Báo cáo khoa học: "Accurate Learning for Chinese Function Tags from Minimal Features" pdf

... guidelines of Penn Chinese Treebank talk of function tags. We will use the term function labels and function tags identically, and hence make no distinction be- tween function labeling and function tagging ... simply extend previous method from English to Chinese, we also proposed an effective way to recognize function tags directly from lexical information, which is e...

Ngày tải lên: 08/03/2014, 01:20

... our learning algorithm is the strategy used to select samples for training. In general, this novel learning framework lies be- tween supervised learning and reinforcement learn- ing. Guided learning ... classification are dynamically incorporated in the learning phase. Guided learning is not as hard as reinforcement learning. At each local step in learning, we always know the u...

Ngày tải lên: 20/02/2014, 12:20

... standard machine learning approach, outperforming them by as much as 4–7% on the three data sets for one of the performance metrics. 2 Related Work As mentioned before, our approach differs from the standard ... ACL, pages 157–164, Ann Arbor, June 2005. c 2005 Association for Computational Linguistics Machine Learning for Coreference Resolution: From Local Classification to Glob...

Ngày tải lên: 20/02/2014, 15:20

... test sets when additional source language data from the Chinese Gigaword corpus compris- ing newswire text is used for transductive learning. These Chinese sentences were sorted according to their ... French–English translation task from the Eu- roParl corpus, and the other one is Chinese English translation as performed in the NIST MT evaluation (www.nist.gov/speech/tests/mt)....

Ngày tải lên: 08/03/2014, 02:21

... n − 1 for a model of order n — may have n-gram arcs entering from other full-order states as well as from backoff states of history size n − 2. 3.2 Encoding with lexicographic semiring For an ... paths from the ep- silon approximation are different, at least in terms of weights, from the shortest paths using the failure LM. For full lattices, 42 (4.7%) of the lexicographic outpu...

Ngày tải lên: 20/02/2014, 04:20

... computeParameters(training) for feature = 1:MAXFEATURES evaluate(parameters,development, [bestFeatures + feature]) keep validation performance end end average_performance and keep average_performance ... saved for later experiments. 4.1 Selecting the features The first task was to reduce the dimensionality and find the best set of features for maximizing the PPV...

Ngày tải lên: 20/02/2014, 16:20

... transform syntactic as well as morphological variations of names into a normalized name form. Basic trans- formations can be achieved via pattern match- ing (regular expressions) while for more ... have to be called. For this, we are developing a comprehensive set of functions which call the constraints with the cor- rect parameters for the given input name. In these functions, it is de...

Ngày tải lên: 08/03/2014, 01:20

... has of course no for- mal consequences for the information contained in the lattice. To determine RE-content appropriate for re- ferring to object ol, we again look for minimal (i.e., nearest ... supportive of minimal RE's and we will only follow this path here; formal indica- tions of minimality are given by the depth and number of paths leading from the node used...

Ngày tải lên: 08/03/2014, 06:20

... and Rosie Jones. 1999. Learning Dic- tionaries for Information Extraction by Multi-Level Bootstrapping. AAAI ’99. Benjamin Rosenfeld and Ronen Feldman. 2007. Clustering for unsupervised relation ... similarity information. First, we obtain from the Web and WordNet a list of terms similar to the given object. Then we retrieve attribute values for each term in this list, and infor- ma...

Ngày tải lên: 20/02/2014, 04:20

... P (t 3 |t 1 , t 2 ), where t 3 stands for the unknown 3 POS, and t 1 and t 2 stand for the two previous POS tags. The POS tags for known words are taken from the tagged training corpus. Following ... reported in previous stud- ies, which was 69%. 2 Chinese Unknown Words The definition of what constitutes a word is prob- lematic for Chinese, as Chinese does not have word delim...

Ngày tải lên: 08/03/2014, 04:22