Báo cáo khoa học: "Cutting the Long Tail: Hybrid Language Models for Translation Style Adaptation" doc
... to their class just before querying the hybrid LM, therefore translation models can be trained on plain un-tagged data. As exemplified in Table 4, hybrid LMs can draw useful statistics on the ... - 27 2012. c 2012 Association for Computational Linguistics Cutting the Long Tail: Hybrid Language Models for Translation Style Adaptation Arianna Bisazza and Marcello...
Ngày tải lên: 08/03/2014, 21:20
... must occur at the other end, which is situated in the other tree of the same tree pair. Thus if the tree for John in a7 is substituted at E] in the left tree of a6, the tree for Jean must ... level specifies the grouping or structure of these trees. Then the mapping takes place on these structures, rather than the object-level trees; hence the need for a gra...
Ngày tải lên: 08/03/2014, 06:20
... implicitly adopted the position that their user's input encodes a request for intormation of; action, and that their job is tO decode the request, retrieve the information, or perform the action, ... situations, the listener's interpretations may be other than the speaker intends, and speakers may compensate for such distortions in the way they construct their...
Ngày tải lên: 24/03/2014, 01:21
Báo cáo khoa học: "Discovering the Discriminative Views: Measuring Term Weights for Sentiment Analysis" doc
... dif- ferences. For the TREC dataset, BM25 performed better than the other models, and for the NTCIR dataset, VS performed better. Our features of the topic association model show mild improvement over the ... mea- sures. Among the topic association models, PMI performs the best in MAP and R-prec, while WP achieved the biggest improvement in P@10. Since BM25 performs the...
Ngày tải lên: 30/03/2014, 23:20
Tài liệu Báo cáo khoa học: "Word representations: A simple and general method for semi-supervised learning" doc
... vocabulary words. They perform hard clustering using the Viterbi algorithm. (Alternately, they could keep the soft clustering, with the representation for a particular word token being the posterior ... understand if the infor- mation they provide mostly overlaps with that of the word representations. After each epoch over the training set, we measured the accuracy of the...
Ngày tải lên: 20/02/2014, 04:20
Tài liệu Báo cáo khoa học: "An Affect-Enriched Dialogue Act Classification Model for Task-Oriented Dialogue" doc
... Indicator for the display of the brow lowerer within 1 second prior to this utterance being sent, for the most recent three utterances • AU4_5sec: Indicator for the display of the brow lowerer ... confusion. 1194 Figure 2. Other facial expressions from the corpus 5 Models The goal of the modeling experiment was to de- termine whether the addition o...
Ngày tải lên: 20/02/2014, 04:20
Tài liệu Báo cáo khoa học: "You’ve Got Answers: Towards Personalized Models for Predicting Success in Community Question Answering" doc
... delay the question appears in the respective category list of open questions. At this point, other users can answer the question, vote on other users’ answers, or interact in other ways. The asker ... un- known if the asker’s information need was satisfied. Based on our exploration we believe that the main reasons for not “closing” a question are a) the asker loses interest in...
Ngày tải lên: 20/02/2014, 09:20
Tài liệu Báo cáo khoa học: "Towards History-based Grammars: Using Richer Models for Probabilistic Parsing*" docx
... model. For the mo- ment, we are using n-gram models with the usual deleted interpolation for smoothing for the other four components of the model. We have assigned bit strings to the syntactic ... sentences for which the correct parse is proposed among the many parses that the gram- mar provides for a sentence. We also measure the parse base, which is defi...
Ngày tải lên: 20/02/2014, 21:20
Báo cáo khoa học: "Faster and Smaller N -Gram Language Models" pptx
... ˆw n−1 1 is the the longest suffix of w n−1 1 contained in the language model. We can then quickly form the context encoding of the next query by simply concatenating the new word with the off- set ... return the value stored in the cache. Otherwise, we fetch the lan- guage model probability from the language model and place the new key and value in the cache, evict...
Ngày tải lên: 07/03/2014, 22:20
Báo cáo khoa học: "Hierarchical Reinforcement Learning and Hidden Markov Models for Task-Oriented Natural Language Generation" ppt
... steps. The random variable τ represents the number of time steps the agent takes to complete a subtask. Actions can be either primitive or composite. The former yield sin- gle rewards, the latter ... derived from the Forward algorithm, of an observation sequence to inform the agent’s learning process. r = 0 for reaching the goal stat...
Ngày tải lên: 07/03/2014, 22:20