Báo cáo khoa học: "Bilingual-LSA Based LM Adaptation for Spoken Language Translation" pot

... the adaptation of a LM from one language based on the adaptation text of another language. In statisticalmachine translation (SMT), one approach is to ap-ply LM adaptation on the target language ... 2007.c2007 Association for Computational LinguisticsBilingual-LSA Based LM Adaptation for Spoken Language TranslationYik-Cheung Tam and Ian Lane and Tanja SchultzInterACT, Language Technologies ... unigram LM, which is ﬁnally integratedinto the background N-gram LM using marginal adaptation (Kneser et al., 1997)In this paper, we propose a framework to per-form LM adaptation across languages,...

Tài liệu Báo cáo khoa học: "ADP based Search Algorithm for Statistical Machine Translation" docx

... structures in both languages. In (Tillmann et al., 1997b) text transformations in the source language are used to adapt the word or- dering in the source strings to the target language grammar. ... additional parameter into the recursion formula for DP. In the following, we will explain this method in detail. 2.3 Recursion Formula for DP In the DP formalism, the search process is described ... A DP based Search Algorithm for Statistical Machine Translation S. Nieflen, S. Vogel, H. Ney, and C. Tillmann Lehrstuhl fiir Informatik VI RWTH Aachen - University...

Tài liệu Báo cáo khoa học: "Exploiting Non-local Features for Spoken Language Understanding" pptx

... performance on thestatistical spoken language understanding(SLU) problem. The statistical natural language parsers trained on text performunreliably to encode non-local informa-tion on spoken ... selec-tion algorithm is very efﬁcient for both perfor-mance and time complexity.2 Spoken Language Understanding as aSequential Labeling Problem2.1 Spoken Language UnderstandingThe goal of SLU ... crite-rion based on ME (the unstructured model) is bet-ter than CRF (the structured model) not only for time cost but also for the performance on our ex-periment4. This result shows that local informa-tion...

Báo cáo khoa học: "Making Tree Kernels practical for Natural Language Learning" potx

... Italymoschitti@info.uniroma2.itAbstractIn recent years tree kernels have been pro-posed for the automatic learning of natural language applications. Unfortunately, theyshow (a) an inherent super linear complex-ity ... recent years tree kernels have been shown tobe interesting approaches for the modeling of syn-tactic information in natural language tasks, e.g.syntactic parsing (Collins and Duffy, 2002), rela-tion ... such hypothe-sis, we measured the impact of the algorithm onthe time required by SVMs for the learning ofabout 122,774 predicate argument examples anno-tated in PropBank (Kingsbury and Palmer,...

Báo cáo khoa học: "Robust, Finite-State Parsing for Spoken Language Understanding" pdf

... Robust, Finite-State Parsing for Spoken Language Understanding Edward C. Kaiser Center for Spoken Language Understanding Oregon Graduate Institute PO Box 91000 ... rely on corpus -based language modeling, which is a large and expensive task. In many practical uses of spoken language technology, like using simple structured dialogues for class room instruction ... also offers the ability to perform the full-context statistical parsing that Briscoe has called for. Chelba and Jelinek (1999) use a struc- tural language model (SLM) to incorporate the longer-range...

Tài liệu Báo cáo khoa học: "Phrase-Based Backoff Models for Machine Translation of Highly Inﬂected Languages" docx

... (Zitouni et al., 2003) for language modeling and by (Gildea, 2001) for semantic rolelabeling. (Resnik et al., 2001) used backoff trans-lation lexicons for cross -language information re-trieval. ... improvements are signiﬁcant almostall training conditions for both languages; BLEUimprovements are signiﬁcant in all conditions for Finnish and for the two smallest training sets for German. The effect ... applied before training and after gener-ating the output in the target language. Normaliza-tion of English/German inﬂectional morphologyto base forms for the purpose of word alignment isperformed...

Báo cáo khoa học: "Corpus-based interpretation of instructions in virtual environments" pot

... for developing con-versational systems for new domains.This paper proposes a fully automated approachto interpreting natural language instructions to com-plete a task in a virtual world based ... computing for perception -based decision processing and analysis: Web -based BISC-DSS. In Masoud Nikravesh, Lotﬁ Zadeh, and JanuszKacprzyk, editors, Soft Computing for InformationProcessing and ... world, based on what humans did when given similar in-structions in the past.2 Corpora situated in virtual worldsOur environment consists of six virtual worlds de-signed for the natural language...

Báo cáo khoa học: "HAL-based Cascaded Model for Variable-Length Semantic Pattern Induction from Psychiatry Web Resources" pdf

... in-formation indicates that the k words are more likely to form a semantic pattern of length k. Here the length k also ranges from 2 to 4. For each k, we compute the mutual information for ... characteris-tics of language. For this consideration, we in-stead refer to the web resources, or more restrict-edly, the psychiatry web resources as our knowl-edge resource. Corpus -based approaches ... large corpora with annotated information to obtain more reliable parameters. For some ap-plication domains, such annotated corpora may be unavailable. Therefore, we propose the use of web...

Báo cáo khoa học: "XML-Based Data Preparation for Robust Deep Parsing" pptx

... P=’JJ’ retrospective /WW P=’NN’ LM= ’study’ study /W W P=’VBD’ LM= ’be’ was /WW P=’VBN’ LM= ’conduct’ conducted /W W P=’IN’ by /W W P=’NN’ LM= ’chart’ chart /WW P=’NNS’ LM= ’review’ reviews /W W P=’IN’ ... tag infor-mation with lexical entries preserves all informa-tion in the lexical entries, including inﬂectionaland subcategorisation information. The preserva-tion of subcategorisation information ... POStag information with the existing ANLT lexical re-sources. Our view is that POS tag information for content words (nouns, verbs, adjectives, adverbs)is usually reliable and informative,...

Báo cáo khoa học: "Web-based LRT services for German" ppt

... XML based data formats were developed beside the TCF format (for example, an encoding for lexi-con based data). In order to avoid any confusion of element names between these different for- mats, ... exchange format, which is preferably based on widely accepted formats already in use (UTF-8, XML). WebLicht uses the RESTstyle API and its own XML -based data exchange for- mat (Text Corpus Format, ... WebLicht's own data exchange format TCF. 5 The TCF Format The D-SPIN Text Corpus Format TCF (Heid et al, 2010) is used by WebLicht as an internal data exchange format. The TCF format allows the combination...

Xem thêm