Báo cáo khoa học: "Extracting Word Sets with Non-Taxonomical Relation" potx

... thematically (non-taxonomically) related word sets among words in docu- ments by employing case-marking particles derived from syntactic analysis. We then verified the usefulness of word sets with non-taxonomical ... constructed word sets consisting of these medical terms. Then, we chose 977 word sets consisting of three or more terms from them, and removed word se...

Ngày tải lên: 17/03/2014, 04:20

... models trained to maximize likelihood: infrequent source words act as “garbage collectors”, with many target words aligned to them (the word dislike in the Model 4 alignment in Figure 2 is an ... Models 1 and 2 (where target words were generated one by one from source words independently of each other) had to be abandoned in favor of one in which each source word had to first decide how...

Ngày tải lên: 17/03/2014, 00:20

... many-to-one word alignments, where each source word is aligned with zero or one target words, and therefore each target word can be aligned with many source words. Each source word is labelled with ... tar- get word. For the example in Figure 1, the words la, de and une all receive a high translation score when paired with the. To discourage all of these French words from ali...

Ngày tải lên: 20/02/2014, 11:21

... algo- rithms for word sense discrimination. Their feature sets included morphology of target word, part of speech of contextual words, absence or presence of particular contextual words, and collocation ... discovered tight clusters called committees by grouping top n words similar with target word using average- link clustering. Then the target word was assigned to committees if t...

Ngày tải lên: 20/02/2014, 16:20

... bitext cell with an English and foreign span. There are three rule types: Terminal unary productions X → e, f, where e and f are an aligned English and for- eign word pair (possibly with one being ... 88.2 83.0 14.4 Table 2: Word alignment results on Chinese-English. Each column is a learning objective paired with an alignment family. The first row represents our best model without...

Ngày tải lên: 17/03/2014, 01:20

... are not found in WordNet. • Some kinds of words are not included in WordNet, such as proper names. To overcome all the above problems, we pro- pose a method to enrich WordNet with Roget's ... drawbacks of WordNet when applied to information retrieval by com- plementing it with Roget's thesaurus and corpus-derived thesauri. Words and rela- tions which are not included in...

Ngày tải lên: 31/03/2014, 21:20

... evaluated within two lexical expansion applications, yield- ing better results than other automatically con- structed baselines and comparable results to Word- Net. A combination with WordNet achieved ... a computer graphics conference Configuration Accuracy Accuracy Drop WordNet + Wikipedia 60.0 % - Without WordNet 57.7 % 2.3 % Without Wikipedia 58.9 % 1.1 % Table 7: RTE accuracy results...

Ngày tải lên: 08/03/2014, 00:20

... type has a dedicated null field with its own multinomial distribution over words, in- tended to model words which refer to that record type in general (e.g., the word passes for passing records). ... sequences of words of all fields generated; note that the segmentation of w provided by c = {c ij } is latent. Think of the words spanned by a record as constituting an ut- terance with a mea...

Ngày tải lên: 17/03/2014, 01:20

... English, the available WordNets are considerably smaller, like for Dutch with a 44k synset WordNet. Here, the lack of coverage creates bigger problems. A man- ual extension of the WordNets is costly. ... term 165 C then term A is also a hypernym of term C. In WordNets, hypernym relations are defined be- tween senses of words (synsets). The Dutch Word- Net (Vossen, 1998) contains 659,284 of...

Ngày tải lên: 17/03/2014, 04:20

... based on feature frequency information (ADF), for very fast word segmentation with new word detection, even given large-scale datasets with high dimensional features. In the proposed training method, ... joint model for Chinese word segmentation and new word detection. • Compared with prior work, our system achieves better accuracies on both word segmentation and new word de...

Ngày tải lên: 23/03/2014, 14:20