Báo cáo khoa học: "Treebank Grammar Techniques for Non-Projective Dependency Parsing" pot

... 478–486,Athens, Greece, 30 March – 3 April 2009.c2009 Association for Computational LinguisticsTreebank Grammar Techniques for Non-Projective Dependency ParsingMarco KuhlmannUppsala UniversityUppsala, ... computesthis transformation for a large, empiricallyrelevant class of grammars.1 Introduction Dependency parsing is the task of predicting themost probable dependency structure for a givensentence. ... non-local inform-ation such as arity constraints and Markovization,and therefore should allow for more predictive stat-istical models than those used by current systems for non-projective dependency...

Báo cáo khoa học: "Generalizing Tree Transformations for Inductive Dependency Parsing" potx

... inverse trans-formation for PADT more problematic than for theother treebanks. The absence of a positive effect for PADT is therefore understandable given the deeplynested non-projective constructions ... allowed, whichpose a problem for projective dependency parsers.Direct non-projective parsing can be performed withgood accuracy, e.g., using the Chu-Liu-Edmonds al-1If dependency arcs are drawn ... usingthe added information in the dependency labels. Theonly assumption made about the parser is thereforethat it can learn to derive labeled dependency struc-tures with augmented dependency labels.2.2...

Báo cáo khoa học: "Discriminative Classiﬁers for Deterministic Dependency Parsing" docx

... ☎❄NMODNNmarkets✞ ☎❄PMOD..❄✞☎PFigure 1: Dependency graph for an English sentence from the WSJ section of the Penn Treebankrequire non-projective dependency arcs. For thepurpose of this paper, however, ... thatSVM outperforms MBL for the three most com-plex models Φ3, Φ4and Φ5, both for English andChinese. The results for Swedish are less clear,although the labeled accuracy for Φ3and Φ5aresigniﬁcantly ... will deﬁne dependency graphs,describe the parsing algorithm used in the experi-ments and ﬁnally explain the extraction of features for the history-based models.2.1 Dependency GraphsA dependency...

Tài liệu Báo cáo khoa học: "Web-Scale Features for Full-Scale Parsing" doc

... errorreduction. Results are for dependency parsing on the dev set for iters:5,training-k:1.tal errors break down by gold head. For example,the 12.1% total error reduction for attachments of anIN ... compute features for the full parsingtask. To show end-to-end effectiveness, we incor-porate our features into state-of-the-art dependency and constituent parsers. For the dependency case,we ... fromconstituent format to dependency format. FollowingKoo et al. (2008), we used the MXPOST tagger(Ratnaparkhi, 1996) trained on the full training datato provide part-of-speech tags for the development3All...

Tài liệu Báo cáo khoa học: "An Integrated Environment for Computational Linguistics Experimentation" pot

... that the LinguaStream platformpromotes the combination of purely declarativeformalisms (when GATE is mostly based on theJAPE language and NOOJ focuses on a uniqueformalism), and allows processing ... analy-sis models and methodological concerns. Finally,when other platforms usually enforce the use of adedicated document format, LinguaStream is ableto process any XML document. On the other ... (they provide a formalrepresentation for a linguistic phenomenon) andoperative (they can be considered as instructionsto drive a computational process).Moreover, the platform takes advantage...

Tài liệu Báo cáo khoa học: "A rich environment for experimentation unification grammars" potx

... into discussion of the under- lying complexity, for which we unfortunately do not have space here, we give an exter- nal form of a lexical entry for some of the senses of the German verb traeumen. ... subscripts. Three other special symbols are used: + stands for the unifica- tion operator * stands for top, the underdefined element. # stands for bottom, the overdefined element that corresponds ... PATR-style languages is their lack of facilities for defining new abstractions and expressing linguistic generalisations not foreseen (or even foreseeable) by the language designer. This becomes...

Tài liệu Báo cáo khoa học: "A COMMON FRAMEWORK FOR ANALYSIS AND GENERATION" potx

... compo- nent describing their functional structure. For the rule for S, for instance, we add an ele- ment describing what the SUBJECT and PRED are for. We could say that the SUBJECT is the theme ... complete formal paraphrase of (1) must include at least as much information as we have given above. In particular, the logical structure of our para- phrases contains essential information ... consid- erable debate about the best way of representing this information. 2 GENERATION Suppose we have the formula given above as a for- mal paraphrase of (1), and we want to generate an English...

Báo cáo khoa học: "Advanced Online Learning for Natural Language Processing" pot

...

Báo cáo khoa học: "Learning Expressive Models for Word Sense Disambiguation" pot

... task outperforms the other machine learning techniques investigated. In the monolingual task, the approach per-forms as well as the state-of-the-art sys-tems which reported results for the same ... customized for this monolingual task, the ILP approach signif-icantly outperforms the majority sense baseline and performs as well as the state-of-the-art system re-porting results for the same ... many techniques have been pro-posed to solve the problem. Recent approaches focus on the use of various lexical resources and corpus-based techniques in order to avoid the sub-stantial effort...

Báo cáo khoa học: "A STOCHASTIC PROCESS FOR WORD FREQUENCY DISTRIBUTIONS" pot

... (1975), have been put forward, all of which have Zipf's law as some special or limiting form. Unrelated to Zipf's law is the lognormal hypothesis, advanced for word fre- quency ... matrix 7 ) defines a uniform distribu- tion (all pi# equal), we immediately have that the expected neighborhood density for length rnl is identical for all targets Yt, while for length m~ > ... probabilities py. Consequently, by (5), for fixed length m, higher frequency words will have more neighbors than lower frequency words for non-uniformly dis- tributed transition probabilities....

Xem thêm