generalizing word lattice translation

Strategies to deal with non - equivalence at word level in translation

Strategies to deal with non - equivalence at word level in translation

... as translation by a more general word and translation by cultural substitution while their English classmates did not use the following strategies: translation using a loan word or a loan word ... to solve non-equivalence. Giménez (2005) notes that translation using a related word; translation by paraphrase using unrelated words and translation by omission seem to be favored by Spanish ... Vietnamese word is impossible. Using Vietnamese words “sự tới dự”, the translation will sound non –Vietnamese. Pharaphasing it by a combination of Vietnamese items has brought out an acceptable translation...

Ngày tải lên: 10/04/2013, 10:37

57 1,9K 14
Tài liệu Báo cáo khoa học: "A Ranking-based Approach to Word Reordering for Statistical Machine Translation" doc

Tài liệu Báo cáo khoa học: "A Ranking-based Approach to Word Reordering for Statistical Machine Translation" doc

... the word order in target language. To this end, we propose a simple but effective ranking-based ap- proach to word reordering. The ranking model is automatically derived from the word aligned ... the paper. 2 Word Reordering as Syntax Tree Node Ranking Given a source side parse tree T e , the task of word reordering is to transform T e to T  e , so that e  can match the word order in ... arcs for dependency tree; word alignment links are lines without arrow between the source and target sentences. parse tree, we can obtain the same word order of Japanese translation. It is true...

Ngày tải lên: 19/02/2014, 19:20

9 616 0
Tài liệu Báo cáo khoa học: "A Discriminative Syntactic Word Order Model for Machine Translation" pdf

Tài liệu Báo cáo khoa học: "A Discriminative Syntactic Word Order Model for Machine Translation" pdf

... Introduction The machine translation task can be viewed as con- sisting of two subtasks: predicting the collection of words in a translation, and deciding the order of the predicted words. For some language ... in Machine Translation We apply our model to machine translation by re- ordering the translation produced by a baseline MT system. Our baseline MT system constructs, for each target translation ... described in Section 4.1 Word Bigram: Word bigrams of the target sen- tence. Examples from Figure 2: “kore”+“niyori”, “niyori”+“roku”. DISP: Displacement feature. For each word posi- tion in the...

Ngày tải lên: 20/02/2014, 12:20

8 404 0
Tài liệu Báo cáo khoa học: "Term-list Translation using Mono-lingual Word Co-occurrence Vectors*" doc

Tài liệu Báo cáo khoa học: "Term-list Translation using Mono-lingual Word Co-occurrence Vectors*" doc

... complicated. Some translation alternatives are polysemous in the target language. If a polysemous word has a very general meaning that co-occurs with various words, then this word is more likely ... multi-dimensional vector space, called WORD SPACE (Schuetze, 1997) for defin- ing the coherence of words. The starting point of WORD SPACE is to represent a word with an n- dimensional vector ... many times the word wi occurs close to the word. For simplicity, we consider w~ and wj to occur close in context if and only if they appear within an m -word distance (i.e., the words occur...

Ngày tải lên: 20/02/2014, 18:20

5 338 0
Tài liệu Báo cáo khoa học: " Word Translation Disambiguation Using Bilingual Bootstrapping" doc

Tài liệu Báo cáo khoa học: " Word Translation Disambiguation Using Bilingual Bootstrapping" doc

... correct Chinese translation of the ambiguous English word, given an English sentence which contains the word. Word translation disambiguation is actually a special case of word sense disambiguation ... an English word usually has several Chinese words as translations (cf., Figure 5). As a translation dictionary, we used the HIT dictionary, which contains about 76000 Chinese words, 60000 ... Experiment 2: Yarowsky’s Words We also conducted translation on seven of the twelve English words studied in (Yarowsky, 1995). Table 5 shows the list of the words. For each of the words, we extracted...

Ngày tải lên: 20/02/2014, 21:20

9 480 0
Tài liệu Báo cáo khoa học: "Bilingually Motivated Domain-Adapted Word Segmentation for Statistical Machine Translation" pptx

Tài liệu Báo cáo khoa học: "Bilingually Motivated Domain-Adapted Word Segmentation for Statistical Machine Translation" pptx

... iterations). 4 Word Lattice Decoding 4.1 Word Lattices In the decoding stage, the various segmentation alternatives can be encoded into a compact rep- resentation of word lattices. A word lattice G ... designated the “end node”. An example of word lattices for a Chinese sentence is shown in Figure 2. 4.2 Word Lattice Generation Previous research on generating word lattices re- lies on multiple monolingual ... utilisation of word lattice decoding. 4.3 Phrase-Based Word Lattice Decoding Given a Chinese input sentence c J 1 consisting of J characters, the traditional approach is to determine the best word segmentation...

