Báo cáo khoa học: "A Meta-Level Grammar: Redefining Synchronous TAG for Translation and Paraphrase" doc

... A Meta-Level Grammar: Redefining Synchronous TAG for Translation and Paraphrase Mark Dras Microsoft Research Institute Department ... how a meta-level grammar resolves the representational problems; and it further shows that this has no effect on the generative capacity of S -TAG. 2 S -TAG and Machine Translation Synchronous ... object-level formal- ism would necessarily have been increased over that of TAG. However, there is a regular form for TAGs (Rogers, 1994), such that the trees of TAGs in this regular form are...

Báo cáo khoa học: "A Suite of Shallow Processing Tools for Portuguese: LX-Suite" doc

... corpusthat were not used for training.The POS tagger we developed is currently thefastest tagger for the Portuguese language, and itis in line with state-of-the-art taggers for other lan-guages, ... a contraction.54 POS tagger For the POS tagging task we used Brant’s TnT tag- ger (Brants, 2000), a very efﬁcient statistical tag- ger based on Hidden Markov Models. For training, we used 90% ... POS tagger: The tagger must ﬁ rst be trainedon a version of the corpus where the ambiguousstrings are not tokenized, and are tagged with acomposite tag when occurring as a contraction (for example...

Báo cáo khoa học: "A SYNTACTIC FILTER ON PRONOMINAL ANAPHORA FOR SLOT GRAMMAR" pdf

... specifically, in terms of c-command and minimal dominating S and NP domains, control and unbounded de- p endency structures can only be handled b~' ad- itional and fairly complex devices. ... Reinhart (1976) and (1983) for alternative definitions of c-command, and discussions of the role of this re- lation in determining the possibilities of anaphora. See Lappin (1985) for additional ... connection between c-command and distinct varieties of pronominal anal3hora. See Chomsky (1981), (1986a) and (1986b) for alternative definitions of the notion 'government' and 'rain,real...

Báo cáo khoa học: "A Feature-Rich Constituent Context Model for Grammar Induction" doc

... language processing(Lari and Young, 1990; Pereira and Schabes, 1992;Carroll and Charniak, 1992). The constituent con-text model (CCM) for inducing constituency parses(Klein and Manning, 2002) was ... dependencygrammar induction. For instance, the dependencymodel with valence (DMV) of Klein and Manning(2004) has been extended to utilize multilingual in-formation (Berg-Kirkpatrick and Klein, 2010; Co-hen ... items rather than part-of-speech(POS) tags. Additional advances have come frommore complex models, such as combining CCM and DMV (Klein and Manning, 2004) and model-ing large tree fragments (Bod,...

Báo cáo khoa học: "A GENERATIVE GRAMMAR APPROACH FOR THE MORPHOLOGIC AND MORPHOSYNTACTIC ANALYSIS OF ITALIAN" ppt

... of endings: andare (to go), for example, admits two different stems, vad (go) and and (went); so there exist two subclasses of endings named respectively dvl andare and dr2 andare. 4. ... di di prep.simple 2 andare vad dv 1 _andare v.intran.simple 1 andare and I dv2. andar© v.intran.simple I The other sets of data are contained in the Prolog workspace and are structured as ... distinction between data: on one hand the set of lemmata, and on the other the sets of affixes, alterations, endings and enclitics. The former (which is the most relevant and needs to be continuously...

Tài liệu Báo cáo khoa học: A functional polymorphism of apolipoprotein C1 detected by mass spectrometry docx

... divided by the sum of intensities for full-length and truncated ApoC1. The rate constant for disappearance ofApoC1 was determined from a ﬁrst-order decay plot, and standard deviation from triplicate ... dithio-threitol and iodoacetamide, with quantiﬁcation of Cysby detection of mass change of a peptide after reduc-tion and alkylation. These and other approaches havebeen described previously [19], and ... Figure 1B shows an expanded view ofthe ApoC1 proteins from this individual who showeda double peak for each of the two forms of ApoC1.This double peak pattern was highly unusual and wasnot observed...

Tài liệu Báo cáo khoa học: A FYVE-containing unusual cyclic nucleotide phosphodiesterase from Trypanosoma cruzi docx

... Juro Supplies,Lucerne, Switzerland) were added, and the slurry was incu-bated for 36 h at 6 °C on a rotating wheel. The beads werethen pelleted by centrifugation, and the supernatant con-taining ... kDa) and cata-lyze (232 kDa).AcknowledgementsWe would like to thank M. Linder and X. Lan Vu for their technical assistance, R. Brun of the Swiss Trop-ical Institute, University of Basel, for ... MD,USA) for providing expression plasmids for Vps27p-FYVE-GST fusion proteins, Peter Buetikofer (Instituteof Molecular Biology, University of Bern) for provi-ding phospholipids and valuable...

Tài liệu Báo cáo khoa học: "A Graph-based Semi-Supervised Learning for Question-Answering" doc

... non-copulaquestions and build the model for only copula questions.ponent of a candidate sentence. For example for the given question, ”When did Nixon die?”, whenthe following candidate sentence, ... affirmed ques-tions did not contain any object and they are alsoin copula (linking) sentence form that is, theyare only formed by subject and information aboutthe subject as: {subject + linking-verb ... Affirmative Form: To derive lin-guistic information from pair of texts (statements),we parse the question and turn into affirmativeform by replacing the wh-word with a place-holder and associating...

Tài liệu Báo cáo khoa học: "A High-Accurate Chinese-English NE Backward Translation System Combining Both Lexical Information and Web Statistics" pdf

... in the form of “Mr. and Mrs. Smith”, “Mr. And Mrs. Smith”, and so on. To deal with these aliasing forms, we transform all different forms into a standard form for the later ranking and identification. ... retrieve candi-dates and then use lexical information, frequen-cies, and distances to find the correct translation. They achieve a Top-1 accuracy of 81.0% and claim that they outperform state-of-the-art ... most titles and nicknames and some or-ganization names would be translated. Another common case is translating by phonetic values for some parts and by meaning for the others. For example,...

Tài liệu Báo cáo khoa học: "A FrameNet-based Semantic Role Labeler for Swedish" pdf

... instances for the start classifier, 500,000 for the end classifier, and 272,000 for the role classifier. The featuresused by the classifiers are described in Subsec-tion 3.2, and the performance ... A list L of chunks and a target word tBinary classifiers starts and endsOutput: The sets S and E of start and end bracketsSplit L into the sublists Lbefore, Ltarget, and Lafter, which ... we trans-lated manually, and obtained an accuracyscore of 0.75 on the classification of pre-segmented frame elements, and precision and recall scores of 0.67 and 0.47 for thecomplete task.1...

Xem thêm