Search
Search Funnelback University
- Refined by:
- Date: 2018
Did you mean economicsadam |u:mi.eng.cam.ac.uk?
1 -
10 of
79
search results for Economics exam |u:mi.eng.cam.ac.uk
where 0
match all words and 79
match some words.
Results that match 1 of 2 words
-
Impact of ASR Performance on Free Speaking Language Assessment ...
mi.eng.cam.ac.uk/~ar527/knill_is2018.pdf15 Jun 2018: Off-topicresponse detection is described in Section 3. Experimental re-. sults on data from real exams are reported in Section 4. ... Data fromnon-native learners of English on the BULATS Business En-glish exam [16] is used for training and test. -
his_uam_slt08.dvi
mi.eng.cam.ac.uk/~sjy/papers/kgmt0820 Feb 2018: For exam-ple, the observation model might not be able to distinguishbetween an acknowledgement and an affirmation for the ut-terance “Yes”, but if the last system act was a -
PHONETIC AND GRAPHEMIC SYSTEMS FOR MULTI-GENRE BROADCASTTRANSCRIPTION …
mi.eng.cam.ac.uk/~ar527/wang_icassp2018.pdf4 Nov 2018: The other three exam-ples illustrate situations where graphemic systems may struggle tomodel letter omission (’r’ in information), vowel (’oo’ in moon),consonant (’th’ in the) and vowel-consonant (’tio’ in ... A more general sys-tem -
Continuously Learning Neural Dialogue Management
mi.eng.cam.ac.uk/~sjy/papers/sgmr16.pdf20 Feb 2018: The hypothesised reason for the loweraccuracy of Query is that the SL training data con-tains robust ASR results and thus the system exam-ples contain more offers and less queries. -
Counter-fitting Word Vectors to Linguistic Constraints Nikola…
mi.eng.cam.ac.uk/~sjy/papers/motg16.pdf20 Feb 2018: For exam-ple, a DST for the restaurant domain needs to detectwhether the user wants a cheap or expensive restau-rant. -
An attention based model for off-topic spontaneous spoken response ...
mi.eng.cam.ac.uk/~ar527/malinin_slate2017.pdf15 Jun 2018: The model is trained on ASR transcriptions of spokenresponses. Due to a lack of off-topic responses, negative exam-ples for both training and evaluation are created by randomlyshuffling prompts and ... is demon-strated on spoken data from the Cambridge -
Cross-Lingual Spoken Language Understanding from Unaligned Data…
mi.eng.cam.ac.uk/~sjy/papers/lemy10.pdf20 Feb 2018: treated as a class because there are not enough exam-ples of individual semantic trees in the data. -
Transformation-based Learning for Semantic parsing F. Jurčı́ček, M. …
mi.eng.cam.ac.uk/~sjy/papers/jgkm09.pdf20 Feb 2018: For exam-ple, the words ”arriving“ and ”Monday“ are neighbours in thedependency tree but they are four words apart in the utterance(see Figure 2). -
Multi-domain Dialog State Tracking using Recurrent Neural Networks…
mi.eng.cam.ac.uk/~sjy/papers/mstg15.pdf20 Feb 2018: For exam-ple, [eat tagged-slot-value food] and [near tagged-slot-value] are clearly features related to food andarea slots respectively. -
PHONETIC AND GRAPHEMIC SYSTEMS FOR MULTI-GENRE BROADCASTTRANSCRIPTION …
mi.eng.cam.ac.uk/~mjfg/ALTA/publications/ICASSP2018_YuWang.pdf12 Sep 2018: The other three exam-ples illustrate situations where graphemic systems may struggle tomodel letter omission (’r’ in information), vowel (’oo’ in moon),consonant (’th’ in the) and vowel-consonant (’tio’ in ... A more general sys-tem
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.