Báo cáo khoa học: "Automatic Acquisition of English Topic Signatures Based on a Second Language" potx

... Automatic Acquisition of English Topic Signatures Based on a Second LanguageXinglong WangDepartment of InformaticsUniversity of SussexBrighton, BN1 9QH, UKxw20@sussex.ac.ukAbstractWe ... Topic signatures can be useful in a number of Natural Language Process-ing (NLP) applications, such as WordSense Disambiguation (WSD) and TextSummarisation. Our method takes ad-vantage of the ... way in whichword senses are lexicalised in English and Chinese, and also exploits the largeamount of Chinese text available in cor-pora and on the Web. We evaluated the topic signatures on...

Tài liệu Báo cáo khoa học: "AUTOMATIC ACQUISITION OF SUBCATEGORIZATION FRAMES FROM UNTAGGED TEXT" doc

... system that gets only positive examples and makes a permanent judgment on a single example will always degrade as the number of occurrences increases. In fact, making a judgment based on any fixed ... AUTOMATIC ACQUISITION OF SUBCATEGORIZATION FRAMES FROM UNTAGGED TEXT Michael R. Brent MIT AI Lab 545 Technology Square Cambridge, Massachusetts 02139 michael@ai.mit.edu ABSTRACT This ... extraordinary accuracy of verb detection within a tiny fraction of the rate achieved by trained human taggers and it's relatively low efficiency are consistent with the priorities laid...

Báo cáo khoa học: "Automatic Acquisition of Ranked Qualia Structures from the Web" potx

... matters. Given a qualiaterm qt as well as a qualia element qe we actuallycalculate Web-P(qe,qt) for a speciﬁc qualia role.4.4 Conditional Probability (P)The non web -based conditional probability ... present a quanti-tative evaluation of our approach and a comparison of the different ranking measures with respect to thisgold standard. Finally, we also provide an evaluationin which test persons ... is on the one hand based on the assumptionthat instances of a certain semantic relation can beacquired by matching certain lexico-syntactic pat-terns more or less reliably conveying the relationof...

Báo cáo khoa học: "Automatic Acquisition of Adjectival Subcategorization from Corpora" docx

... frequency of SCFs for each ad-jective is absent.The inadequacy of manually-created dictionariesand the difﬁculty of adequately enhancing and main-taining the information by hand was a central moti-vation ... grammaticality.6 ConclusionWe have described a novel system for automati-cally acquiring adjectival subcategorization and as-sociated frequency information from corpora, alongwith an annotation ... linguisticannotation of SCFs in corpus data aimed at alleviat-ing the process of obtaining training and test data forsubcategorization acquisition. The tool incorporatesan intuitive interface with...

Báo cáo khoa học: "Automatic Acquisition of Named Entity Tagged Corpus from World Wide Web" pot

... learning approach, which is moreattractive because it is trainable and adaptable, andsubsequently the porting of a machine learning sys-tem to another domain is much easier than that of a rule -based ... corpus.2 Automatic Acquisition of an NE TaggedCorpusWe only focus on the three major NE categories (i.e.,person, organization and location) because othersare relatively easier to recognize and ... sep-aration of functional words, segmentation of com-pound nouns, and veriﬁcation of the usefulness of the extracted sentences.An NE is often concatenated with more than onejosa, a Korean functional...

Báo cáo khoa học: "Automatic Acquisition of Language Model based on Head-Dependent Relation between Words" pdf

... which is a key part of many natural language applications such as speech recognition and statistical machine translation. In this paper, we present a language modeling based on a kind of simple ... associate a priori probability to a sentence. It is a key part of many natural language applications such as speech recognition and statistical machine translation. Previous works for language ... a robust grammar, grammar -based language modeling is expected to be more powerful and compact in model size than n-gram -based one. In this paper we present a language modeling based on a...

Báo cáo khoa học: "AUTOMATIC ACQUISITION OF A LARGE SUBCATEGORIZATION DICTIONARY FROM CORPORA" doc

... INTRODUCTION Rule -based parsers use subcategorization information to constrain the number of analyses that are generated. For example, from subcategorization alone, we can deduce that the ... corpora of unrestricted text: 1. Dictionaries with subcategorization information are unavailable for most languages (only a few recent dictionaries, generally targeted at non- native speakers, ... has been done on various sorts of col- location information that can be obtained from text corpora, the only research that I am aware of that has dealt directly with the problem of the automatic...

Báo cáo khoa học: "AUTOMATIC ACQUISITION OF THE LEXICAL SEMANTICS OF VERBS FROM SENTENCE FRAMES*" doc

... an object, always takes an agent, always has a patient, and always has the patient serving as object. The learner will also assume that em break never takes a location, a dative, etc. ... subject and object grammatical relations, and a representation of what NPs serve as agent, patient, instrument and location. This may be seen as begging the question of verb acquisition, because, ... is actually a combination of this weak form of semantic bootstrapping with what is called em syntactic bootstrapping, the notion that syntactic frames alone offer enough information to classify...

Báo cáo khoa học: "Automatic Acquisition of Script Knowledge from a Text Collection" docx

... occur one after the other and can be ex-tracted as a pair of actions. Let us first explainwhat we mean by 'action', 'pair of actions', and'sequence of actions' ... objects. A 'pair of actions'consists of two actions that occur in time order. A 'sequence of actions' can be defined as a transitiveclosure of all the pairs of actions.1. Cases ... collectionwere syntactically analyzed by using a Japanesesyntactic analyzer, KNP(Kurohashi and Nagao,1994).2.2 Extracting Pairs of ActionsIn this section, we describe three cases where twoactions...

Báo cáo khoa học: "Dependency Parsing of Japanese Spoken Monologue Based on Clause Boundaries" docx

... by a professional have been consid-ered as human valuable intellectual property andhave gathered attention. In applications, such asautomatic summarization, machine translation andso on, ... Parsing of Japanese Spoken Monologue Based on Clause BoundariesTomohiro Ohno a) Shigeki Matsubara‡Hideki Kashioka§Takehiko Maruyamaand Yasuyoshi Inagaki†Graduate School of Information ... Information Science, Nagoya University, Japan‡Information Technology Center, Nagoya University, Japan§ATR Spoken Language Communication Research Laboratories, JapanThe National Institute for Japanese...

Xem thêm