Search
Search Funnelback University
- Refined by:
- Date: 2018
11 -
20 of
555
search results for news |u:mi.eng.cam.ac.uk
Fully-matching results
-
Enginuity
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/1997-Enginuity-face-detection.pdf13 Mar 2018: A new approach. An engineering viewpoint. This is part of a more ambitious project on understanding vision and making machines see. -
acl2010.dvi
mi.eng.cam.ac.uk/~sjy/papers/gjkm10.pdf20 Feb 2018: other pointsas a representative of a new region. ... 2005. Reinforcementlearning with Gaussian processes. InICML ’05:Proceedings of the 22nd international conference onMachine learning, pages 201–208, New York, NY. -
Multi-domain Dialog State Tracking using Recurrent Neural Networks…
mi.eng.cam.ac.uk/~sjy/papers/mstg15.pdf20 Feb 2018: The procedure can also be usedto initialise dialog systems for entirely new do-mains. ... Such features facilitate transfer learningbetween slots and allow the system to operate onunseen values or entirely new slots. -
Cross-Lingual Spoken Language Understanding from Unaligned Data…
mi.eng.cam.ac.uk/~sjy/papers/lemy10.pdf20 Feb 2018: However, de-veloping a statistical SLU module for a new language remainscostly, as it typically requires a large data collection phase. ... 5. ConclusionThis paper has investigated methods for bootstrapping an SLUcomponent in a new target language from -
Learning Domain-Independent Dialogue Policies via…
mi.eng.cam.ac.uk/~sjy/papers/wsws15.pdf20 Feb 2018: Moreover, in many cases,one will need a basic (e.g. rule-based) workingSDS to be built before starting the data collectionprocedure, whereas developing the initial systemfor a new domain requires ... It will be undoubtedly beneficial to SDS de-velopment -
poyosp08
mi.eng.cam.ac.uk/~sjy/papers/dpyo08.pdf20 Feb 2018: Because of the inability to properly control the. pharingoesophageal segment acting as the new voice source. ... 3) where dN is the new duration, dP is the predicted duration, dO. -
Incremental on-line adaptation of POMDP-based dialogue managers…
mi.eng.cam.ac.uk/~sjy/papers/gktb14.pdf20 Feb 2018: Therefore, everytime a new attribute is added the dialogue manager must adjustits behaviour. ... In order to do that, the similarity is com-puted between the new attribute and each existing attribute bycomparing cardinalities. -
SPOKEN LANGUAGE UNDERSTANDING FROM UNALIGNED DATA USINGDISCRIMINATIVE …
mi.eng.cam.ac.uk/~sjy/papers/mgjk09.pdf20 Feb 2018: in the dialogue domain as category/valuepairs (e.g., CITY = New York; see Section 2.3). ... Boston New Yorkflight(toloc citycity_name-0). classifier. (flighttoloc). classifier. (toloccitycity_name-1). classifier. (tolocstatestate_name-1). classifier. -
Counter-fitting Word Vectors to Linguistic Constraints Nikola…
mi.eng.cam.ac.uk/~sjy/papers/motg16.pdf20 Feb 2018: A new fea-ture of this version is that it assigns relationtypes to its word pairs. ... 2012. Excitatoryor inhibitory: A new semantic orientation extracts con-tradiction and causality from the Web. -
Toward Multi-domain Language Generation usingRecurrent Neural…
mi.eng.cam.ac.uk/~sjy/papers/wgmr15.pdf20 Feb 2018: We also tested whether generatorscan be extended to a new, unseen domain by using only a limited amount of in-domain data. ... Goodfellow, Arnaud Bergeron,Nicolas Bouchard, and Yoshua Bengio. Theano: new features and speed improvements.
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.