an active learning approach to finding related terms

... Linguistics An Active Learning Approach to Finding Related Terms David Vickrey Stanford University dvickrey@cs.stanford.edu Oscar Kipersztok Boeing Research & Technology oscar.kipersztok @boeing.com Daphne ... belongs to G when presented with that word. To evaluate a particular active learning algo- rithm, we can just run the algorithm manually, and see how many candidate words we say “Yes” to (note ... For example, to determine how similar (the only sense of) “factory” is to the word “plant,” we compute the similarity of “factory” to the “in- dustrial plant” sense of “plant” and to the “living thing”...

Ngày tải lên: 30/03/2014, 21:20

... and learning energy can get lost. Learning organisations make conscious efforts to retain this energy: A learning company is an organisation that facilitates the learning of all its members and ... leads to exploration, discovery and learning. In the learning organisation, leadership can be defined as learning on behalf of the organisation. Is Challenge 2: creating a learning organisation ... together with an action learning process to help you to address any challenge. xii A Manager’s Guide to Leadership Pedler00v3_00 21/04/10 09:39 Page xii This book is an active guide to leadership...

Ngày tải lên: 17/03/2014, 21:29

... experience and deep knowledge of storage management to help customers create more efficient storage management operations. Prior to EMC, Joel held technology management and consultant positions ... critical success factor and should be defined according to your role: storage managers, for example, will likely want to monitor more frequently, perhaps to publish a quarterly or annual report for ... courses and enhanced, hands-on labs offer practical skills and tips that you can immediately put to use. Our expert instructors draw upon their experiences to help you understand key concepts and...

Ngày tải lên: 26/10/2013, 22:15

Ngày tải lên: 11/12/2013, 23:51

... but also to the German NEGRA and the Chinese CTB. (Zollmann and Sima&apos ;an 2005 propose a different consistent estimator for DOP, which we cannot go into here). 5 UML-DOP Analogous to U-DOP, ... estimator corresponds to maximum likelihood (Chi and Geman 1998), and which we shall refer to as "ML-PCFG". To this end, we used a random 90%/10% division of WSJ40 into a training set and ... parsing technique by Huang and Chiang (2005), but we have not yet incorporated this into our implementation. To give an example of the dependencies that U-DOP can take into account, consider the following...

Ngày tải lên: 20/02/2014, 12:20

... HCI and HHC and that it is not possi- ble simply to take the human-human interaction results and transpose results for one situation to the other. The structuring devices of the human -to- human construction ... human-human interaction employs a variety of dialogue structuring mech- anisms, ranging from meta-talk to discourse markers, and that some of these can usefully be employed for automatic analysis ... constructor in the HHC setting was another human interlocutor; in the other scenario, the participants were seated in front of a computer but were informed that they were actually talking to an automatic...

Ngày tải lên: 08/03/2014, 21:20

... An HMM-Based Approach to Automatic Phrasing for Mandarin Text- to- Speech Synthesis Jing Zhu Department of Electronic Engineering Shanghai Jiao Tong University zhujing@sjtu.edu.cn Jian-Hua ... described an approach to automatic prosodic phrasing for Mandarin TTS synthesis based on word format and HMM and its variants. We also evaluated these methods through experiments and demonstrated ... structure(Black and Taylor, 1994; Klatt, 1987; Wightman, 1992; Hirschberg 1996; Wang, 1995; Taylor and Black, 1998). To our understanding, POS is a grammar- based structure that can be extracted...

Ngày tải lên: 17/03/2014, 04:20

... form of the anaphor ana gramrole grammatical role of the anaphor ana agr agreement of the anaphor ana semclass* semantic class of the anaphor ante npform NP form of the antecedent ante gramrole ... arts and entertainment, and travel. 4.2 The MMAX Annotation Tool The manual annotation of the training data was done with the MMAX (Multi-Modal Annotation in XML) annotation tool (M¨uller and ... grammatical role of the an- tecedent ante agr agreement of the antecedent ante semclass* semantic class of the an- tecedent dist distance in markables between anaphor and an- tecedent (1 20) same...

Ngày tải lên: 17/03/2014, 06:20

... 5 Conclusion An effective and efficient approach to phrasal verb identification is presented. This approach handles both separable and inseparable phrasal verbs in English. An Expert Lexicon ... clown blew up the balloon. The overlapping phenomenon can be handled by assigning both a transitive feature and an intransitive feature to the identified PVs in the same way that we treat the ... parser to use. The representation of a canonical form for an identified PV is necessary to allow for individual rules to be associated with identified PVs in further processing and to facilitate...

