Báo cáo khoa học: "ALIGNING SENTENCES IN BILINGUAL CORPORA USING LEXICAL INFORMATION" pot

... ALIGNING SENTENCES IN BILINGUAL CORPORA USING LEXICAL INFORMATION Stanley F. Chen* Aiken Computation Laboratory Division of Applied Sciences Harvard University Cambridge, MA 02138 Internet: ... algorithm is language indepen- dent. 1 Introduction In this paper, we describe an algorithm for align- ing sentences with their translations in a bilingual corpus. Aligned...

Ngày tải lên: 31/03/2014, 06:20

... nique for aligning sentences with their translations in two parallel corpora. In addition to certain anchor points that are available in our da.ta, the only information about the sentences that ... appear are shown in Table 1. ALIGNING ANCHOR POINTS After examining the Hansard corpora, we realized that the comments laced throughout would serve as uscflll anchor points i...

Ngày tải lên: 20/02/2014, 21:20

... respectively. In addition, using the results of the alignment pro- cess, we develop a browsing and retrieval system for articles in TV newscasts and newspapers. 1 Introduction Pattern information ... 2.1 TV Newscasts In a TV newscast, events are generally reported in the following modalities: • image information, • speech information, and • text information (telops). In T...

Ngày tải lên: 17/03/2014, 07:20

... concern the testing of the scheme's efficiency at lower levels endowed with necessary bilingual information about potential delimiters. INTRODUCTION Parallel linguistically meaningful text ... stored in a database and input expressions are rendered in the target language by retrieving from the database that example which is most similar to the input. A task of crucial impo...

Ngày tải lên: 08/03/2014, 07:20

... follows. In the next section we explain the motivation behind aligning the medical ontologies. Section 3 discusses related work in ontology alignment in general and in the biomedical domain. In ... exploited by an intensive use of linguis- tic alignment methods. Use of external resources: As we are in a specific domain (medicine) and as we are not domain experts, we are in...

Ngày tải lên: 08/03/2014, 21:20

... split the data into 90% training and 10% testing sets for 5-cross validation. MOCHA and TORGO data are never combined in a single training set due to dif- fering EMA recording rates. In all cases, ... component takes into account var- ious physiological aspects of human speech production, including intergestural and in- terarticulator co-ordination and timing (Nam and Saltzman, 2003; Go...

Ngày tải lên: 16/03/2014, 23:20

... trained on MRDA using lexical and/or prosodic features, and Wiki talk pages using lexical features. 3.4 Adaptation Results For bootstrapping, we first train an initial baseline classifier using ... domain- independent features. SCL has generated much in- terest lately because of the ability to incorporate fea- tures not seen in the training data. The main idea is to use unlabeled...

Ngày tải lên: 17/03/2014, 00:20

... the information gained by giving a joint descrip- tion of a and b in terms of what they have in com- mon, compared to describing a and b separately. The relevant data in the lexical domain is ... those in Fig- ure 2.2. After an initial introductory sentence, the 3 entities were introduced in separate sentences. In all discourses, the pairs {e 1 , e 2 } and {e 2 , e 3 } could be...

Ngày tải lên: 17/03/2014, 04:20

... the bilingual lexicon of a trans- fer based, multi-lingual MT system under development. Evidence The two lexicalization patterns under analysis can be illustrated using the following three sentences ... following generalization can be made: whatever the translation P of the locative sense of an English preposition is, its path incorporating sense is translated as pot P and its...

Ngày tải lên: 23/03/2014, 20:20

... a~alysls. In short, we believe in using as much evidence from formal systemn a~ seems understandable and reasonable, to constrain what the system should be doing. The Interaetlons Finally, ... one, in which many instances of the same thin6 are done at once ~ (an in an array of parallel adders-) and another, in which the many thinks done slmul~aneously can be differe...

Ngày tải lên: 24/03/2014, 01:21