automatic verb classification incorporating selectional preferences

... 113K verb instances, 97K of which are verbs represented in at least one VerbNet class Semlink includes 495 verbs, whose instances are labeled with more than one class (including one single VerbNet ... interest has been paid to two verb categorization schemes: VerbNet (Schuler, 2005) and FrameNet (Baker et al., 1998), which has also fostered production of many automatic ap-proaches to predicate ... lexical and syntactic features for learning verb classification ap-pears to be computationally problematic For exam-ple, the verb order can belongs to the two VerbNet classes: – The class 60.1, i.e.,

Ngày tải lên: 23/03/2014, 14:20

... a huge amount of data Among those tools, automatic musical genre classifiers (AMGC) can have a particularly important role, since they could be able to automatically index and retrieve audio data ... create an automatic equalizer able to choose which frequency bands should be attenuated or re-inforced according to the label assigned to the signal being considered AGC could also be used to automatically ... Trang 1Volume 2007, Article ID 64960, 12 pagesdoi:10.1155/2007/64960 Research Article Automatic Genre Classification of Musical Signals Jayme Garcia Arnal Barbedo and Amauri Lopes Departamento

Ngày tải lên: 22/06/2014, 23:20

... al., 1999 Verb-object Verb-subject none Target, relative, and relation in a parsed corpus (parsed BNC) clustering Ritter, 2010 Verb-subject Verb-object Subject-verb-object Subject-verb-object ... POS N-grams to generate test data for their selectional preferences model, but not to infer preferences Zhou et al (2011) identified selectional preferences of one word for another Reference ... inverse dependencies Inverse selectional preferences are selectional preferences of arguments for their predicates, such as a preference of a subject or object for its verb They capture semantic

Ngày tải lên: 22/02/2014, 03:20

... that cannot be easily incorporated into the existing classification scheme, resulting in a growing problem in the comprehensive evolutionary classification of the secretory PLA2 superfamily [1] ... University of Florida, Gainesville, FL, USA Keywords enzymatic activity; phospholipase A2; phylogenetic classification; sea anemone; sequence; venom Correspondence T Turk, Biotechnical Faculty, Department ... A2 isolated from the sea anemone Urticina crassicornis – its primary structure and phylogenetic classification ˇ ˇ ˇ ˇ ˇ ˇ Andrej Razpotnik1, Igor Krizaj2, Jernej Sribar2, Dusan Kordis2, Peter

Ngày tải lên: 06/03/2014, 11:20

... LDA-style models for the task of computing selectional preferences This work learns selectional preferences between the fol-lowing grammatical relations: verb-object, noun-noun, and adjective-noun ... (e.g., the subject and direct object of a verb) 3 Topic Models for Selectional Prefs We present a series of topic models for the task of computing selectional preferences These models vary in the ... naturally model the class-based nature of selectional preferences, but don’t take a pre-defined set of classes as input Instead, they compute the classes automatically This leads to better lexical

Ngày tải lên: 07/03/2014, 22:20

... complement the verbal content available in messages, they should give us a way to automatically label messages ac-cording to emotional class, while leaving us with messages with enough verbal content ... actual non-verbal behavior; Provine et al (2007) also found that emoticons are used to “punctuate” messages rather than replace lexical content, appearing in similar grammatical locations to verbal ... conventions understood by the users to perform some of the same functions as these acoustic and non-verbal cues The most familiar of these is the use of emoticons, either Western-style (e.g :), :-(

Ngày tải lên: 08/03/2014, 21:20

... the New York Times corpus (Sandhaus, 2008), the word “states” has a higher likelihood of being a verb in let-ters (approx 20%) than in editorials (approx 2%) Part-of-Speech (PoS) taggers or statistical ... experiments in German (Wolters and Kirsten, 1999) and Russian (Braslavski, 2004) In subsequent research, automatically gener-ated feature sets have become more popular Most of these tend to be language-independent ... language A, using a document representation containing only content words (nouns, adjectives, and verbs with a high corpus frequency) These words are then trans-lated from language B to language

Ngày tải lên: 17/03/2014, 22:20

... multicopper oxidases (MCOs) from fungi, insects, plants, and bacteria provided the basis for a refined classification of this enzyme family into laccases sensu stricto (basidiomyc-etous and ascomyc(basidiomyc-etous), ... metabolism has been proposed [32] Laccases have only recently been discovered in bac-teria and their classification and function are still con-troversial The first report of a bacterial laccase was from ... similarity and phylo-genetic analysis until specific physiological functions are defined They presented a classification of plant LMCO sequences and, together with expression pro-files, provided strong evidence

Ngày tải lên: 23/03/2014, 11:20

... the cross-language text classification problem reduces to a standard classification problem in the cross- lingual space. Note that the existing methods for cross-language text classification can be ... task, or a sentiment classification task. In addition, we are given labeled documents for the identical task in a different source language S. Such type of cross-language text classification problems ... dif- ferent sentiment classification tasks. The paper is organized as follows: Section 2 surveys related work. Section 3 states the termi- nology for cross-language text classification. Sec- tion

Ngày tải lên: 23/03/2014, 16:20

... use a range of methods based on local and global formulations and introduce novel approaches for incorporating the outputs of machine learners into collective classifica-tion algorithms Our experimental ... for collective document classification tasks; (3) we demonstrate effective novel approaches for incorporating the outputs of SVM classifiers into collective classifiers; and (4) we demonstrate ... “same class” or “different class” Let Ψ denote a set of functions representing the classification preferences produced by the content-only and citation classifiers: • For each Vi∈ V, φi∈ Ψ is a

