Báo cáo khoa học: "Where''''''''s the Verb? Correcting Machine Translation During Question Answering" pot

... Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pages 333–336, Suntec, Singapore, 4 August 2009. c 2009 ACL and AFNLP Where's the Verb? Correcting Machine Translation During Question ... any other translation record, then the VTG will not be processed. To do this, our system first builds verb phrase tables from relevant documents and then uses the tab...

Ngày tải lên: 31/03/2014, 00:20

... Furthermore, as they often require the overexpression and ⁄ or tagging of the RNA degradosome components, the complexes formed may not truly represent what is occurring in the cell. In view of these ... or whether parts of the ribosome or, indeed, other protein com- plexes co-electrophorese with the degradosome; this is likely when one considers the abundance of these pro- teins...

Ngày tải lên: 29/03/2014, 21:20

... of the rule (a particular phrase pair in the training corpus), the context will be the words instantiating the non-terminals. In turn, the context for the sub-phrases that instantiate the ... esti- mating the translation model. The second one is the small data condition where only the FBIS 3 corpus is used to train the translation model. We trained two langu...

Ngày tải lên: 20/02/2014, 04:20

... each hypothesis expansion, our decoder generates the following information for the new hypothesis h: • a partial translation x; • a coverage set of input words c; • a translation score σ. In the ... implementation supports the case of phrases of any length. Line 3 determines whether the translation hypothesis is complete, in which case it explicitly builds the graph G and 77...

Ngày tải lên: 20/02/2014, 07:20

... processes. 1 Background The LOGON projects aims at building an exper- imental machine translation system from Norwe- gian to English of texts in the domain of hiking in the wilderness (Oepen et ... hy- potheses. In a nutshell, a central research question in LOGON is to what degree state-of -the- art ‘deep’ NLP resources can contribute towards a precision MT system. We hope to enga...

Ngày tải lên: 20/02/2014, 12:20

... the test set (subset with OOV words). D in Figure 2), the backoff model produced a good translation, but the translation was a para- phrase rather than an identical match to the ref- erence translation. ... w t−2 )p BO (w t |w t−1 ) otherwise where p ML denotes the maximum-likelihood estimate, c denotes the count of the triple (w i , w i−1 , w i−2 ) in the training data, τ...

Ngày tải lên: 22/02/2014, 02:20

... evaluation The evaluation of the goodness of fit for the curve families is presented in Table 3. The average values of the root mean- squared error and the average residuals across all the learning ... give a measure of the closeness of the curve fit using only the initial points with the gold fit using all the points; the value of this gold fit at 10K is not necessarily...

Ngày tải lên: 07/03/2014, 18:20

... text are the vocabulary used, the length of the sentences, the syntactic structures present in the text, and the usage of discourse markers. One effort to create a simple version of English at the ... sentences. On the other hand, we observe some differences in the percentage of cases in which the systems de- cide to produce a sentence identical to the input. In 22 perce...

Ngày tải lên: 07/03/2014, 18:20

... composes a new hypothesis using smaller hypotheses in the search spaces           . These rules further extend     with hypotheses generated by the HM decoder itself. ... HM decoding, in which the translations surrounded by the dotted lines are newly generated hypotheses. Hypotheses light-shaded come from a phrase-based system, and hypotheses dark- shade...

Ngày tải lên: 07/03/2014, 22:20

... score of the F+M hypothesis -26.67. This could be the reason why the baseline selects the word “was” instead of “is”. As can be seen, there is an- other “is” in the preceding context of the word ... enhanced with the MI trigger model (F+M) selects the former while the baseline selects the latter. The forward language model score for the baseline hypothesis is -26.41, w...

Ngày tải lên: 07/03/2014, 22:20