Báo cáo khoa học: "A Comparison and Semi-Quantitative Analysis of Words and Character-Bigrams as Features in Chinese Text Categorization" potx

... both used as features in Chinese text process-ing tasks, but no systematic comparison or analysis of their values as features for Chinese text categorization has been re-ported heretofore. We ... LinguisticsA Comparison and Semi-Quantitative Analysis of Words and Character-Bigrams as Features in Chinese Text Categorization Jingyang Li Maosong Sun Xian Zhang National Lab. of Intelligent ... 1 Introduction1 Because of the popularity of the Vector Space Model (VSM) in text information processing, document indexing (term extraction) acts as a pre-requisite step in most text information...

Báo cáo khoa học: " A Tool for Error Analysis of Machine Translation Output" doc

... informa-tion, and then an item for each menu containing:• The name of the menu• A list of menu items, containing:– Display name– Internal name (used in annotation ﬁle, and internally in BLAST)– ... especially in combination with a part -of- speech analysis (Popovi´c et al., 2006).Human evaluation is also often quantitative, forinstance in the form of estimates of values such as adequacy and ... highlight-ing similarities between the MT output and a refer-ence. Its modular design allows easy integration of new modules for preprocessing. BLAST has threeworking modes for handling error...

Báo cáo khoa học: "A System for Semantic Analysis of Chemical Compound Names" pdf

... these tasks. Krauthammer and Nenadic (2004)divide the identiﬁcation task into the subtasks of term recognition (marking the interesting words in a text) , term classiﬁcation (classifying them ... ver-tices and its set of edges. Therefore, the domain of a graph consists of a set of possible vertices, in ourcase for the atoms, and possible edges, in our casefor the bonds. The constraints can ... Classifying Names of Chemi-cal Compounds with CHEMorph. In Sophia Anani-adou and Juliane Fluck, editors, Proceedings of theSecond International Symposium on Semantic Min-ing in Biomedicine,...

Báo cáo khoa học: "A Comparison of Document, Sentence, and Term Event Spaces" potx

... ab-stracts, and the full -text IDF (see section 4.4). 4.4 Abstract vs full text comparison Although abstracts are often easier to obtain, the availability of full -text documents continues to increase. ... This comparison reflects a previous analysis comprising a random sample of 193 words from a 50 million word corpus of 85,432 news articles (Church and Gale 1999). Church and Gale’s analysis of ... where N was the number of documents in each journal and ni was the number of times the stemmed term appears in the text of that journal. 4 Results and Discussion The 100830 full text documents...

Báo cáo khoa học: "A Comparison of Loopy Belief Propagation and Dual Decomposition for Integrated CCG Supertagging and Parsing" potx

... Computational Linguistics.J. R. Finkel, C. D. Manning, and A. Y. Ng. 2006. Solv-ing the problem of cascading errors: ApproximateBayesian inference for linguistic annotation pipelines. In Proc. of EMNLP.J. ... Forest Reranking: Discriminative pars-ing with Non-Local Features. In Proceedings of ACL-08: HLT.W. Jiang, L. Huang, Q. Liu, and Y. L¨u. 2008. A cas-caded linear model for joint Chinese word ... and part -of- speech tagging. In Proceedings of ACL-08: HLT.N. Komodakis, N. Paragios, and G. Tziritas. 2007.MRF optimization via dual decomposition: Message-passing revisited. In Proc. of Int....

Báo cáo khoa học: "A Comparison of Head Transducers and Transfer for a Limited Domain Translation Application" pptx

... translation. In the case of text translation for publishing, it is reasonable to adopt economic measures of the Fei Xia Department of Computer and Information Science University of Pennsylvania ... additional source of counts used in the transfer system was an unsupervised training method in which 13000 training utterances were translated from English to Chinese, and then back again; the derivations ... functions, including likelihood ratios (cf. Dunning 1993), make use of both positive and negative instances of performing a task. Here we take a positive instance to be the derivation of a "'correct"...

Báo cáo khoa học: "A comparison of clausal coordinate ellipsis in Estonian and German: Remarkably similar elision rules allow a language-independent ellipsis-generation module" pot

... Nor do we deal with recasts of clausal coordina-tions as coordinate NPs (e.g., John likes skating and Peter likes skiing becoming John and Peter like skating and ski-ing, respectively). Presumably, ... and Pseudogapping because they involve the generation of pro-forms instead of, or in addi-tion to, the ellipsis proper. For example, John laughed, and Mary did, too—a case of VP Ellipsis—includes ... example in (12)). (12) Minu naine soovib osta autot ja minu poeg soo-vibg ostagg mootorratast Meine Frau will ein Auto kaufen und mein Sohn willg ein Motorrad kaufengg In Subgapping,...

Tài liệu Báo cáo khoa học: "A Comparison of Alternative Parse Tree Paths for Labeling Semantic Roles" ppt

... Aligning arguments to parse trees nodes in a training / testing corpus We began our investigation by creating a training and testing corpus of 400 sentences each contain-ing an inflection of ... ate:eat,V,i↓He:he,N,s Minipar B: A second parse tree path encoding was generated from Minipar parses that relaxes some of the constraints used in Minpar A. In- stead of using all the information contained at ... include complementizers such as ‘that’ in ‘be-lieve that’ in an argument. (3) Do include prepo-sitions such as in in ‘believe in . (4) When in doubt, assume phrases attach locally. Using...

Tài liệu Báo cáo khoa học: "A SPEECH-FIRST MODEL FOR REPAIR DETECTION AND CORRECTION" docx

... found cases of 'lengthened' intonational phrases in repair intervals, as illustrated in the single-phrase reparandum in (8), where the corresponding fluent ver- sion of the reparandum ... acoustic-phonetic and prosodic analysis of a corpus of repairs in spontaneous speech, indicating that reparanda offsets end in word fragments, usually of (in- tended) content words, and that these ... repair processing algorithms. Investigation of repair phrasing in other corpora covering a wider variety of genres is needed in order to assess the generality of these findings. For exam-...

Tài liệu Báo cáo khoa học: "A Pattern Matching Method for Finding Noun and Proper Noun Translations from Noisy Parallel Corpora" doc

... better initializing basis for EM methods. It has also shown promise for finding noun phrases in English and Chinese, as well as finding new Chinese words which were not tokenized by a Chinese ... such as follows: • finding Chinese words: Chinese texts do not have word boundaries such as space in English, therefore our text was tokenized into words by a statistical Chinese tokenizer (Fung ... position binary vector for each word using the anchor points. The re- maining nouns and proper nouns in English and all words in Chinese are represented in a non- linear segment binary vector...

Xem thêm