Báo cáo khoa học: "Using Decision Trees to Construct a Practical Parser" pdf

... Using Decision Trees to Construct a Practical Parser Masahiko Haruno* Satoshi Shirai t Yoshifumi Ooyama t mharuno ~hlp.atr.co.jp shirai,~cslab.kecl.ntt.co.jp oovama~cslal).kecl.nt t.co.j p *ATR ... training data, it not only adapts to any application domain but. also may avoid over- fitting to the data. In the late 80s and early 90s, the induction and parameter estimation of probabilis- ... shown to have significant advantages; 1) better pars- ing accuracy than its single-tree counterpart for any amount of training data and 2) no over-fitting to data for various iterations....

Tài liệu Báo cáo khoa học: "Using Multiple Sources to Construct a Sentiment Sensitive Thesaurus for Cross-Domain Sentiment Classiﬁcation" doc

... sensitive to senti-ment. Unlabeled data is cheaper to collect compared to labeled data and is often available in large quan-tities. The use of unlabeled data enables us to ac-curately estimate the ... UKj .a. carroll@sussex.ac.ukAbstractWe describe a sentiment classiﬁcation methodthat is applicable when we do not have any la-beled data for a target domain but have somelabeled data for ... information between a feature (uni-gram or bigram) and a domain label. After selectingsalient features, the SCL algorithm is used to train a binary classiﬁer. SFA is the spectral feature align-ment...

Tài liệu Báo cáo khoa học: "USING BRACKETED PARSES TO EVALUATE A GRAMMAR CHECKING APPLICATION" ppt

... the hand parse), Recall (the percentage of phrases in the hand parse that are also in the ma- chine parse), and Precision (the percentage of phrases in the machine parse that are in the hand ... utilizing hand-bracketed corpora (such as the University of Pennsylvania Treebank) as a basis for evaluation metrics have been discussed in Black et al. (1991), Harrison et al. (1991), and Black ... had a reasonably correct parse available to them? 3. The Simplified English (SE) standard allows some exceptions to the 'single part of speech' rule in its core vocabulary of about...

Báo cáo khoa học: "Using Reinforcement Learning to Build a Better Model of Dialogue State" pdf

... research (such as (Singhet al., 1999)) for describing a dialogue as a tra-jectory within a Markov Decision Process (Suttonand Barto, 1998). A MDP has four main com-ponents: states, actions, a ... indicate that a small training corpus isactually acceptable to use in a M DP framework aslong as the state and action features are pruned ef-fectively. The use of features such as context andstudent ... user’s last dialogue act,which was found to produce a 52% increase in av-erage reward. Williams et al. (2003) used Super-vised Learning to select good state and action fea-tures as an initial...

Tài liệu Báo cáo khoa học: "Using adaptor grammars to identify synergies in the unsupervised acquisition of linguistic structure" docx

... class—which may partially explain whywe obtained such poor results using morphologyadaptor grammars. It’s straight forward to designan adaptor grammar that can capture a ﬁnite numberof concatenative ... PCFGs to Adaptor GrammarsThis section introduces adaptor grammars as an ex-tension of PCFGs; for a more detailed exposition seeJohnson et al. (2007b). Formally, an adaptor gram-mar is a PCFG ... is a potential rule, with its own probability, so an adap-tor grammar is nonparametric if there are inﬁnitelymany possible adapted subtrees. (An adaptor gram-mar can thus be viewed as a tree substitution...

Tài liệu Báo cáo khoa học: "Using linguistic principles to recover empty categories" ppt

... motivated by the failure of such approaches in this domain; on the contrary, no one seems to have tried a rule-based approach to this problem. Instead it appears that there is an understandable ... this case, the principles of early GB theory. As a result, the recovery of empty categories is, for the most part, more amenable to a rule-based approach than to a learning approach. It makes ... such an approach; and second, to establish a more realistic baseline for future (possibly data-driven or hybrid) approaches. Although it does not seem likely that any application trying to...

Báo cáo khoa học: "Using Machine-Learning to Assign Function Labels to Parser Output for Spanish" ppt

... output by a prob-abilistic parser trained on Cast3LB. To our knowl-edge, this paper is the ﬁrst to describe applying a data-driven approach to function-tag assignment to a language other than English.Our ... complex labels asatomic categories the number of unique labels in-creases and parse quality can deteriorate due to sparse data problems. Secondly, this approach, byrelying on the parser to assign ... oftarget node can have negative impact, greater re-liance on context means greater susceptibility to parse errors. Another factor to consider is the factthat we trained and adjusted parameters on...

Báo cáo khoa học: "From Prosodic Trees to Syntactic Trees" doc

... are automatically generated by a parser and then manually checked in a tree editor. Once a tree has been edited or approved, its phrase boundaries are recorded in a database. When the same ... correct regardless of the changes in the details of trees. We call this a “dynamic treebank” where, instead of maintaining a set of trees, we maintain a parser/grammar, a dictionary, a set of ... sentences, and a database of bracketing information. The trees can be generated at any time. Since our parser/grammar can consult known phrase boundaries to build trees, its performance can be...

Báo cáo khoa học: "Using Similarity Scoring To Improve the Bilingual Dictionary for Word Alignment" doc

... word-aligned data is crucial for example-based machinetranslation, statistical machine translation, but alsoother applications such as cross-lingual informationretrieval. Since it is a hard and ... time-consuming task to hand-align bilingual data, the automation of thistask receives a fair amount of attention. In this pa-per, we present an approach to improve the bilin-gual dictionary that is ... onthe target language at hand. For instance, in Ger-man, a and¨ a will be assigned to the same equiva-lence class, because some inﬂections cause a to be-come¨ a. An improved similarity scoring...

Báo cáo khoa học: "Using Grammatical Relations to Compare Parsers" pptx

... Grammatical Relations to Compare ParsersJudita Preiss*Computer LaboratoryUniversity of CambridgeJudita.PreissAcl.cam.ac.ukAbstractWe use the grammatical re-lations (GRs) described inCarroll ... differentparsers in an anaphora resolution system.This will indicate the impact of a change inparser performance on a real task: althoughone parser may have a marginally higher pre-cision than another ... 32.8345.73Table 9: Anaphora ResultsThe results of the Lappin and Leassanaphora resolution algorithm using each ofthe parsers are presented in Table 9.7 The'algorithms' are only evaluated...

Xem thêm