sociality and pragmatic function should be the basis for langue,while effect principle and ethic principle should be the basis for parole.When dealing with the transitional area between langue and parole,the normal and the abnormal,we should not go to extremes.
This study investigates customers’ responses to the phrase, How do you like your cereal?, a question posed by servers at a cereal cafe. This phrase, along with several variants, abrogates linguistic service encounter norms, and customer response type is heavily influenced by the type and content of the servers’ questions. The data indicate that certain types of questions encourage direct orders from customers, whereas other questions, namely How do you like your cereal?, provoke disfluencies and confusion among customers. An analysis of how the questions violate linguistic norms is given, along with why customers interpret some questions as requests for information and others as ordering prompts.
In this paper, we present a system which can extract syntactic feature structures from a Korean Treebank (Sejong Treebank) to develop a Feature-based Lexicalized
Recent work in the social cognitive aging literature, encounters a domain of functioning that might reveal a positive trajectory into old age, namely emotional memory. Some authors argue that older adults prioritize positive over negative information in memory and more so than young adults do. In order to investigate age-related differences in an emotion-based processing prioritization (i.e. preference for positive information), I used the heterogeneity-homogeneity list paradigm. If processing prioritization contributes to the proposed positivity effect in older adults memory, a positivity effect is expected in an emotion-heterogeneous but not in an emotion-homogeneous list context. Based on a preparatory word rating study, in which 24 young and 24 older adults were asked to rate 200 adjectives on six dimensions (valence, arousal, control, imagery, self-relevance, age- relevance), 30 negative, 30 positive, and 30 neutral words were selected. Words were combined to form three emotion-homogeneous (lists of 30 negative, 30 positive, and 30 neutral words) and three emotion-heterogeneous lists (three mixed lists of 10 positive, 10 negative, and 10 neutral words). In a between-subjects design, 72 young (aged 18 to 31 years) and 72 older adults (aged 64 to 75 years) were presented emotion-heterogeneous or emotion- homogeneous word lists and were asked to do a free recall across five learning trials and two long-term retention intervals (1-hour, 1-week). Regarding the effects of valence, both age groups recalled more negative than positive and neutral words in an emotion-heterogeneous list condition. In an emotion- homogeneous list condition, however, both age groups showed no recall differences between positive and negative words. In both list conditions, there was no evidence for the proposed positivity effect in older adults memory (i.e., no Age x Valence interaction). Follow-up analyses showed that the obtained findings were robust. The effects of valence were not moderated by (a) interindividual differences in person characteristics, (b) differences in word characteristics, or (c) the subjective evaluation of the to-be- remembered words by the participants. The findings in the two long-term retention intervals supported the pattern of findings in the learning phase. Contrary to recent proposals in the lifespan literature, the present dissertation did not support the idea that age differently modulates memory for positive and negative material. However, across the two contexts, a differential pattern of recalling positive and negative words was found. This finding is consistent with the idea that negative information receives processing priority in some contexts.
This paper aims at developing methods of extracting figurative expressions from a domain-specific corpus and extending the multi-lingual lexical database entries for those expressions to be included. The nominal entries which can be used figuratively are selected from the annotated corpus, using the hierarchical semantic class of Sejong Electronic Dictionary. And from the raw corpus, the partially-parsed corpus are constructed automatically. To extract candidates for figurative expression, we fixed some syntactic patterns in advance, for example [NP+sbj-marker NP+obj-marker V], and extract those patterns from partially-parsed corpus. After investigating the extracted expressions and classifying them whether figurative or literal, we concluded that some nominal entries are used more figuratively in specific syntactic patterns.
DEB II platform is a new language independent development platform for lexicographic tools based on the client/server architecture. It uses web Mozilla Development Platform for building special interface modules allowing to build the resulting lexicographic application such as a dictionary writing system from several components. The DEB II consists of a dictionary browser and editor for more XML dictionaries, an integrated Czech morphological analyzer and can cooperate with other applications such as corpus manager Manatee/Bonito and Word Sketch Engine or a geographical information system GRASS (used for building a Czech onomastic dictionary). The properties and assets of the DEB II platform will be presented as one of its current applications, the tool named PRALED, which is designed for preparation of the new Czech Lexical Database in the Institute of Czech Language in Prague.
