Báo cáo khoa học: "Extracting Paraphrases from a Parallel Corpus" pdf

... ex- tract new paraphrases. In addition to learning lex- ical paraphrases, the method also learns syntactic paraphrases, by generalizing syntactic patterns of the extracted paraphrases. Extracted paraphrases are ... well as syntactic para- phrases. 1 Introduction Paraphrases are alternative ways to convey the same information. A method for the automatic acquisition of paraphrases h...

Ngày tải lên: 23/03/2014, 19:20

... References Susumu Akamine, Daisuke Kawahara, Yoshikiyo Kato, Tetsuji Nakagawa, Yutaka I. Leon-Suematsu, Takuya Kawada, Kentaro Inui, Sadao Kurohashi, and Yutaka Kidawara. 2010. Organizing information on ... expressions that have a large distributional simi- larity are paraphrases. There are also variants of this approach that address entailment acquisition (Geffet and Dagan, 2005; Bhagat e...

Ngày tải lên: 30/03/2014, 21:20

... extracted from non -parallel corpora using contextual similarity (Lin, 1998). They can also be obtained from parallel corpora if such data is available (Barzilay and McKeown, 2001; Ibrahim et al., ... of ex- tracting technical paraphrases from a par- allel software corpus, namely, a collec- tion of duplicate bug reports. Paraphrase acquisition is a fundamental task in the eme...

Ngày tải lên: 08/03/2014, 01:20

... Fourth, as performed by Fujii et al. (2004), we use a Japanese Katakana dictionary and extract a candidate loanword that is phonetically similar to a Katakana word as a loanword. We romanize ... identify Katakana words that are phonetically similar to a candidate loanword. In other words, we use a candidate loanword, and each Katakana word as a query and a document, res...

Ngày tải lên: 23/03/2014, 18:20

... shock. Largest tobacco company in the world: 1. Philip Morris, 2. BAT, 3. Japan Tobacco, 4. Imperial Tobacco, 5. Altadis. Largest rodent in the world: 1. Capybara, 2. Beaver, 3. Patagonian Cavies. ... require a significant amount of la- beled data. To get around this problem, we repre- sent each (x, k, s) as a vector of features and train two Naive Bayes classifiers: one for classifying s a...

Ngày tải lên: 23/03/2014, 16:20

... a partic- ular template. The present template was ClaC2aCaa, the past template aCtC2aaC3, and the future template aClaC2Caa. Thus the three forms for the root pmn were pamana, apmaan, ... rules, involving three forms: (1) present: CzaC2aCaa, past: aCiC2aaC3, future: aClaC2C 3a (2) present: ClaC2Caaa, past: aC1C2aCaa, future: aClaC3aC2. 282 PC 2 ,,,,i,,, 2 -0.4 -0....

Ngày tải lên: 20/02/2014, 21:20

... unification strength is always a value between 0 and 1. The Parser: Activated Chart Edges The parser is a modified unification-based chart parser. Chart edges are assigned activation levels, which ... GRADED UNIFICATION: A FRAMEWORK FOR INTERACTIVE PROCESSING Albert Kim * Department of Computer and Information Sciences University of Pennsylvania Philadelphia, Pennsylvania, US...

Ngày tải lên: 20/02/2014, 21:20

... representation of Max embarque la caisse sur le cargo [3J/Max em- barks the crate on the cargo boat can be analyzed in two steps. First there is a transition from an initial state IS where ... cargo~the crate was embarked on the cargo boat, and is schematized in (2). One of the argument (cargo boat) is used as a localization while the other argument is used as a localized ent...

Ngày tải lên: 17/03/2014, 08:20

... facet. Finally, we train a machine learning classi- fier on training data and use it to classify unseen test examples, assigning a Table 1 label for each reference answer facet. We used a variety ... answer facets that are not ad- dressed at all by the student’s answer Table 1. Facet Annotation Labels 3 Automated Classification As partial validation of this knowledge representa-...

Ngày tải lên: 23/03/2014, 17:20

... were applied to two sets of new abstracts downloaded from Medline: 100 new abstracts from the origi- nal four medical areas (25 abstracts from each area), and 30 abstracts from two new domains (15 ... kill can be para- phrased as to cause to die. We analyzed the 200 training abstracts to identify the linguistic markers (such as causal links and causative verbs) used to indicate causal...

Ngày tải lên: 31/03/2014, 04:20