Coreference resolutior maximum metric score training, domain adaptation, and zero pronoun resolution

... COREFERENCE RESOLUTION: MAXIMUM METRIC SCORE TRAINING, DOMAIN ADAPTATION, AND ZERO PRONOUN RESOLUTION SHANHENG ZHAO (B.E, SOUTH CHINA UNIVERSITY ... for Coreference Resolution 19 2.2 Maximum Metric Score Training 22 2.3 Domain Adaptation for Coreference Resolution 24 2.4 Zero Pronoun Resolution ... propose a novel maximum metric score trainin...

Ngày tải lên: 10/09/2015, 08:29

... 4.2 In -Domain and Out-of -Domain Evaluation 47 4.2.1 47 Training and Evaluating on OntoNotes ii 4.2.2 4.3 Using Out-of -Domain Training Data 49 Concatenating ... attempt to use the existing training data of one word as the training data for other words Kohomban and Lee (2005) tried to use training examples of words different from the actual word to be cla...

Ngày tải lên: 09/09/2015, 10:06

... the two-stage GT training of all phrase and lexicon models BLEU Expected BLEU sentence-level BLEU (Exp BLEU) score of N-best lists and the corpus-level BLEU score of 1-best translations The conjectured ... in a phrase- based system usually include LM, reordering model, word and phrase counts, and phrase and lexicon translation models Given the focus...

Ngày tải lên: 23/03/2014, 14:20

... for Word Sense Disambiguation 19 2.2 Domain Adaptation for Word Sense Disambiguation 23 2.3 Word Sense Disambiguation for Machine Translation 24 Our Word Sense Disambiguation ... WORD SENSE DISAMBIGUATION: SCALING UP, DOMAIN ADAPTATION, AND APPLICATION TO MACHINE TRANSLATION CHAN YEE SENG (B.Computing (Hons.), NUS) A THESIS SUBMITTED FOR...

Ngày tải lên: 11/09/2015, 16:08

... other works, back- Domain Adaptation of Maximum Entropy Models Recently, a hierarchical Bayesian adaptation method was proposed that can be applied to a large family of discriminative learning ... the future since the choice of hyperparameters has a strong impact on the performance of the model References Ciprian Chelba and Alex Acero 2006 Adaptation of maximum entropy...

Ngày tải lên: 23/03/2014, 16:20

... OI, and OO, two with in -domain seed Corresponding to a 100 iterations of 30 sentences each (II, IO) and two with out -of -domain seed (OI, OO), examining in -domain self-training (II, OI) and outof -domain ... -5.7% Table 3: Reduction of the number of manually annotated constituents needed for achieving f score value of 80 on section 23 of the WSJ In all cases the s...

Ngày tải lên: 23/03/2014, 18:20

... dependency" The role of dehydroepiandrosterone (DHEA), thyroid hormone, estrogen and hypophysectomy in aging Ann N Y Acad Sci 1988; 521: 260-73 17 Herbert J Neurosteroids, brain damage, and mental illness ... according to the manufacturer’s procedures BP, HR, and arterial oxygen saturation BP and HR were measured quietly and at constant temperature (~ 23°C) Participants were pro...

Ngày tải lên: 31/10/2012, 16:49

... them We resolve this problem by using pseudoerror sentences and domain adaptation 3.1 Pseudo -Error Generation Correct sentences, which are halves of the paired sentences, can be easily acquired ... manuals, 527,151 sentences in total SRILM (Stolcke et al., 2011) was used to train a trigram model source domain and the real-errors as the target domain Pseudo -error Corpus:...

Ngày tải lên: 19/02/2014, 19:20

... class membership estimates, for the instances in the target domain These probabilities were then used by the machine learning methods to estimate the sense priors of each word in the target domain ... of predominant sense is often indicative of a change in domain, as different corpora drawn from different domains usually give different predominant senses For example,...

Ngày tải lên: 08/03/2014, 02:21

... active learning for domain adaptation, followed by count-merging Next, we describe an EMbased algorithm to estimate the sense priors in the new domain Performance of domain adaptation using active ... adaptation examples added (%) Figure 3: Using true predominant sense for the nouns the sense priors in WSJ Using this new set of training examples, we perform domain adapta...

Ngày tải lên: 08/03/2014, 02:21

... trained without adaptation, while the gold standard is an in -domain classifier trained on the same domain as it is tested Figure gives accuracies for all pairs of domain adaptation The domains are ... 2006 Analysis of representations for domain adaptation In Neural Information Processing Systems (NIPS) John Blitzer, Ryan McDonald, and Fernando Pereira 2006 Domain adaptati...

Ngày tải lên: 08/03/2014, 02:21

... to adaptation could hope to attenuate this problem There have been a few attempts to measure or perform domain adaptation in machine translation One of the first approaches essentially performs ... Marcello Federico 2009 Domain adaptation for statistical machine translation with monolingual resources In StatMT ’09: Proceedings of the Fourth Workshop on Statistical Machine Tr...

Ngày tải lên: 17/03/2014, 00:20

... 35.9 36.0 35.1 Table 5: Domain adaptation results DE–FR Domain: Alpine texts Full IN TM: Using the full in -domain parallel corpus; small IN TM: using 10% of available in -domain parallel data weights.12 ... When moving from a binary setting with one in -domain and one out-of -domain translation model (trained on all available out-of -domain data) to 4–10 translation...

Ngày tải lên: 17/03/2014, 22:20

... a pseudo multi-view algorithm where original data has only one view Therefore, it is not suitable for the true multi-view case as ours Zhang et al (2011) proposed an instance-level multi-view ... deemed as different domains The task is defined as top category classification For example, the dataset denoted as DA-EC consists of source domain: DA 1(+), EC 1(-); and target domain: DA 2(+),...

Ngày tải lên: 23/03/2014, 14:20

... domain -adaptation setting is that some of the latent variables will correspond to clusters of features specific only to the source domain, and consequently, the classifier relying on this latent ... expectation of this feature given by the model, where the prior expectation is provided by the model designer as a form of weak supervision In our case, both expectations are pro...

Ngày tải lên: 30/03/2014, 21:20