The Czech Academic Corpus version 1.01 is a corpus with a manual annotation of morphology of the Czech language consisting of approximately 600,000 words in continuous texts. The process and the size of the Czech Academic Corpus (CAC) project differs from every traditional project. The primary goal of this project was to create a computerized corpus that would contain manual annotation of morphology and syntax of Czech. This manual annotation of morphology and syntax was initially developed more than twenty years ago (1971-1985) at the Institute of the Czech Language of the Czech Academy of Science as a basis for constructing a frequency dictionary of Czech at that time. Having mentioned the years when the history of CAC has started we cannot miss the fact that there were available two computerized annotated corpora in the 1960s Brown Corpus of American English and LOB Corpus of British English. Both corpora became well known to the corpus linguists whereas CAC (although containing richer annotation schemes) has remained hidden mainly because of the political regime of the 1980s in the Czech Republic. Fortunately for Czech computational linguistics, CAC was (and still is, obviously) of significant importance because the very first experiments on the corpus-based processing of Czech could be performed thanks to CAC. Independent from CAC, the project of the Prague Dependency Treebank (PDT) was launched in 1996. The complexity of the PDT three-layer annotations (morphological, syntactic-analytical, tectogrammatical) is reflected in the volume of the annotated data 2 million words are annotated only morphologically, 1,5 million words have also an analytic annotation and from them 800,000 words is provided with tectogrammatical annotation. The second version of PDT has been released in summer 2006 (Hajic et al., 2006), (PDT 2.0, 2006). The experience acquired from annotating such a huge volume of data is so exceptional and illuminating that it has become one of the main motivations for further work within CAC the idea of converting the internal format and annotation schemes of CAC in a way that they would be compatible within PDT was proposed. This conversion will facilitate the possibility of integrating CAC annotations directly into PDT. The currently released first version of CAC (CAC 1.0, 2006) is a result of conversion of the internal format and morphological annotations. The guide to the CAC 1.0 (Hladka et al., 2006) is a road map to the CD-ROM which offers:
We introduce MaltParser, a data-driven parser generator for dependency parsing. Given a treebank in dependency format, MaltParser can be used to induce a parser for the language of the treebank. MaltParser supports several parsing algorithms and learning algorithms, and allows user-defined feature models, consisting of arbitrary combinations of lexical features, part-of-speech features and dependency features. MaltParser is freely available for research and educational purposes and has been evaluated empirically on Swedish, English, Czech, Danish and Bulgarian. 1.
Introduction: Stimulation with affective stimuli elicits event-related potentials (ERP), the area under the curve (AUC) correlating with „arousal“-values of these stimuli. The International Affective Picture System (IAPS) contains 716 pictures with different „arousal“-values (1 to 9), most of them identical (i.e. sports, food), some different (erotic pictures) for men and women. The aim of this study was to examine sex differences in the generation of ERP, elicited by pictures with large differences in the arousal-ratings in both sexes.
We introduce Talbanken05, a Swedish treebank based on a syntactically annotated corpus from the 1970s, Talbanken76, converted to modern formats. The treebank is available in three different formats, besides the original one: two versions of phrase structure annotation and one dependency-based annotation, all of which are encoded in XML. In this paper, we describe the conversion process and exemplify the available formats. The treebank is freely available for research and educational purposes. 1.
Natural language processing researchers currently have access to a wealth of information about words and word senses. This presents problems as well as resources, as it is often difficult to search through and coordinate lexical information across various data sources. We have approached this problem by creating a shared environment for various lexical resources. This browser, BULB (Brandeis Unified Lexical Browser) and its accompanying front-end provides the NLP researcher with a coordinated display from many of the available lexical resources, focusing, in particular, on a newly developed lexical database, the Brandeis Semantic Ontology (BSO). BULB is a module-based browser focusing on the interaction and display of modules from existing NLP tools. We discuss the BSO, PropBank, FrameNet, WordNet, and CQP, as well as other modules which will extend the system. We then outline future extensions to this work and present a release schedule for BULB. 1.
Celebrity Recognition Priming: Is Association Required? Lara L. Jones (laraj@uga.edu) Adam Pope (adrepo@uga.edu) Eva Bonney Reed (bonreed@uga.edu) Patrick Thompson (thompson.patrick.d@gmail.com) Elizabeth Cooper (lizzie23@uga.edu) Kevin Wilson (iamag2@uga.edu) Department of Psychology, University of Georgia Psychology Building, Athens, GA 30602 USA from a musical artist familiarity task (n = 50) on the basis of having no association with the target and having a familiarity rating ≥ 5.00. Finally, 34 participants rated the similarity between the target and each of the three Prime- types (counterbalanced across three lists). The categorical primes (M = 4.88, SE =.14) were reliably more similar than the associative primes (M = 3.99, SE =.21) and the unrelated primes (M = 2.38, SE =.09), both ps <.05. Participants judged whether each of 72 target names was a known celebrity name. The experimental trials consisted of 18 related (either associative or categorical) prime-target trials, 18 unrelated prime-target trials (e.g., Sting AE Adam Sandler), and 36 filler trials consisting of fictional target names (e.g., Bruce Willis AE Carl Spencer). Each prime celebrity name was displayed on a computer screen for 500 msec, followed by a 1500 msec blank screen, and then the target name until a response was provided. Does the semantic organization of actors consist of only associative links (e.g., former co-stars in a popular movie)? Or can two actors share a purely categorical link? Previous studies on celebrity recognition have found that celebrity names (e.g., Adam Sandler) were recognized faster following presentation of an associated person (e.g., Drew Barrymore). Yet the evidence for semantic priming without association (i.e., “categorical priming”; Jimmy Fallon AE Adam