Báo cáo khoa học: "Choosing Sense Distinctions for WSD: Psycholinguistic Evidence" potx

... pages 249–252,Columbus, Ohio, USA, June 2008.c2008 Association for Computational LinguisticsChoosing Sense Distinctions for WSD: Psycholinguistic Evidence Susan Windisch Brown Department ... unre-lated senses), we found a reliable difference (same sense mean: 1056ms, different sense mean: 1272ms; t32 =6.33; p<.0001). We also found better accuracy for same sense pairs (same sense: ... related senses, (3) closely related senses, and (4) same senses (see Table 1 for examples). Placement in these groups depended both on the classification of the usages by WordNet and the Oxford...

Tài liệu Báo cáo khoa học: "Bilingual Sense Similarity for Statistical Machine Translation" ppt

... that uses the VSM to compute sense similarity for terms from parallel corpora. The sense similarities, i.e. the translation probabilities in a translation mod-el, for units from parallel corpora ... co-occurrence counts of the two units. Therefore, questions emerge: how good is the sense similarity computed via VSM for two units from parallel corpora? Is it useful for multi-lingual applications, ... Semantic Roles for SMT: A Hybrid Two-Pass Model. In: Proceedings of NAACL/HLT, Boulder, CO. D. Yuret and M. A. Yatbaz. 2009. The Noisy Channel Model for Unsupervised Word Sense Disambigua-tion....

Báo cáo khoa học: "Word Sense Induction for Novel Sense Detection" pot

... other senses discovered for cheat, we notice that the model has induced amyriad of senses: the relationship sense of cheat(senses 1, 3 and 4, e.g. husband cheats); the examusage of cheat (sense ... gold sense x, then sense a is mapped to gold sense x. Therefore, if the proportion of junk senses in the map-ping instances is low, their inﬂuence on WSD results will benegligible.594 Sense ... novel sense or not. This binary dis-tinction is easier than ﬁne-grained sense annota-tion, and since we do not use these annotations for formal evaluation — only for selecting items for our...

Báo cáo khoa học: "Automatic sense prediction for implicit discourse relations in text" docx

... used for training.7 Classiﬁcation Results For all experiments, we used sections 2-20 of thePDTB for training and sections 21-22 for testing.Sections 0-1 were used as a development set for feature ... 2% for Comparison, and 6% for Contingency.7.3 Best resultsAdding other features to word pairs leads to im-proved performance for Contingency, Expansionand Temporal relations, but not for ... annotated with a sense. The sensesare arranged in a hierarchy, allowing for annota-tions as speciﬁc as Contingency.Cause.reason. Inour experiments, we use only the top level of the sense annotations:...

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

... 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. ... 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 ... 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...

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: "Using Derivation Trees for Treebank Error Detection" potx

... andpoints on either side). See Dickinson and Meur-ers (2003b) for details. This work forms the basis for the DECCA system.12.2 Motivation for Our Approach(2) a. NPqmpsummitNP$rmSharmNPAl$yxthe ... SheikhNP#a3qmpsummit#b1S:1.2NPNP^$rmSharm#b2NPAl$yxThe Sheikh For (2a) For (2b) For (2c) A:1.1,left#b3NPAl$yxThe SheikhA:1.1,left#c3$rmSharmFigure 1: Etrees and Derivation Trees for (2abc).tree-substitution, sister-adjunction, ... to compare for inconsistent an-notation, and are computed separately for each in-stance of each nucleus from the full derivation treethat each instance is part of.5 For example, for comparing...

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

... treebanks, making the 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 ... Transformations, Parsers, and TreebanksPseudo-projective parsing and transformations for coordination and verb groups are instances of thesame general methodology:1. Apply a tree transformation ... data-drivenparser designed for (projective) labeled dependencystructures. In this sense, the tree transformationsare independent of parsing methodology. Whetherthe beneﬁcial effect of a transformation, if...

Báo cáo khoa học: "A Connectionist Architecture for Learning to Parse" potx

... computed. However the link weights that perform this computation are the same for all the positions in the sequence. Therefore the infor- mation that was learned for an input and context in one sequence ... pattern for the gestalt inputs is straightforward, since these inputs per- tain to information about the sentence as a whole. Whenever a tag is input to the network, the activa- tion pattern for ... problem because out- puts for the extra constituents are produced on the same units by the same link weights as for other constituents. The training that occurred for the other constituents...

Báo cáo khoa học: "Learning PP attachment for filtering prosodic phrasing" potx

... according to these search meth-ods was used for freq(X P). The freq(X) was de-rived from the WWW by performing a separatesearch for the single word form.Method I: cooccurrence NnearP or VnearPVolk ... al-gorithm for Dutch (van Herwijnen and Terken,2001b). This phrasing algorithm uses syntactic in-formation and sentence length for the allocationof prosodic phrase boundaries. For a subset ... of information about syntacticstructure being useful for placing phrase bound-aries is the attachment of prepositional phrases(PPs). When a PP is attached to the precedingNP or PP (henceforth...

Xem thêm