Báo cáo khoa học: "Active Sample Selection for Named Entity Transliteration" pptx

... pages 53–56, Columbus, Ohio, USA, June 2008. c 2008 Association for Computational Linguistics Active Sample Selection for Named Entity Transliteration Dan Goldwasser Dan Roth Department of Computer ... using an active sample selection scheme. The sample selection process is guided by the Suf- ficient Spanning Features criterion (SSF) introduced in section 2.2, to identify...

Ngày tải lên: 31/03/2014, 00:20

... Data point selection The key idea in our experiments is that we can use a simple form of instance weighting, similar to what is often used for correcting sample selection bias or for domain adaptation, ... the Association for Computational Linguistics:shortpapers, pages 682–686, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Data point sel...

Ngày tải lên: 17/03/2014, 00:20

... acquire more over time: we in- tend for it to generalize and encapsulate best practices, and serve as a testbed for new practices. Dyna is now be- ing used for parsing, machine translation, morphological analysis, ... probabilities, which permits heuristic early stopping before the agenda is empty. With viterbi values, it amounts to uniform-cost search for the best parse, and an item’...

Ngày tải lên: 20/02/2014, 16:20

... longer afford to waste human time and effort building manually these ever changing and in- complete databases or design language specific applications to solve this problem. The need for an automatic ... brackets). For average size texts (e.g. the Written Ques- tions), these words account for about 5% of the total (about 3k words / text). This number varies according to language similar...

Ngày tải lên: 20/02/2014, 18:20

Ngày tải lên: 08/03/2014, 01:20

... predicates like force generally introduce E-type SEs: (7) I forced [John to run the race with me]. (8) * I forced [John to know French]. The feature force-PREV is extracted if a member of the force-type ... punctuation WT W (see above) POSONLY POS tag for each word WORD/POS word/POS pair for each word WTL WT (see above) FORCEPRED T if clause (or preceding clause) contains force predicate...

Ngày tải lên: 08/03/2014, 02:21

... Carlo approximation. We collect samples of the vari- ables over which we wish to marginalize but for which we cannot compute closed-form integrals. We then approximate the marginal probabilities for undeciphered ... Kondrak, 2009). These methods typically rely on informa- tion that is unknown in a typical deciphering sce- nario (while being readily available for living lan- guages). Fo...

Ngày tải lên: 17/03/2014, 00:20

... it still performs well above random chance predictions, which, for the given average of 4 items per ranking, is about 25% for best and worst ranking predictions, and about 8.33% for both. Again, ... single measure by implementing a weighted harmonic mean, for which the weighting factor can be adjusted for optimizing the metric performance. The rest of the paper is organized a...

Ngày tải lên: 17/03/2014, 00:20

... compare SIMR's performance on these language pairs to the performance of other algorithms, Table 2 shows that the performance on other language pairs is no worse than performance on French/English. ... significant part of the port- ing effort, if no such program is available in advance. The effort may be lessened, however, by the realiza- tion that it is acceptable for the tokeni...

Ngày tải lên: 17/03/2014, 23:20

... impor- tant parts ofthe message. By structuring information this way, parentheticals make it easier for readers to decode the message conveyed by a text. Consider for example the following message that ... (Joshi, 2004). The input to the generator is a set of rhetorical relations and semantic formulas. For each formula the system selects a set of trees from the grammar, resulting in a n...

Ngày tải lên: 23/03/2014, 17:20