Báo cáo khoa học: "Novel Semantic Features for Verb Sense Disambiguation Dmitriy Dligach" ppt

... Ohio, USA, June 2008. c 2008 Association for Computational Linguistics Novel Semantic Features for Verb Sense Disambiguation Dmitriy Dligach The Center for Computational Language and Education ... @colorado.edu Abstract We propose a novel method for extracting semantic information about a verb& apos;s arguments and apply it to Verb Sense Disambiguation...

Ngày tải lên: 23/03/2014, 17:20

... WORDNET senses for supervised WSD, as we describe in section 3.1. Once the classification is done for an instance, the resulting semantic classes can be transformed into finer grained senses using ... origi- nal sense of the instance, the accuracy of the fine- grained answers will be below 100%. Figure 1 shows the performance of this trans- formed fine-grained classifier (CG) for nouns a...

Ngày tải lên: 31/03/2014, 03:20

... on lexical features (the verb before the preposition, the noun between the verb and the preposition, if any, and the noun after the preposi- tion) to a classifier trained on attachment features which ... represented by 25 lexical features and 4 combination features: Lexical Token and POS n-grams in a 2 word window around the preposition, plus the head verb in the preceding verb...

Ngày tải lên: 30/03/2014, 21:20

... sentences for each verb which use the most frequent translation are shown in Table 1. For the monolingual scenario, we use the sense tagged corpus and sense repositories provided for verbs in Senseval-3. ... of verbs. 1 Introduction Word Sense Disambiguation (WSD) is concerned with the identification of the meaning of ambi- guous words in context. For example, among th...

Ngày tải lên: 08/03/2014, 02:21

... of senses before and after sense lump- ing is 5.07 and 3.52 respectively. After sense lumping, we trained a WSD classi- fier for each noun w, by using the lumped senses in the manually sense- tagged ... sample task of SENSEVAL-2. We rely on two sources to decide on the sense classes of w: (i) The sense definitions in WordNet 1.7, which lists seven senses for the noun channe...

Ngày tải lên: 08/03/2014, 04:22

... " ;sense& quot; is not clearly defined; for instance, dictionaries may provide sense distinctions that are too fine or too coarse for the data at hand. Also, one needs to have training data for ... word sense disambiguation prob- lem, the method to be tested is presented with an ambiguous word in some context, and is asked to identify the correct sense of the word fr...

Ngày tải lên: 31/03/2014, 21:20

... contexts. For instance, frequency of the pattern The noun prep suggests noun attach- ment and of the pattern verb adverb prep suggests verb attachment for the preposition in the phrase verb noun ... selected for by the verb, such as adverbs like directly. As another example of known useful features being learned automatically, Table 8 shows the previous-context-word paraphrase...

Ngày tải lên: 20/02/2014, 04:20

... the found set of features for text classification (index- ing) for an OIR query of the first level (finds opin- ionated information) and for an OIR query of the second level (finds opinionated information ... effective kind of features for sentiment polar- 38 ity discrimination (detection) which can be used for OIR 2 . Nie et al. (2000) found that for Chinese IR the most effective...

Ngày tải lên: 20/02/2014, 12:20

... test examples. We use a number of features, including information-theoretic features previously used in unsupervised keyword extraction, as well as a novel set of features based on syntactic and ... properties of the text, or on informa- tion extracted from external knowledge repositories. 3.1 Phraseness and Informativeness We use the phraseness and informativeness features that we pre...

Ngày tải lên: 08/03/2014, 01:20

... of translation equivalents for words from the general lexicon using comparable corpora and semantic annotation that is uniform for the source and target languages. For a sentence, phrase or a ... EST and developing a parallel tool for Russian - Russian Semantic Tag- ger (RST). We have found that the USAS semantic categories were compatible with the semantic cat- egorizations o...

Ngày tải lên: 08/03/2014, 21:20