Báo cáo khoa học: "Word Sense Induction for Novel Sense Detection" pot

... and points on either side). See Dickinson and Meur- ers (2003b) for details. This work forms the basis for the DECCA system. 1 2.2 Motivation for Our Approach (2) a. NP qmp summit NP $rm Sharm NP Al$yx the ... Sheikh NP #a3 qmp summit #b1 S:1.2 NP NP^ $rm Sharm #b2 NP Al$yx The Sheikh For (2a) For (2b) For (2c) A:1.1,left #b3 NP Al$yx The Sheikh A:1.1,left #c3 $rm Sharm Figure 1...

Ngày tải lên: 17/03/2014, 00:20

... approach is to transform the abbreviation 425 into its full-form for which the current SMT system knows how to translate. For example, if the baseline system knows that the translation for “ ” is “Hong ... ∗] (1) 3.4 Translation Induction for Chinese Abbreviations Given a Chinese abbreviation and its full-form, we induce English translation entries for the abbrevia- tion by us...

Ngày tải lên: 20/02/2014, 09:20

... that the LinguaStream platform promotes the combination of purely declarative formalisms (when GATE is mostly based on the JAPE language and NOOJ focuses on a unique formalism), and allows processing ... analy- sis models and methodological concerns. Finally, when other platforms usually enforce the use of a dedicated document format, LinguaStream is able to process any XML document. On the o...

Ngày tải lên: 22/02/2014, 02:20

... discussion of the under- lying complexity, for which we unfortunately do not have space here, we give an exter- nal form of a lexical entry for some of the senses of the German verb traeumen. ... PATR-style languages is their lack of facilities for defining new abstractions and expressing linguistic generalisations not foreseen (or even foreseeable) by the language designer....

Ngày tải lên: 22/02/2014, 10:20

... compo- nent describing their functional structure. For the rule for S, for instance, we add an ele- ment describing what the SUBJECT and PRED are for. We could say that the SUBJECT is the theme ... complete formal paraphrase of (1) must include at least as much information as we have given above. In particular, the logical structure of our para- phrases contains essential inform...

Ngày tải lên: 22/02/2014, 10:20

Ngày tải lên: 08/03/2014, 01:20

... the order of hypotheses. If hypothesis 2 is aligned before hypothesis 1, the final CN will not be good. Therefore, the obser- vation in Rosti et al. (2008) that different order of hypotheses does ... align- ment of any of the hypotheses, no matter how good the alignments of other hypotheses are. For ex- ample, suppose we have the backbone “he buys a computer” and two hypotheses “he bought a...

Ngày tải lên: 17/03/2014, 01:20

... treebanks, making the inverse trans- formation for PADT more problematic than for the other treebanks. The absence of a positive effect for PADT is therefore understandable given the deeply nested ... Transformations, Parsers, and Treebanks Pseudo-projective parsing and transformations for coordination and verb groups are instances of the same general methodology: 1. Apply a tree tran...

Ngày tải lên: 17/03/2014, 04:20

... lemma with a novel sense, poster, is also the lemma with the least-frequent novel sense. This result is unsur- prising as our novelty score will be higher for higher-frequency novel senses. The ... Tugwell, 2002) 10 for each of these lemmas in the BNC and ukWaC for collocates that likely correspond to the novel sense; we exclude any lemma for which we find evidence of the n...

Ngày tải lên: 17/03/2014, 22:20

... 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 verbs with be- tween ... simple, containing only the sentence identifier and the sense of the verb in that sentence, i.e. sense( snt, sense) : sense( snt 1 ,voltar). sense( snt 2 ,ir). … Based on the...

Ngày tải lên: 08/03/2014, 02:21