Báo cáo khoa học: "Discriminative Classifiers for Deterministic Dependency Parsing" docx

... Sessions, pages 316–323, Sydney, July 2006. c 2006 Association for Computational Linguistics Discriminative Classifiers for Deterministic Dependency Parsing Johan Hall V ¨ axj ¨ o University jni@msi.vxu.se Joakim ... comparison of memory-based learning (MBL) and sup- port vector machines (SVM) for inducing classifiers for deterministic dependency parsing, using data from Ch...

Ngày tải lên: 23/03/2014, 18:20

... different trans- formations have been studied by Johnson (1998), Klein and Manning (2003), and Bikel (2004). Corre- sponding manipulations in the form of tree transfor- mations for dependency- based ... treebanks, making the inverse trans- formation for PADT more problematic than for the other treebanks. The absence of a positive effect for PADT is therefore understandable given the...

Ngày tải lên: 17/03/2014, 04:20

... Though proposed for English, this method is effective for Chinese ASR (Chen et al., 2004). Gao et al. (2002) combined an information gain-like metric and the perplexity reduction criterion for lexicon ... struc- ture for SDR, which significantly outperforms word-based methods for IV or OOV queries. Here we apply S-CN structure to investigate the effec- tiveness of improved character...

Ngày tải lên: 20/02/2014, 07:20

... Association for Computational Linguistics, pages 795–804, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Collective Classification for Fine-grained Information ... best of our knowledge, we therefore present the first English corpus reliably annotated for a wide range of IS categories as well as full anaphoric information for three main anap...

Ngày tải lên: 30/03/2014, 17:20

... error reduction. Results are for dependency parsing on the dev set for iters:5,training-k:1. tal errors break down by gold head. For example, the 12.1% total error reduction for attachments of an IN ... compute features for the full parsing task. To show end-to-end effectiveness, we incor- porate our features into state-of-the-art dependency and constituent parsers. For the d...

Ngày tải lên: 20/02/2014, 04:20

... grouping of information, thus expressing the information in- terdependencies. The language which SUG pro- vides for specifying these descriptions allows par- tiality both in the information about ... thereby also forgetting the predications over the nodes. This forgetting operation abstracts away from the existence of the forgotten node in the phrase structure. Once a node is forgot...

Ngày tải lên: 20/02/2014, 21:20

... map-free information- theoretic criterion—see Gao and Johnson (2008) for details. Although we find M-to-1 to be the most reliable criterion of the three, we include the other two criteria for completeness. ... Table 1 compares the per- formance of SVD2 to other leading models. Fol- lowing Gao and Johnson (2008), the number of induced tags is 17 for PTB17 evaluation and 50 for PTB45...

Ngày tải lên: 07/03/2014, 22:20

... appro- priately dropped, compared with 17 for the An- notated system. Of those pronouns, the meaning could still be understood for 7/12 for the Baseline system compared with 8/14 for the Annotated sys- tem. ... 26 April 2012. c 2012 Association for Computational Linguistics Improving Pronoun Translation for Statistical Machine Translation Liane Guillou School of Informatics Unive...

Ngày tải lên: 17/03/2014, 22:20

... syntactic realizations for each semantic class and distributions of syntactic dependency arcs for argument types. In this section we present relevant background on PY processes. For a more detailed ... of type t appears for a given semantic frame occur- rence 3 . For the frame WinPrize these parameters would enforce that there exists exactly one Winner and exactly one Opponent fo...

Ngày tải lên: 23/03/2014, 16:20

... clusters are used for predicted and conditional words. In particular, for clustering conditional words, we try to minimize the perplexity of training data for a bigram of the form P(w i |W i-1 ), ... clusters for words in different positions. For the predicted word, w i , we will denote the cluster of the word by PW i , and we will refer to this as the predictive cluster. ....

Ngày tải lên: 23/03/2014, 20:20