Ngày tải lên: 23/03/2014, 16:20

... models (HMMs) to obtain a sequence-based subdivision of the SDR superfamily that allows for automatic classification of novel sequence data and provides the basis for a nomenclature system Results ... for every member in a family, thus support-ing the present classification We also find a good correlation between the present family classification and the function(s) among families for which a ... families are only found among bacteria, where the ‘classical’ SDR type is most prominent The HMM-based classification is used as a basis for a sustainable and expandable nomenclature system Abbreviations

Ngày tải lên: 29/03/2014, 09:20

... solving the IS subproblem of whether a per-son proper name is already known to the reader im-proves automatic summarization of news There-fore, we here model IS in written text, creating a new dataset ... as full anaphoric information for three main anaphora types (coreference, bridging, comparative) Automatic recognition of IS. Vieira and Poesio (2000) describe heuristics for processing definite ... integrate our annotations with it This definition includes coreference with noun phrase as well as verb phrase antecedents3 Mediatedrefers to entities which have not yet been introduced in the text

Ngày tải lên: 30/03/2014, 17:20

... Schmid, 2008 Combining EM Training and the MDL Principle for an Auto-matic Verb Classification Incorporating Selectional Preferences ACL ’08. ... annotation of the WSJ sections 2– 21 Verbs were identified using MXPOST (Ratna-parkhi, 1996) Words tagged with any of the verb tags, except of the auxiliary verbs (‘have’, ‘be’ and ‘do’) were considered ... (excluding punctuation) which contain a single verb A sequence of words will be marked as an argument of the verb if it is a con-stituent that does not contain the verb (according to the unsupervised parse

Ngày tải lên: 30/03/2014, 21:20

... conciseness, we only reportthe FPS results for the automatically derived database classification Finally,for the Controlled dataset, we use the automatically derived classification with da-τ es ... ˆp(w|D) = df (w)  . Callan et al [1999] and Callan and Connell [2001] presented pioneering work on automatic extraction of approximate content summaries from tive” text databases that do not export ... likely to retrieve mainly documents that are related to the “Health” category Gravano et al [2003] automatically construct thesetopic-specific queries using document classifiers, derived via supervised

Ngày tải lên: 30/03/2014, 22:20

... frequent a verb can be used with the interpretation of a process Note that Portuguese allows modifiers to occur freely between a verb and its complements, so this test should work for transitive verbs ... a+b Processes can be modified by for ad-verbials, whereas culminated processes are modified by in adverbials. This indicator tests the occurrence of a verb in contexts that require these aspectual ... subcate-gorization frames of verbs from large amounts of data Relevant to our work is that of Siegel and McKeown (2000) The authors guess the aspec-tual type of verbs by searching for specific

Ngày tải lên: 31/03/2014, 20:20

... of an NPI Rather, the most common collocations of DEOs are the selectional preferences of the DEO, such as common argu-ments to verbal DEOs, prepositions that are part of the subcategorization ... highS(y) score Examples of piggybackers found by DLD09 in-clude the proper noun Milken, and the adverb vig-orously, which collocate with DEOs like deny in the corpus they used DLD09’s solution ... 211041 NPI contexts in AFP, using the same list of 26 NPIs defined by DLD09 We first define an automatic measure of per-formance that is common in information retrieval We use average precision

Ngày tải lên: 31/03/2014, 20:20

... {jcabessa,avilla}@nhrg.org Abstract We provide a refined hierarchical classification of first-order recurrent neural networks made up of McCulloch and Pitts cells The classification is achieved by first proving the equivalence ... Muller automata, and then translating the Wadge classification theory from the automata-theoretic to the neural network context The obtained hierarchical classification of neural networks consists of ... neural networks made up of Mc-Culloch and Pitts cells, and provide a refined classification of the networks of this class The classification is achieved by first proving the equivalence between the expressive

Ngày tải lên: 28/04/2014, 09:49

... classification methods proposed were not fully automatic In 2008, Yin et al proposed the use of a Gaussian mixture model- (GMM-) based classifier to automatically classify different cognitive load ... formant frequencies under different load conditions and utilize formant frequency-based features for automatic cognitive load classification We find that the slope, dispersion, and duration of vowel ... the cognitive load classification system that was used in this section Formant frequencies were automatically extracted from full utterances of both databases using the Wavesurfer/Snack toolkit,

Ngày tải lên: 21/06/2014, 07:20

... understood, the shape of the true optimal filterbank for automatic recognition is not known More-over, the recognition performance of automatic systems degrades when speech signals are contaminated ... formant space As a consequence, this phoneme set consists of a group of classes which is difficult for automatic recognition [29] 4.2 Experimental Setup Our phoneme classifier is based on continuous

Ngày tải lên: 21/06/2014, 07:20

... gait recognition technology, there is a large amount of research concerned with the development of automatic radar gait recognition systems Radars have certain advantages over optical-based systems ... directly on short time-frequency windows The raw spectrogram windows are processed and classified automatically into one of three types of arm motion: FAM, PAM, and NAM The HICA, shown Trang 3Time ... extract the best features possible In the proposed approach, the feature extraction process is automatically handled during training 4.5 Classification of Short-Time Segments Several existing

Ngày tải lên: 21/06/2014, 16:20