Báo cáo khoa học: "Tailoring Word Alignments to Syntactic Machine Translation" docx
... choice to STOP immediately is a choice to emit another foreign word from the current English word. 4. We flatten unary transitions from the tree when computing distortion probabilities. 5. Null alignments ... transducer inventory is strongly related to the effectiveness of the translation model (Galley et al., 2006). We will demonstrate that this coverage, in turn, is related to...
Ngày tải lên: 08/03/2014, 02:21
... P i,j f aligned to P m,n e , we mean all words in P i,j f are either aligned to words in P m,n e or unaligned, and vice versa. Furthermore, at least one word in P i,j f is aligned to a word in P m,n e . 4 If ... P m,n e , D, A) are valid phrase alignments, where source phrase P i,j f is 2 Here we use words instead of word indexes in categories to make the example easy to unde...
Ngày tải lên: 17/03/2014, 02:20
... pairs. In SSP, words that should be aligned to “empty” word are programmed to be aligned to real words. Unlike most word alignment methods (Och and Ney, 2003) that add “empty” word to ac- count ... advantage is the main contribution to the per- formance or not, we unpack pseudo -word into words after GIZA++ aligning. Aligned pseudo- words are unpacked into m×n word a...
Ngày tải lên: 23/03/2014, 16:20
Báo cáo khoa học: "Better Word Alignments with Supervised ITG Models" pdf
... (Chiang, 2007) machine translation system. 2 Alignment Families In order to structurally restrict attention to rea- sonable alignments, word alignment models must constrain the set of alignments ... null alignments. which to attach null alignments to a bitext cell; we address this by adapting the grammar to force a null attachment order. We introduce symbols N 00 , N 10 ,...
Ngày tải lên: 17/03/2014, 01:20
Tài liệu Báo cáo khoa học: "Integration of Speech to Computer-Assisted Translation Using Finite-State Automata" pdf
... words to a single target word. The fertility model provides the probabili- ties p(φ|e) for aligning a target word e to φ source words. In this section, we propose a method for rescoring ASR word ... large word graph. We consider MT and ASR word graphs as FSA. Then, we are able to use FSA algorithms to integrate MT and ASR word graphs. The FSA implementation of the search al...
Ngày tải lên: 20/02/2014, 12:20
Báo cáo khoa học: "From Prosodic Trees to Syntactic Trees" doc
... turn to prosodic structures that can be adjusted to correspond to syntactic structures. They usually involve the use of function words such as conjunctions, prepositions and determiners. Syntactically, ... we use to mark constituent structures. At that time, those cantillation marks were intended to record the correct way of reading or chanting the Hebrew text: how to gr...
Ngày tải lên: 08/03/2014, 02:21
Báo cáo khoa học: "A Simple Measure to Assess Non-response" docx
... value to the prefer- ences (-1, 0, 1). Now we want to interpret in some way the value that Formula (1) assigns to unanswered questions. For this purpose, we need to transform Formula (1) into a ... respond- ing to some. The same reasoning is applicable to loga092de compared to base092de for German. 5 Related Work The decision of leaving a query without response is related to t...
Ngày tải lên: 17/03/2014, 00:20
Báo cáo khoa học: "Using Mutual Information to Resolve Query Translation Ambiguities and Query Term Weighting" doc
... the word pair candidate between wl and w2 are (motorcar, air), (automobile, air), and (car, air). Here because the weight of the word pairs (automobile, air) is W, = 0.83, the word "automobile" ... query can be translated into English words with semantically similar but different words like "motorcar", "automobile", and "car". The second w...
Ngày tải lên: 17/03/2014, 07:20
Tài liệu Báo cáo khoa học: "Bilingual Sense Similarity for Statistical Machine Translation" ppt
... different words in different lan- guages, and also their dimensions I and J are not assured to be the same. Therefore, we need to first map a vector into the space of the other vec- tor, so that ... 1997), word clustering (Pantel and Lin 2002), word sense disambigua- tion (Yuret and Yatbaz 2009), etc. Use of the vector space model to compute sense similarity has also been adapt...
Ngày tải lên: 20/02/2014, 04:20
Tài liệu Báo cáo khoa học: "Quadratic-Time Dependency Parsing for Machine Translation" pdf
... features: h -word, h-pos, h -word ∧ h-pos, m -word, m-pos, m -word ∧ m-pos Bigram features: h -word ∧ m -word, h-pos ∧ m-pos, h -word ∧ h-pos ∧ m -word, h -word ∧ h-pos ∧ m-pos, m -word ∧ m-pos ∧ h -word, m -word ... Table 2. We write h -word, h-pos, m -word, m-pos to refer to head and modi- fier words and POS tags, and append a numerical value to shift the word offset either...
Ngày tải lên: 20/02/2014, 07:20