Báo cáo khoa học: "Detecting Compositionality in Multi-Word Expressions" doc

... 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 (Baldwin, 2006). In ... (Agirre and Soroa, 2007) and helps in showing whether sense induction can assist determining compositionality. Our method was evaluated for each P 1 , P 2 , P 3  combinati...

Ngày tải lên: 23/03/2014, 17:20

... occurring in a hand-cleaned sub-corpus, as well as linguistic intuition. Using this method, Kveain and Oliva (2002) report find- ing 2661 errors in the NEGRA corpus (containing 396,309 tokens). Interestingly, ... work Considering the significant effort that has been put into obtaining pos-tagged reference corpora in the past decade, there are surprisingly few pub- lications on the issue...

Ngày tải lên: 22/02/2014, 02:20

... shown in grey. 3 Being distinct means that each corpus position is only taken into account for the longest variation n-gram it occurs in. 2.2 Detecting variation in syntactic annotation In Dickinson ... a constituent, despite being in a nearly identical sen- tence. We would thus like to assign the discontinu- ous string sich einig in (5b) the label NIL, so that the labeling of thi...

Ngày tải lên: 17/03/2014, 06:20

... information con- cerning their role in the media narration of events. The interactive interface allows the users to retrieve news report supporting the relations of interest. 1 Introduction U.S presidential ... plot using the first two eigenvalues of the adjacency matrix, which seems to capture the main groupings in the politi- cal narrative. Future work will include making better use of t...

Ngày tải lên: 17/03/2014, 22:20

... finding inconsistencies in annotation for identical recur- ring strings. This emphasis on identical strings can result in high precision, but many strings do not re- cur, negatively impacting ... comparisons In comparing rules, we are trying to find evidence that a particular (parsed) rule is valid by examining the evidence from the (training) grammar. Units of comparison To determine sim...

Ngày tải lên: 30/03/2014, 21:20

... role in defining sentences. The combination of these constraints carl be and actually is very useful, when trying to exploit the information contained in definitions, and when transforming ... definitions in which the word FORHA appears, only those defining something as "having the shape of something else". The implementation of these links allows to produce another...

Ngày tải lên: 31/03/2014, 17:20

... for as- sessing therelative decrease in retrieval performance when indexing summaries instead of full documents. The idea behind it is similar to (Sparck-Jones and Sakai, 2001). In that experiment, ... summarizers. 1 Introduction Automatic document summarization is a field that has seen increasing attention from the NLP commu- nity in recent years. In part, this is because sum- marizat...

Ngày tải lên: 20/02/2014, 16:20

... statistical tech- nique for aligning sentences with their translations in two parallel corpora. In addition to certain anchor points that are available in our da.ta, the only information about the sentences ... appear are shown in Table 1. ALIGNING ANCHOR POINTS After examining the Hansard corpora, we realized that the comments laced throughout would serve as uscflll anchor po...

Ngày tải lên: 20/02/2014, 21:20

... such that it prefers that an interrogating agent not find out the requested information. This might block the formation of an intention to inform, but what is it that inspires the agent to respond ... the role of the dialogue manager in the TRAINS dialogue system which acts as an intelligent planning assistant in a transportation domain. While this is a domain where the assumption of...

Ngày tải lên: 20/02/2014, 21:20

... subjects of finite verbs have nomina- tive case, so in the FINITE class frame we stipulate (CASE NOMINATIVE) for the subject. If we used the complete mode of inheritance in determining the case ... grammatical information appearing in the make entry below is a consequence of our maintaining the strong position that only infor- mation which is idiosyncratic should be included in...

Ngày tải lên: 21/02/2014, 20:20