Ngày tải lên: 17/03/2014, 06:20

... applied in lan- guage processing to a wide range of linguistic tasks, from phonology to semantic analysis. Our goal was to investigate the performance of a memory–based approach to the event ... Daelemans, A. Van den Bosch, and J. Zavrel. 1999. Forgetting exceptions is harmful in language learning. Machine Learning, Special issue on Natural Language Learning, 34:11–41. W. Daelemans, J. ... corpus and modelling the task applying an approach similar to the one that has been applied to tasks like semantic role labeling (Morante et al., 2008) or negation scope detection (Morante and Daelemans,...

Ngày tải lên: 23/03/2014, 13:20

... with semantic affinity patterns and relevant regions. In Joint Conference on Empirical Methods in Natural Language Processing. S. Patwardhan and E Riloff. 2009. A unified model of phrasal and sentential ... Empirical Methods in Natural Language Processing (EMNLP). Slav Petrov, Leon Barrett, Romain Thibaux, and Dan Klein. 2006. Learning accurate, compact, and interpretable tree annotation. In Proceedings ... Incrementally Train- able Statistical Approach to Information Extraction: Based on Token Classification and Rich Context Model. VDM Verlag, Saarbr ¨ ucken, Germany, Ger- many. 295 Ment Acc. Ent. Acc. INDEP...

Ngày tải lên: 23/03/2014, 16:20

... can be some other con- struction methods which show higher performance. Still, we believe that this is one of the best ac- quisition performances achieved ever and will be an important step to ... of ACL SIGLEX, 231–238. Christiane Fellbaum. 1998. WordNet: an electronic lexi- cal database, MIT Press. Maayan Geffet and Ido Dagan. 2004. Feature Vector Quality and Distributional Similarity. ... 268– 275. Dekang Lin. 1998. Automatic retrieval and clustering of similar words. Proc. of COLING/ACL 98, 786–774. Shachar Mirkin, Ido Dagan, and Maayan Geffet. 2006. Integrating pattern-based and distributional...

Ngày tải lên: 23/03/2014, 17:20

... between anaphor and antecedent 13. wdist distance between anaphor and antecedent in words 14. mdist distance between anaphor and antecedent in markables 15. sdist distance between anaphor and antecedent ... have non-NP-antecedents. Many of these pronouns do not have an antecedent at all. Oth- ers are vague in that human annotators felt them to be referential, but could not determine an an- tecedent. ... the number of anaphorically accessible 4 S- and VP-markables between anaphor and potential antecedent. The feature ante tfifd (23) is supposed to capture the relative importance of an expression...

Ngày tải lên: 23/03/2014, 19:20

... Ken-Ichi Takami, and Yuru Wu. 1999. Quantifi er scope in English, Chinese, and Japanese. Language, 75(1):63-111. M. Marcus, S. Santorini, and M. Marcinkiewicz. 1993. Building a large annotated corpus ... with transformational gram- mar. In J. Cole, G. Green, and J. Morgan, editors, Linguistics and Computation, pages 103-143. Noam Chomsky. 1957. Syntactic Structures. Janua Linguarum. Mouton, ... in- terpretation of the sentence, and could contribute to a natural language understanding or machine translation application. Since WH dependencies also tend to distort the surface subcategorization properties...

Ngày tải lên: 24/03/2014, 03:20

... high-level analysis, performs like a human receptionist or operator and passes the enquiry to the most relevant subclass for a more detailed analysis specific to that subclass. Any available ... if a transaction is to be meaningful. 3 Some important system characteristics The current prototype (Figure 1 below) focuses on dialogue management. It is not intended to transcribe and parse ... the relevant Expert subclass (here the Travel Expert), the system analyses the supplied information, to try to establish the context of the transaction, and then to process the transaction...

Ngày tải lên: 24/03/2014, 03:20

... error correction. We use the Stanford coreNLP toolkit 1 (Toutanova and Manning, 2000; Klein and Manning, 2003a; Klein and Manning, 2003b; Finkel et al, 2005) to extract the features. 2.3. ... the overall performance. The base classifiers can be expected to become more informative as more data are provided. We followed the structural learning approach (Ando and Zhang, 2005), which ... learner corpus to derive more accurate results (Han et al., 2010; Rozovskaya and Roth, 2010). Since the two approaches are closely related to each other, they can be informative to each other....

Ngày tải lên: 30/03/2014, 17:20

Ngày tải lên: 31/03/2014, 00:20

Ngày tải lên: 31/03/2014, 03:20

Ngày tải lên: 31/03/2014, 04:20

Ngày tải lên: 31/03/2014, 20:20