Báo cáo khoa học: "A Machine Learning Approach to Pronoun Resolution in Spoken Dialogue" docx

... A Machine Learning Approach to Pronoun Resolution in Spoken Dialogue Michael Strube and Christoph M ¨ uller European Media Laboratory GmbH Villa Bosch Schloß-Wolfsbrunnenweg ... masculine and feminine pronouns (3mf), third person neuter pronouns (3n), and third person plural pronouns (3p). Since only 3n-pronouns have non- NP-antecedents, we were mainly interested in im- prov...

Ngày tải lên: 23/03/2014, 19:20

... A Machine Learning Approach to German Pronoun Resolution Beata Kouchnir Department of Computational Linguistics T¨ubingen University 72074 T¨ubingen, Germany kouchnir@sfs.uni-tuebingen.de Abstract This ... presents a novel ensemble learning approach to resolving German pronouns. Boosting, the method in question, combines the moderately ac- curate hypotheses of several clas...

Ngày tải lên: 17/03/2014, 06:20

... paper consists in the de- velopment of a machine- learning approach to the identification of WH gaps. This approach reduces the lexical prerequisites for this task, while main- taining a high degree ... A machine- learning approach to the identification of WH gaps Derrick Higgins Educational Testing Service dchiggin@alumni.uchicago.edu Abstract In this paper, we pursue ......

Ngày tải lên: 24/03/2014, 03:20

... a machine learning approach to evaluating the well- formedness of output of a machine translation system, using classifiers that learn to distinguish human reference translations from machine ... minus number of left-branching nodes ¾ branching index for NPs only ¾ branching weight index: number of tokens covered by right-branching nodes minus number of tokens covered by left-br...

Ngày tải lên: 31/03/2014, 04:20

... with a larger training set. It would result in a better over- all performance. Switching from decision trees to other training methods such as Support Vector Ma- chines or using semantically ... for instance to mark polarity by linking a not to its main verb. We identify these links simul- taneously with the event detection. We augmented the phrase-structure rules to handle subordin...

Ngày tải lên: 31/03/2014, 20:20

... similarity set- ting, in contrast, the contributions of context types are uniformly fixed. In order to elucidate what is happening in this situation, the investigations on ma- chine learning settings, as ... approach is enhanced with the supervised machine learning. In this paper, we propose a novel approach to automatic synonym identification based on super- vised learnin...

Ngày tải lên: 23/03/2014, 17:20

... training and test data. We hold out 10% of the data for the test. We applied 20% under-sampling to the training instances that do not have any errors to alleviate data imbalance in the training ... structural learning. We adopted the feature set investigated in De Felice (2008) for article error correction. We use the Stanford coreNLP toolkit 1 (Toutanova and Manning, 2000; Kl...

Ngày tải lên: 30/03/2014, 17:20

... 2005), up to 14 percentage points better than MLE. We find improvements both when training from data alone, and using a tagging dictionary. 1 Introduction Unsupervised learning of linguistic structure ... dic- tionary information, and Section 6 concludes. 2 A Bayesian HMM 2.1 Motivation In model-based approaches to unsupervised lan- guage learning, the problem is formulated in terms...

Ngày tải lên: 20/02/2014, 12:20

... the result, suggesting the effectiveness of the new introduced features. Regarding the two training settings in reranking, we find that there is no gain from reranking when using only one best ... and Lapata, 2008) investigates sentence compression in broadcast news using an integer linear programming approach. There is only a few existing work in spon- taneous speech domains. (Liu and...

Ngày tải lên: 07/03/2014, 18:20

... 1983, and 1984) in which the process of representing the meaning of a natural language text is split into three main tasks, namely: sentence understanding, structure capturing, and i mportance ... values (integers) according to their relative importance in the text. Once the HPN representation of a text has been produced, it is easy to prune the less relevant parts in order...

Ngày tải lên: 09/03/2014, 01:20