Báo cáo khoa học: "Contextual Dependencies in Unsupervised Word Segmentation∗" docx

... mis-analyzes fre- quently occurring words. In particular, many of these words occur in common collocations such as what’s that and do you, which the system inter- prets as a single words. It turns out that ... discovering word bound- aries in continuous text or speech, is of interest for both practical and theoretical reasons. It is the first step of processing orthographies without ex...

Ngày tải lên: 23/03/2014, 18:20

... word in the sentence (the pre-x or post-x word) . Without attempting to rearrange the word order of the Russian sen- tence, one can obtain the following by compari- son of each ambiguous word ... meaning, and that the barest kind of routine comparison re- sults in a high (although not absolute) degree of accuracy in the determination of meaning. Non-structural clarificat...

Ngày tải lên: 23/03/2014, 13:20

... but it should be borne in mind by those linguists who are seriously interested in developing machine translation as a concrete reminder that, for every increase in linguistic analytic complexity, ... a feminine def- inite article or as a feminine accusative pro- noun. We assume that la has already been monolingually placed within a set of monolin- gual grammatical systems, inclu...

Ngày tải lên: 19/02/2014, 19:20

... dialogues, we distinguish between task level goals and plans (e.g., investing, traveling), and communicative level inten- tions and speech acts (e.g., explaining, re- questing information) [2,6,11]. ... (sentence 14). In the case of inconsistent values (sentence 20), a subplan is inserted for explaining why the value is inconsistent and asking the user to change something in order...

Ngày tải lên: 22/02/2014, 10:20

... the first joint model for word segmen- tation, POS tagging, and dependency parsing for Chinese. Based on an extension of the incremental joint model for POS tagging and dependency pars- ing (Hatori ... Model 3.1 Incremental Joint Segmentation, POS Tagging, and Dependency Parsing Based on the joint POS tagging and dependency parsing model by Hatori et al. (2011), we build our joint model to s...

Ngày tải lên: 07/03/2014, 18:20

... the time. 1 Introduction Incorrect writings in Chinese are related to our under- standing of the cognitive process of reading Chinese (e.g., Leck et al., 1995), to our understanding of why people ... Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pages 25–28, Suntec, Singapore, 4 August 2009. c 2009 ACL and AFNLP Capturing Errors in Written Chinese Words Chao-Lin Liu 1...

Ngày tải lên: 17/03/2014, 02:20

... performance against a baseline, 1c 1word, that assigns the whole graph to a single cluster and no graph clustering is performed. 1c 1word corresponds to a relevant SemEval-2007 baseline (Agirre and ... which the meaning of a MWE can be predicted by com- bining the meanings of its components. Unlike syntactic compositionality (e.g. by and large), se- mantic compositionality is continuous (Bal...

Ngày tải lên: 23/03/2014, 17:20

Ngày tải lên: 31/03/2014, 17:20

... massively paral- lel marking passing, which is computationally efficient and is more powerful in high-level processing involv- ing variable-binding, structure building, and constraint propagations ... [21]). Understanding of an input sentence (or speech input in ~/iDMTRANS PLUS) is defined as changes made in a memory network. Parsing and natural language understanding in these...

Ngày tải lên: 01/04/2014, 00:20

... entries from CELEX that are compound words containing dashes are dis- carded instead of being split into parts, since many of these are not in fact Dutch words. 2 5 Experimental design We use ... lefthyphenmin and last righthyphenmin letters of each word. For 1 The single word with more than two alternative hyphenations is “invalid” whose three hyphenations are in- va-lid in- val-id an...

Ngày tải lên: 20/02/2014, 04:20