Sandler) is equivocal (see Carson & Burton, 2001). Several possible reasons could account for the lack of reliable categorical priming including: target familiarity, prime and target similarity (see McRae & Boisvert, 1998), and stimulus onset asynchrony (SOA), with longer SOAs required for categorical than associative priming. We more closely controlled these critical factors to re-examine whether celebrity names would be recognized faster following an associatively or categorically related celebrity. Prime-type (associative vs. categorical) was a between- participants factor to prevent the robust associative relation from overshadowing the weaker categorical relation. Results and Discussion Overall, targets were recognized faster following the related primes (M = 757, SE = 13) than the unrelated primes (M = 784, SE = 13), p <.01. The Prime-type × Relation interaction was not reliable (p =.64). Critically, the related items were judged faster than the unrelated items within both the associative condition (31 msec; p <.05) and the categorical condition (23 msec; p <.05). Thus, results indicate that people belonging to the same category may be organized on the basis of similarity in addition to association. Method Participants University of Georgia undergraduates participated in the experiment for course credit and were randomly assigned to the associative (n = 53) or to the categorical (n = 51) Prime- type condition. An additional 196 undergraduates participated in the stimulus-norming tasks described below. Table 1: Response Times (msec); Standard errors are in parentheses Materials and Procedure Participants (n = 52) rated the familiarity of 268 actor names on a scale from 1 (unfamiliar) to 7 (very familiar). From these names, 140 were selected on the basis of having familiarity ratings ≥ 5.00 for inclusion in the association task, wherein participants (n = 60) provided the name of the first person who came to mind for the presented celebrity. Both forward and backward association probabilities were calculated for a selected 36 associatively-related prime- target pairs (M =.35, SE =.04 and M =.23, SE =.03). Celebrities that were similar to these targets were generated by the authors to serve as categorical primes. These primes were from the same actor category but were unassociated with the target. Thirty-six unrelated primes were selected Prime-type Associative Categorical Related Unrelated References Carson, D. R. & Burton, A. M. (2001). Semantic priming of person recognition: Categorical priming may be a weaker form of the associative priming effect. The Quarterly Journal of Experimental Psychology, 54A, 1155-1179. McRae, K. & Boisvert, S. (1998). Automatic semantic similarity priming. Journal of Experimental Psychology: Learning, Memory, and Cognition, 24, 558-572.
In this paper, we present a generic analysis of etymological data intended to provide a uniform framework for modeling such information in lexical databases. Based on the explicit reification of etymons and of the links between them, our proposal provides means to state additional constraints for both, as well as a preliminary set of standard descriptors to be used to this end. The model has been extensively tested on a variety of concrete cases extracted from the TLFi (Trésor de la Langue Française informatisé), allowing us to identify further mechanisms (alternatives, multiple links, composition, etc.) needed for etymological data representation. Taking into account the current standardization efforts within ISO committee TC 37/SC 4 to define a specification platform for lexical data (aka LMF, Lexical Markup Framework), we try to show that our proposal could be a possible contribution to this project
This paper describes a peer-to-peer architecture for representing and disseminating linguistic corpora, linguistic annotation, and resources such as lexical databases and gazetteers. The architecture is based upon a ‘Universal Database’ technology in which all information is represented in globally identified, extensible bundles of attribute-value pairs. These objects are replicated at will between peers in the network, and the business rules that implement replication involve checking digital signatures and proper attribution of data, to avoid information being tampered with or abuse of copyright. Universal identifiers enable comprehensive standoff annotation and commentary. A carefully constructed publication mechanism is described that enables different users to subscribe to material provided by trusted publishers on recognized topics or themes. Access to content and related annotation is provided by distributed indexes, represented using the same underlying data objects as the rest of the database.
We exploit the resources in the Arabic Treebank (ATB) for the novel task of automatically creating lexical semantic verb classes for Modern Standard Arabic (MSA). Verbs are clustered into groups that share semantic elements of meaning as they exhibit similar syntactic behavior. The results of the clustering experiments are compared with a gold standard set of classes, which is approximated by using the noisy English translations provided in the ATB to create Levin-like classes for MSA. The quality of the clusters is found to be sensitive to the inclusion of information about lexical heads of the constituents in the syntactic frames, as well as parameters of the clustering algorithm. The best set of parameters yields an Fβ=1 score of 0.501, compared to a random baseline with an Fβ=1 score of 0.37.
Queneau's language has been analysed many times, mostly from a linguistic point of view, with special attention being paid to such procedures as phonetic transcription, lexical and syntactic mistakes or vocabulary typical of colloquial speech. However, Queneau's aim is not simply to imitate spoken discourse. Underlining of the oral aspect of a literary text emphasises its ludic character, i.e., its being -- in a sense -- the author's intellectual game with the reader. Queneau's linguistic experiments are not just limited to the most frequently mentioned techniques, by means of which he introduces the spoken discourse into literature. Simultaneously, Queneau employs very sophisticated, precise or even technical vocabulary as well as varied stylistic figures, often very complex. The present article analyses this play of linguistic registers, which constitutes the originality of Queneau's style and demonstrates that it is the conscious strategy of the author, who, rejecting established linguistic norms and literary conventions, plays with the reader.
This paper describes the usage of XML for representing cross-language phrase alignments in parallel treebanks. We have developed a TreeAligner as a tool for interactively inserting and correcting such alignments as an independent level of treebank annotation.