Báo cáo khoa học: "Improving Domain-Specific Word Alignment for Computer Assisted Translation" potx

... generate2 is called. • If a link word is found, an autonomous word is searched for whose root node can be unified with the left ( substitution )nodeofthelink word. Letting the word s root and the terminal ... modi- fying the head word. And such a phrase in its turn can semantically modify an autonomous word by way of attaching a connective to it’s right, forming a phrase, or inflecti...

Ngày tải lên: 08/03/2014, 05:20

... tool for creating word alignments, one design objective was to minimize mouse travel required to align words. The inter- face therefore has no ‘link words’ button but uses mouse clicks on words ... visualization and ma- nipulation of word- and phrase-level alignments of parallel text. Unlike most other tools for manual word alignment, it relies on dynamic markup to visualize alignm...

Ngày tải lên: 20/02/2014, 09:20

... candidate. This information is de- rived before word alignment model training and will act as soft constraints that need to be respected dur- ing training and alignments. For a given word pair, the ... source words as rows and target words as columns and uses statis- tics from word alignment training to form word pair co-occurrence association. More specifically, we regard each t...

Ngày tải lên: 20/02/2014, 12:20

... methods for word alignment. In addition, we improve the word alignment results by combining the results of the two semi-supervised boost- ing methods. Experimental results on word alignment ... get the word alignment results shown in table 2. For all of the methods in this table, we perform bi-directional (source to target and target to source) word alignment, and obt...

Ngày tải lên: 08/03/2014, 02:21

Ngày tải lên: 20/02/2014, 04:20

... recognize words beyond their vocab- ulary, many of which are information rich terms, like named entities or foreign words. Hybrid word/ sub -word systems solve this problem by adding sub -word units ... coherence. Hybrid word/ sub -word recognizers can produce a sequence of sub -word units in place of OOV words. Ideally, the recognizer outputs a complete word for in-vocabulary (IV)...

Ngày tải lên: 20/02/2014, 04:20

... data. the 100K -word CMU pronunciation dictionary. For all models, we allowed one non-dictionary word per utterance, but only for lines longer than four words. For allowable non-dictionary words, SONIC’s ... to every mismatch- ing word sequence between the utterance-aligned manual and ASR transcripts. For every mismatching sequence of words, a set 766 ⋄ for every sequence of wo...

Ngày tải lên: 20/02/2014, 07:20

... more than one word, this process is first carried out for the first new word in the hypothe- sis. It is then repeated for the remaining words in the hypothesis extension. Once the final word in the ... lat- tice nodes represent multi -word target language phrases. For such translation lattice nodes, δ will be called once for each newly hypothesized target language word in the nod...

Ngày tải lên: 20/02/2014, 04:20

... length. Single source and target words are denoted by and respectively, where and . We will also use a special single -word block set which contains only blocks for which . For the experiments in this ... is defined for each event in the list . The average size of is successor blocks. If we were to compute a Viterbi block alignment for a training sentence pair, each block in this bl...

Ngày tải lên: 20/02/2014, 15:20

... corpus. This additional information could be: Simple context information: information of the words surrounding the word pair; Syntactic information: part-of-speech in- formation, syntactic constituent, ... position . The alignment may contain align- ments with the ‘empty’ word to ac- count for source words that are not aligned to any target word. In (statistical) alignment models ,...

Ngày tải lên: 20/02/2014, 18:20