Báo cáo khoa học: "Extracting Parallel Sub-Sentential Fragments from Non-Parallel Corpora" pdf

... boxes from the figure show, some parallel fragments of data do exist; but they are present at the sub-sentential level. In this paper, we present a method for extracting such parallel fragments from ... deals with sub-sentential fragments. However, they obtain parallel fragments from parallel sentence pairs (by chunking them and aligning the chunks appropri- ately), wh...

Ngày tải lên: 08/03/2014, 02:21

... model personality suggests an ability to model so- cial power lects as well. Apart from text classification, work from the topic modeling community is also closely related to Social Power Modeling. ... that including these features would also benefit from algorithmic means of se- lecting n-grams that are indicative of particular lects, and even from binning these relevant n- gra...

Ngày tải lên: 07/03/2014, 22:20

... infer the meaning of a target term from other terms in a text. For example, a Question An- swering system may infer the answer to a ques- tion regarding luxury cars from a text mentioning Bentley, ... announcement from the text “Margaret Thatcher announced”. To perform such inferences, systems need large scale knowledge bases of LR rules. A prominent available resource is WordNet (Fellb...

Ngày tải lên: 08/03/2014, 00:20

... queries posedbyusers.Thequerylogconsistsof557que- ries,collected from twenty-eighthumansubjectsat the Shanghai Jiao Tong University (Ying 2002). Eachsubjectisaskedtopose20separatequeriesto retrievegeneralinformation from theWeb. After ... mostlybasenoun phraseandnamedentity.Thephrasesarederived from twosources.We firstderivedasetofcom-...

Ngày tải lên: 31/03/2014, 03:20

... also differ from Livesay and Burgess (1997) who found that mediated primes were fur- ther from their targets than unrelated controls, us- ing however a model and corpus different from the ones ... are all significantly different from CA (see Table 3, where × indicates statistical significance, a = .05). Furthermore, ANT and SYN are signifi- cantly different from PA. Kilgarriff and Yall...

Ngày tải lên: 17/03/2014, 06:20

... engineering is desired. Paraphrases can be extracted from non -parallel corpora using contextual similarity (Lin, 1998). They can also be obtained from parallel corpora if such data is available (Barzilay ... naturally form a semi- parallel corpus, and (3) they contain many techni- cal terms. However, bug reports have characteristics that raise many new challenges. Different from m...

Ngày tải lên: 08/03/2014, 01:20

... paraphrase patterns from our corpus. Examples of such contexts are verb-object re- lations and noun-modifier relations, which were traditionally used in word similarity tasks from non -parallel corpora ... and it prevents us from using methods developed in the MT community based on clean parallel corpora, such as (Brown et al., 1993). Another distinction between our corpus and parall...

Ngày tải lên: 23/03/2014, 19:20

... non-comparatives by extracting only comparatives from text documents. Then we classify the comparatives into seven types. 3.1 Extracting comparative sentences from text documents Our strategy is to ... effectively filter out non-comparative sentences from CS-candidates, we use the sequences of “continuous POS tags within a radius of 3 words from each CK” as features. Each word...

Ngày tải lên: 20/02/2014, 04:20

... comparative sentences from text documents. This paper first investigates many comparative sentences referring to pre- vious studies and then defines a set of compar- ative keywords from them. A sentence ... to eliminate non- comparative sentences only from comparative sentence candidates with a CKL2 keyword. 4 Eliminating Non-comparative Sen- tences from the Candidates 3 A...

Ngày tải lên: 20/02/2014, 09:20

... rather straightforward. However, this might not be the case if we build the lexicon from a very different representation or even from corpora, where post- modification by hand is simply inevitable. A paradigm ... Help.n). This is ex- actly where we finally use the parameters from Help argument of the type NP defined above. We only use the declension tables from the argu- 2 In this exampl...

Ngày tải lên: 20/02/2014, 12:20