Báo cáo khoa học: "Learning More Effective Dialogue Strategies Using Limited Dialogue Move Features" ppt

... July 2006. c 2006 Association for Computational Linguistics Learning More Effective Dialogue Strategies Using Limited Dialogue Move Features Matthew Frampton and Oliver Lemon HCRC, School of Informatics University ... the user’s last dialogue move to the state. • Strategy 3 (USDM) was learned by adding both the user and system’s last dialogue moves to the state. The pos...

Ngày tải lên: 17/03/2014, 04:20

... predicting breaks other than those already indicated by intra-sentential punctuation, however, appears to be more challenging. 1 Introduction Any text-to-speech (TTS) system that aims at pro- ducing understandable ... right locations (and may involve tune choice as well). Pitch accents correspond roughly to pitch movements that lend emphasis to certain words in an utterance. Prosodic breaks...

Ngày tải lên: 17/03/2014, 06:20

... of the term can not be measured using contextual information 3. Specificity Measuring Methods In this section, we describe information theory like methods using compositional and contextual ... is more infor- mative than frequency of words. Method 2 showed the best performance, preci- sion 70.0% and coverage 70.2%, when we counted modifiers which modify the target terms two or...

Ngày tải lên: 08/03/2014, 04:22

... Experimental setup All parse experiments are performed using 10-fold cross-validation for training and testing. Overall parsing accuracy will be reported using the stan- dard metrics of labeled attachment ... trained on the same data set, but a grammar- driven parser outputing a deep LFG analysis. We furthermore show how a range of other features – morphological, structural and semantic –...

Ngày tải lên: 17/03/2014, 02:20

... syntactic phenomena like constituent movement (e.g. wh- extraction), discontinuous constituents, and miss- ing elements (PRO elements, empty complemen- tizers and relative pronouns). Moved constituents are ... with a trace which is located at the position where the moved constituent is to be interpreted. Figure 1 shows an example of con- stituent movement in a relative clause. Empty categorie...

Ngày tải lên: 17/03/2014, 04:20

... this kind will probably offer more coverage (and hence lower accuracy) than is desirable for any given spe- cific application. It is however feasible to address the problem using corpus-based techniques ... representations. This is done using a left-corner parser representation of the grammar. 2. The treebank is used to produce a specialised grammar in REGULUS format, using the EBL alg...

Ngày tải lên: 17/03/2014, 06:20

... automat- ically learning effective dialogue strategies, generated from a library of dialogue content, using reinforcement learning from user feed- back. This library includes greetings, so- cial dialogue, chit-chat, ... learning of effective dialogue strategies for information seeking spo- ken dialogue systems, and in particular the use of reinforcement learning methods to...

Ngày tải lên: 20/02/2014, 12:20

... April 2009. c 2009 Association for Computational Linguistics Learning to Interpret Utterances Using Dialogue History David DeVault Institute for Creative Technologies University of Southern California Marina ... of situated task-oriented dialogue. The system accu- mulates training examples for ambiguity resolution by tracking the fates of alter- native interpretations across dialogue,...

Ngày tải lên: 08/03/2014, 21:20

... recommendation strategies using reinforcement learning (Rieser and Lemon, 2009; Hernandez et al., 2003; Rieser and Lemon, 2010), and joint optimisation of Dialogue Management and NLG using hierarchical ... the time taken to com- plete each dialogue task. We used these data to build a regression model to calculate total dialogue time for dialogue simulations. The strategies wer...

Ngày tải lên: 16/03/2014, 23:20

... (M(h ∗ )  M(h)): remove h from L 6: else if (M(h)  M(h ∗ )): remove h from L; set h ∗ = h 7: end for 8: Add h ∗ to Frontier Set F 9: for each h in L do 10: if (M(h ∗ )  M(h)): remove h from L 11: ... metrics. We also discuss the issue of metric tunability and show that our Pareto approach is more effective in incorporating new metrics from MT evaluation for MT optimization. 1 Introduct...

Ngày tải lên: 19/02/2014, 19:20