Báo cáo khoa học: "An IR Approach for Translating New Words from Nonparallel, Comparable Texts" pot

... An IR Approach for Translating New Words from Nonparallel, Comparable Texts Pascale Fung and Lo Yuen Yee HKUST Human Language ... and other words from this online nonparallel, comparable corpus of newspaper materials. We choose to use issues of the En- glish newspaper Hong Kong Standard and the Chinese newspaper Mingpao, ... almost all unambiguous Chinese...

Ngày tải lên: 08/03/2014, 05:21

... Association for Computational Linguistics An Approximate Approach for Training Polynomial Kernel SVMs in Linear Time Yu-Chieh Wu Jie-Chi Yang Yue-Shi Lee Dept. of Computer Science and Information ... efficiently expand new features for the original feature vectors, we propose a new method to fast discovery patterns. Essentially, the PrefixSpan al- gorithm gradually expand...

Ngày tải lên: 20/02/2014, 12:20

... unaligned phrase pair (where |e| = 0 or |f| = 0) according to a fixed probabil- ity p u 3 , then generating from P ba for aligned phrase pairs, or P bu for unaligned phrase pairs. For P ba , we adopt ... the reliability of the phrase pair. It will be high for common phrase pairs that are gen- erated directly from the model, and also for phrases that, while not directly included i...

Ngày tải lên: 20/02/2014, 04:20

... and test data are from the same domain and when they are from different domains. For a test setting used by previous work, we show an error reduction of 31% as opposed to their 20%. 1 Introduction Many ... clutter, for the filter f-score measure we use the maximum recall (MR) baseline rather than the minimum length (ML) baseline, since the former outperforms the lat- ter. Thus, ML is o...

Ngày tải lên: 20/02/2014, 12:20

... (2) the DOP hypothesis which states that parse accuracy increases with increasing frag- ment size is confirmed for LFG-DOP; (3) LFG- DOP's relative frequency estimator performs worse than ... hypothesis, which states that there is an increase in parse accuracy if larger fragments are taken into account (Bod 1998), is confirmed for LFG-DOP. We report on an improved search technique f...

Ngày tải lên: 20/02/2014, 18:20

... hypothesis, we need to solve two problems. First, we need a means to acquire vast amounts of background knowledge from which we can derive, for example, that the word pairs good – fails and embargo – legally ... 1999). For each discourse relation pair , we train a word-pair-based classifier using the automatically derived training examples in the Raw corpus, from which we first removed...

Ngày tải lên: 20/02/2014, 21:20

... suggestions for correct continuation. A choice from the menu can be typed or selected u~ng the mouse. |NGLISH in fact allows all actions to be performed from the keyboard or with the mouse and for ... circuit | IND led-2 COND[ STATE on [ FORM <sta~(O IND FORM), (t STATE FORM))> CNCL [ DEV tr~i,~torol7 t FORM <s~u.¢((, DEV), fa~ed)> t FORM <rule(O COND),...

Ngày tải lên: 21/02/2014, 20:20

... as well as their connec- tions. Thus, available formalisms allow linguistic knowledge to be directly “transcribed” and used. Involved procedural mechanisms, committed to the platform, can be ignored. ... annota- 96 tions. Available formalisms make it possible to ex- press constraints on these annotations by means of unification. Thereby, the platform promotes pro- gressive abstraction from s...

Ngày tải lên: 22/02/2014, 02:20

... accumulation of information for each dimension. Virtual Machine The evaluation of a query is done by a specific Virtual Machine inspired by the Warren’s Abstract Machine (see (Ait-Kaci, 1991)). First, it ... to Claire Gardent for useful comments on this work. This work is partially supported by an INRIA grant. In this paper, we present a metagrammar system for tree-based grammars which d...

Ngày tải lên: 22/02/2014, 02:20

... linguistic formulaic expressions. Previous discourse-level annotation schemes (e.g. Liddy, 1991; Kircz, 1991) show that infor- mation retrieval can profit from added rhetorical information ... of or support for own work? Figure 2: Decision tree for annotation Our materials consist of 48 computational lin- guistics papers (22 for Study I, 26 for Study II), taken from the C...

Ngày tải lên: 22/02/2014, 03:20