Báo cáo khoa học: "Learning Semantic Classes for Word Sense Disambiguation" pptx

... data for each word. This can be done be- cause the semantic classes are common to words unlike senses; for learning the properties of a given class, we can use the data from various words. For instance, ... that the primes are common for words, and training data can hence be reused. Yarowsky (1992) used Roget’s Thesaurus cate- gories as classes for word senses. These class...

Ngày tải lên: 31/03/2014, 03:20

... verbs. 1 Introduction Word Sense Disambiguation (WSD) is concerned with the identification of the meaning of ambi- guous words in context. For example, among the possible senses of the verb “run” ... 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. There are 32 ve...

Ngày tải lên: 08/03/2014, 02:21

... 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's arguments and apply it to Verb Sense Disambiguation (VSD). We co...

Ngày tải lên: 23/03/2014, 17:20

... 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 channel. Two senses are ... 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 man...

Ngày tải lên: 08/03/2014, 04:22

... cluster words into classes of similar words, so that one can base the estimate of a word pair's probability on the averaged cooccurrence prob- ability of the classes to which the two words ... long. However, a word is therefore modeled by the average behavior of many words, which may cause the given word& apos;s idiosyncrasies to be ig- nored. For instance, the word...

Ngày tải lên: 31/03/2014, 21:20

... Association for Computational Linguistics:shortpapers, pages 153–158, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics AM-FM: A Semantic Framework for Translation ... 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 8.3...

Ngày tải lên: 17/03/2014, 00:20

... sub-parse. For example, see the rule 962 FORM → state , λx 1 .state(x 1 ) FORM → by area , λx 1 .λx 2 .area(x 1 ,x 2 ) FORM → smallest FORM 1 FORM 2 , λx 1 .smallest(x 2 ,(FORM 1 (x 1 ),FORM 2 (x 1 , ... answer(x 1 ,FORM) FORM → smallest(x 2 ,(FORM,FORM)) FORM → state(x 1 ) FORM → area(x 1 ,x 2 ) Figure 4: Word alignment for the sentence pair in Figure 1(a). extracted for the sma...

Ngày tải lên: 17/03/2014, 04:20

... hw syntactic head word of C 5 path syntactic path from C to P 6 position whether C is to the left/right of or overlaps with P 7 firstword first word spanned by C 8 lastword last word spanned by C 9 ... predicate 2 ptype syntactic category (phrase type) of the constituent C 3 firstword first word spanned by C 4 lastword last word spanned by C 5 rsis.ptype phrase type of right sister 6 no...

Ngày tải lên: 23/03/2014, 18:20

... related semantic classes • Demonstration that dependency parser paths are inadequate for semantic classification into 7 WordNet classes on TREC news corpora • A benchmark of 10-class semantic ... for example “mp3 player” or “ipod”. We can use WordNet as training data for such classification to the extent that the training on pairs found in Word- Net and testing on pairs found...

Ngày tải lên: 20/02/2014, 12:20

... and Franz, 2006), using <keyword> <pronoun> < ;word& gt; patterns, where before and after were the keywords for temporals, and because was the key- word for causals. Word scores were assigned ... information for the temporal relation task. For C=1.0 (for all other models), and loss-function=F1 (for all models). For causals, C=0.1 and loss-function=precision/recal...

Ngày tải lên: 08/03/2014, 01:20