Ngày tải lên: 22/02/2014, 02:20

9 236 0
Tài liệu Báo cáo khoa học: "A Word-to-Word Model of Translational Equivalence" pptx

Tài liệu Báo cáo khoa học: "A Word-to-Word Model of Translational Equivalence" pptx

... two-class word- to -word model of translational equivalence from 13 million words of the Canadian Hansards, aligned using the method in (Gale & Church, 1991). One class repre- sented content -word ... all candidate translations. The correct translations of a word that has several correct trans- lations will be assigned a lower probability than the correct translation of a word that has ... u and v being mutual translations, for all u and v: B(ku,vln<,,,,, ),+) L(u,v) = B(ku,vln~,v, A_ ) . (61 4 Class-Based Word- to -Word Models In the basic word- to -word model, the hidden...

Ngày tải lên: 22/02/2014, 03:20

8 456 0
Báo cáo khoa học: "Tailoring Word Alignments to Syntactic Machine Translation" docx

Báo cáo khoa học: "Tailoring Word Alignments to Syntactic Machine Translation" docx

... compat- ibility with the word alignment. For a constituent c of t, we consider the set of source words s c that are aligned to c. If none of the source words in the lin- ear closure s ∗ c (the words between ... VBN NNS DT AUX The jobs are career oriented . les emplois sont axés sur la carrière . . Legend Correct proposed word alignment consistent with human annotation. Proposed word alignment error inconsistent with human annotation. Word alignment constellation that renders ... statistical machine translation. In Proceedings of the Conference on Theoretical and Methodological Issues in Machine Transla- tion. Robert C. Moore. 2005. A discriminative framework for bilin- gual word alignment....

Ngày tải lên: 08/03/2014, 02:21

8 287 1
Báo cáo khoa học: "Word Sense Disambiguation Improves Statistical Machine Translation" docx

Báo cáo khoa học: "Word Sense Disambiguation Improves Statistical Machine Translation" docx

... recast as a word translation task. The 33 No. of All test sentences +1 from Collins sign-test words in No. of % match No. of % match WSD translations WSD translations used reference WSD translations ... contains the word e 3 (“every”), it is noted as a candidate translation. Later, it is determined that the most number of words any candidate translation has is two words. Since among all the 2 -word candi- date ... extra English words pro- vided by Hiero+WSD, though appropriate, do not 39 translation choices for a word w were defined as the set of words or phrases aligned to w, as gathered from a word- aligned...

Ngày tải lên: 08/03/2014, 02:21

8 285 0
Báo cáo khoa học: "Multi-Engine Machine Translation Guided by Explicit Word Matching" docx

Báo cáo khoa học: "Multi-Engine Machine Translation Guided by Explicit Word Matching" docx

... original translations are considered in principle to be word synchronous in the sense that selecting a word from one original translation normally implies “marking” a corre- sponding word in ... score with each word in a synthetic translation based on the confidence of the system from which it originated. If the word was contributed by several different original translations, we ... hypothesis translation with the best score is selected as the final output of the MEMT combination. 2.1 The Word Alignment Matcher The task of the matcher is to produce a word- to -word alignment...

Ngày tải lên: 08/03/2014, 04:22

4 228 0
Báo cáo khoa học: "Automatic Identification of Word Translations from Unrelated English and German Corpora" pot

Báo cáo khoa học: "Automatic Identification of Word Translations from Unrelated English and German Corpora" pot

... two words ahead of another word B, a second vector for the case that word A is one word ahead of word B, a third vector for A directly following B, and a fourth vector for A following two words ... 100 Ger- man test words. For each of these test words, the top five translations as automatically generated are listed. In addition, for each word its ex- pected English translation from the ... of test words. 4 This means that alternative translations of a word were not considered. Another approach, as conducted by Fung & Yee (1998), would be to consider all possible translations...

Ngày tải lên: 08/03/2014, 06:20

8 438 0
Báo cáo khoa học: "Identifying Word Translations in Non-Parallel Texts" potx

Báo cáo khoa học: "Identifying Word Translations in Non-Parallel Texts" potx

... algorithms for sentence and word- alignment allow the automatic iden- tification of word translations from paxalhl texts. This study suggests that the identi- fication of word translations should also ... co-occurrences of German word pairs in the German corpus. As a starting point, word order in the two matrices was chosen such that word n in the German matrix was the translation of word n in the English ... increases the likelihood that the English and German words axe in corresponding order. Word n in the English matrix is then the translation of word n in the German matrix. 3 Simulation A simulation...

Ngày tải lên: 08/03/2014, 07:20

3 219 0
Báo cáo khoa học: "Detecting Highly Confident Word Translations from Comparable Corpora without Any Prior Knowledge" doc

Báo cáo khoa học: "Detecting Highly Confident Word Translations from Comparable Corpora without Any Prior Knowledge" doc

... confidence of a translation pair. In other words, if the most prob- able translation candidate for a source word w S 1 is a target word w T 2 and, vice versa, the most prob- able translation candidate ... the list. In other words, if the first translation candidate for the source word isola is the target word island, and, vice versa, the first translation candidate for the target word island is isola, ... contains a word w T s,high , the final translation candidate of the source word w S s . If the list F inal s is not empty, the final re- sult of this process will be the cross-language word translation...

Ngày tải lên: 08/03/2014, 21:20

11 290 0

Bạn có muốn tìm thêm với từ khóa:

w