Báo cáo khoa học: "PROCESSING ENGLISH WITH A GENERALIZED PHRASE STRUCTURE GRAMMAR" pdf

... Linguistic generalizations can be captured in a context-free grammar with a metagrammor, i.e. a higher-level grammar that generates the actual grammar as its language. The metagrammar has two ... PROCESSING ENGLISH WITH A GENERALIZED PHRASE STRUCTURE GRAMMAR Jean Mark Gawron, Jonathan King, John Lamping, Egon Loebner, Eo Anne Paulson, Geoffrey K. Pullum, Ivan A. Sag, and Thomas Wasow Computer ... : 1. Grammar a. Lexicon b. Rules and Metarules 2. Parser and Grammar Compiler 3. Semantics Handler 4. Disambiguator 5. HIRE database 3. GRAMMAR AND LEXICON The grammar that has been...

Báo cáo khoa học: "Simple English Wikipedia: A New Text Simpliﬁcation Task" pdf

... removed all article pairs where eitherarticle: contained only a single line, was flagged as a stub, was flagged as a disambiguation page or was a meta-page about Wikipedia. After pairing and filter-ing, ... paragraph pair (i.e. a simpleparagraph and one or more normal paragraphs), wethen used a dynamic programming approach to findthat best global sentence alignment following Barzi-lay and Elhadad ... simplificationcan improve the performance of NLP tasks, includ-ing parsing, semantic role labeling, machine transla-tion and summarization (Miwa et al., 2010; Jonnala-gadda et al., 2009; Vickrey and...

Báo cáo khoa học: "Chinese Segmentation with a Word-Based Perceptron Algorithm" docx

... the source agenda and thetarget agenda. Initially the source agenda containsan empty sentence and the target agenda is empty.At each processing stage, the decoder reads in a character from ... with each candidate in the source agenda and puts thegenerated candidates onto the target agenda. Aftereach character is processed, the items in the targetagenda are copied to the source agenda, ... havinglength l5 a word ending with character c and havinglength l6space-separated characters c1and c27character bigram c1c2in any word8the ﬁrst and last characters c1and c2of anyword9word...

Báo cáo khoa học: "Machine Translation with a Stochastic Grammatical Channel" doc

... the language-independent bracketing degenerate case of the SITG: 3 all A -4 [AA] aO A + (AA) A b(54Y) x/y VX, y lexical translations A b(.~¢) .z'/~? VX language 1 vocabulary A b(_~y) ... statistical and grammatical machine translation. As with the pure statistical translation model described by Wu (1996) (in which a bracketing transduction grammar models the channel), alternative ... only (1) a translation lexicon, (2) a context-free grammar for the target language, and (3) a bigram language model. The fact that no explicit bilingual translation rules are used makes the...

Báo cáo khoa học: "Lexicon acquisition with a large-coverage unification-based grammar" pot

... chosefor a statistical PoS tagger, i.c. Trigrams'n'Tags(TnT) (Brants, 2000). These taggers return a num-ber of alternatives each associated with a proba-bility, so that the parser can ... features. Barg and Walther (1998)talk about generalisable and revisable information.The former are values that are too specific (e.g.case), while the latter are values that should bechangeable. ... acquisition with a large-coverage unification-based grammarFrederik FouvryComputational LinguisticsSaarland UniversityPO Box 15 11 50D-66041 Saarbrticken, Germanyfouvry@coli.uni—sb.deAbstractWe...

Báo cáo khoa học: "Meaningful Conversation with a Mobile Robot" pot

... engaging in a dialogue.3.2 The Internal MapGodot moves about in the basement of our depart-ment and uses an internal map for navigation. Ithas two levels of representation: a geometrical and a topological ... OAA connectionUSER 1— Image Viewer I- Semantic Map'Map Viewer ISpoken Dialogue System Imap infooff-boardon-boardNavigation System4-10ModuleNavigationNavigationOAA ... representation it usesfor navigation and communication with the dia-logue manager, and the navigation component.3.1 Godot, the RobotGodot is an RWI Magellan Pro mobile robot plat-form with an...

Báo cáo khoa học: "Capturing Salience with a Trainable Cache Model for Zero-anaphora Resolution" doc

... MatsumotoGraduate School of Information ScienceNara Institute of Science and Technology8916-5, Takayama, IkomaNara 630-0192, Japan{inui,matsu}@is.naist.jpAbstractThis paper explores how to apply ... particular, for languages such as Japanese,anaphora resolution is crucial for resolving a phrase in a text to its referent since phrases, es-pecially nominative arguments of predicates, arefrequently ... empirical evaluation on Japanesezero-anaphora resolution shows that our learning-based cache model drastically reduces the searchspace while preserving accuracy.The procedure for zero-anaphora...

Báo cáo khoa học: "Unsupervised Decomposition of a Document into Authorial Components" pdf

... more similar to ours was done by Graham et al. (2005). However, they assume that examples of pairs of paragraphs labeled as same-author/different-author are available for use as the basis of ... University Tel Aviv University Ramat Gan, Israel Jerusalem, Israel Ramat Aviv, Israel {moishk,navot.akiva}@gmail.com dershowitz@gmail.com nachumd@tau.ac.il Abstract We propose a novel ... reasons that will be made clear below. 4.1 (Almost) Automatic Synset Identification One of the advantages of using biblical litera-ture is the availability of a great deal of manual annotation....

Báo cáo khoa học: "Discriminative Training of a Neural Network Statistical Parser" pdf

... uses a large-vocabularytagger (Ratnaparkhi, 1996) as a preprocessingstage may compensate for its smaller vocabu-lary. Also, the main reason for using a smallervocabulary is the computational ... computationally tractable forlarge datasets and a good approximation to thetheoretically optimal method. The parser whichuses this approach outperforms both a genera-tive model and a discriminative ... post-word beam width to 5 achieves fastparsing with reasonable performance in all mod-els. For the parsers with generative probabilitymodels, maximum accuracy is achieved with a post-word beam width...

Báo cáo khoa học: "AN ALGORITHM FOR GENERATION IN UNIFICATION CATEGORIAL GRAMMAR" pdf

... their argument with their own semantics. That is, they are semantically vacuous. Examples from English are complementisers and case-marking prepositions. Again, we add an additional clause ... other hand, a lexical NP such as Harry will bind a variable in the semantics of an expression indicating that the translation of Harry is a constant. However, no other semantic material will ... representation language itself. In particular, the only use of variables in the language is in representing existentially quantified variables over individuals. Thus every appearance of a variable...

Xem thêm