Báo cáo khoa học: "Semantic Class Induction and Coreference Resolution" pptx

... models. For instance, Daum´e and Marcu’s model assumes as input a corpus annotated with both MD and coreference information. On the other hand, we tackle coreference and SC induction separately (rather ... Cor- pus, where coreference information is absent. 3 Semantic Class Induction This section describes how we train and evaluate a classifier for determining the SC of an N...

Ngày tải lên: 17/03/2014, 04:20

... par- titions for training, development, and testing, and later per-partition merged (MERGED) for system evaluation. The distribution of coreference chains and referring expressions is given in ... features WN CLASS U if RE i or RE j have an undefined WordNet semantic class. Else if they both have a defined one and it is the same T; else F. 2 Possible values are U(nknown), T(rue) a...

Ngày tải lên: 08/03/2014, 21:20

... been proposed, including work in lexical acquisition (Riloff and Shepherd, 1997; Roark and Charniak, 1998) and in discovering instances, named enti- ties, and alternate glosses (Etzioni et al., 2005; Pasc¸a, ... 2003), a variety of verb re- lations (Chklovski and Pantel, 2004), and general purpose analogy relations (Turney et al., 2003). Such classifiers use hand-written or automat...

Ngày tải lên: 20/02/2014, 12:20

... to query the web and extract semantic class instances: CLASS NAME such as CLASS MEMBER and *. We hypothesized that a doubly-anchored pattern, which includes both the class name and a class member, ... identify candidate instances for a semantic class: < ;class name> such as < ;class member> and * This pattern has two variables: the name of the se- mantic class...

Ngày tải lên: 17/03/2014, 02:20

... detec- tion and tracking, and one segment of the text. In order to annotate unambiguously, we need to detect and track both landmarks and actions. A landmark is a hallway or a door, and an action is ... in ”go straight and make the first left you can, then go into the first door on the right side and stop” , LEFT and FIRST occur exactly once for the first action, and FIRST, DOO...

Ngày tải lên: 17/03/2014, 04:20

... system of (Briscoe and Carroll, 1997) distinguishes 163 verbal subcategorisation classes by means of a statistical shallow parser, a classifier of subcategorisation classes, and a priori estimates of ... Large-Scale Induction and Evaluation of Lexical Resources from the Penn-II Treebank Ruth O’Donovan, Michael Burke, Aoife Cahill, Josef van Genabith, Andy Way National Centre for Langua...

Ngày tải lên: 17/03/2014, 06:20

... 3: WSJ Sentences. In table 4, we show the standard deviation measured from three different randomly chosen training sets of each sample size and randomly chosen test sets of 500 sentences each, ... present results and compare these results to other recent results in automatic grammar induction. INTRODUCTION There has been a great deal of interest of late in the automatic induct...

Ngày tải lên: 31/03/2014, 06:20

... be handled by pretending they are a form of prepos=t=onal phrase The regular and predictable relattonsn~p between s~mple statements. ¢~uestions and relalwe clauses and between act=ve and ... effic=ency on grin ~atical ,nput. and robustness in the face of ungrammatmcal tnput Wh~le Plume ~s well adapted to s=mpte ,:;~ectaratwe and ~mperat=ve utterances, it handles 0ass=yes re...

Ngày tải lên: 31/03/2014, 17:20

... enriched with classification features by fea- ture extractors, and then handed over to a machine learning-based classifier that decides, given the fea- tures, whether anaphor and candidate are corefer- ent ... guidelines of MUC and ACE corpora) usually involves fine-tuning of mention cre- ation (using pipeline and MentionFactory settings), as well as the selection and fine-tuning of cla...

Ngày tải lên: 20/02/2014, 09:20

... baselines train separate classifiers for gesture and speech, and then combine their posteriors. The modality- specific classifiers are conditionally-trained lin- ear models, and again use the same ... between meaningful gestures and irrelevant hand motions (e.g., self- touching, adjusting glasses) (Goodwin and Good- win, 1986), NLP systems may be confused by such seemingly random movem...

Ngày tải lên: 20/02/2014, 12:20