an affectenriched dialogue act classification model

Tài liệu Báo cáo khoa học: "An Affect-Enriched Dialogue Act Classification Model for Task-Oriented Dialogue" doc

Tài liệu Báo cáo khoa học: "An Affect-Enriched Dialogue Act Classification Model for Task-Oriented Dialogue" doc

Ngày tải lên : 20/02/2014, 04:20
... Abstract Dialogue act classification is a central chal- lenge for dialogue systems. Although the im- portance of emotion in human dialogue is widely recognized, most dialogue act classifi- cation ... automatic dialogue act classification modeled dis- course structure with hidden Markov models, ex- perimenting with lexical and prosodic features, and applying the dialogue act model as a constraint ... systems. 2 Background and Related Work 2.1 Dialogue Act Classification Because of the importance of dialogue act classifi- cation within dialogue systems, it has been an ac- tive area of research...
  • 10
  • 426
  • 0
Báo cáo khoa học: "Segmented and unsegmented dialogue-act annotation with statistical dialogue models∗" ppt

Báo cáo khoa học: "Segmented and unsegmented dialogue-act annotation with statistical dialogue models∗" ppt

Ngày tải lên : 08/03/2014, 02:21
... Kompe, H. Niemann, and E. N ¨ oth. 1997. Integrated Dialog Act Segmentation and Classifica- tion using Prosodic Features and Language Models. In Proc. European Conf. on Speech Communication and Technology, ... proposed a method for simultane- ous segmentation and annotation of dialogue ut- terances. In contrast to previous models for this task, our model does not assume manual utterance segmentation. Instead ... computer-to-human dialogues, and the main aim of the task is to answer telephone queries about train timetables, fares, and services for long- distance trains in Spanish. A total of 900 dialogues were...
  • 8
  • 387
  • 0
Báo cáo khoa học: "Recognizing Authority in Dialogue with an Integer Linear Programming Constrained Model" pptx

Báo cáo khoa học: "Recognizing Authority in Dialogue with an Integer Linear Programming Constrained Model" pptx

Ngày tải lên : 23/03/2014, 16:20
... Interspeech. Diane Litman and Kate Forbes-Riley. 2006. Correlations betweeen Dialogue Acts and Learning in Spoken Tu- toring Dialogue. In Natural Language Engineering. Diane Litman, Mihai Rotaru, and Greg ... Lan- guage Tasks. In Proceedings of CoNLL. Emanuel Schegloff. 2007. Sequence Organization in In- teraction: A Primer in Conversation Analysis. Ethan Selfridge and Peter Heeman. 2010. Importance- Driven ... “dominant” - statements of fact or opinion, and commands or instructions - and two that appear less dominant - questions or requests for information, and narration of an action. We sum these together to...
  • 9
  • 442
  • 0
An introduction to disk drive modeling

An introduction to disk drive modeling

Ngày tải lên : 12/09/2012, 14:16
... next most important features to get right are the data transfer model, including overlaps between mechanism activity and the bus transfers (20 percent demerit), and the seek- time and head-switching ... buses. Bruce Worthington and Greg Ganger at the University of Michigan took this approach and managed to fine-tune the controller-overhead and bus-transfer components of a model similar to ours. ... producer-consumer interlocks between the mechanism and bus transfers. • Data layout model: reserved sparing areas, including both sector- and track-based models, zoning, and track and cylinder skew. • Head movement...
  • 19
  • 1.1K
  • 0
Tài liệu IDENTIFICATION OF AN UNKNOWN ORGANIC COMPOUND: Classification Tests ppt

Tài liệu IDENTIFICATION OF AN UNKNOWN ORGANIC COMPOUND: Classification Tests ppt

Ngày tải lên : 14/02/2014, 08:20
... by the rate of reaction with the the Lucas reagent to form an alkyl chloride. Tertiary alcohols react immediately and form a cloudy solution. Secondary alcohols usually react to form a cloudy ... 10-20mL of NaHCO 3 solution. IDENTIFICATION OF AN UNKNOWN ORGANIC COMPOUND Classification Tests In this experiment you will attempt to identify an organic unknown from a selected group of compounds ... have been added. Note any color change. Place a piece of moist litmus paper (blue) in the vapor space and note any indication of HBr, which would indicate a substitution reaction instead of addition....
  • 6
  • 401
  • 0
Tài liệu Báo cáo khoa học: "Semantic Information and Derivation Rules for Robust Dialogue Act Detection in a Spoken Dialogue System" pptx

Tài liệu Báo cáo khoa học: "Semantic Information and Derivation Rules for Robust Dialogue Act Detection in a Spoken Dialogue System" pptx

Ngày tải lên : 20/02/2014, 05:20
... language under- standing (SLU) module converts W t to an abstract representation of the user’s dialogue act (DA). The dialogue management (DM) module determines the user’s dialogue act A ∗ t and ... constructed model is then used to generate a semantic score for dialogue act detection given an input speech utterance. The proposed approach is implemented and evalu- ated in aMandarin spoken dialogue ... out- put sentence. Semantic information and the derivation rules of the partial sentence trees are extracted and used to model the relation- ship between the dialogue acts and the deriva- tion...
  • 6
  • 555
  • 0
Tài liệu Báo cáo khoa học: "An ISU Dialogue System Exhibiting Reinforcement Learning of Dialogue Policies: Generic Slot-filling in the TALK In-car System" pot

Tài liệu Báo cáo khoa học: "An ISU Dialogue System Exhibiting Reinforcement Learning of Dialogue Policies: Generic Slot-filling in the TALK In-car System" pot

Ngày tải lên : 22/02/2014, 02:20
... pol- icy, or can be called only in certain circumstances. This makes it usable for whole dialogue strategies, but also, if desired, it can be targetted only on specific dialogue management decisions ... slots via their importance f or an application. In order to do this we define the mappings shown in table 2 between COMM UN ICATOR dialogue actions and in-car dialo gue actions, for each sub-task ... mul- timodal dialogue management, and also to test and fur- ther develop learnt dialogue strategies in a realistic ap- plication scenario. For these reasons we have built a system which: contains an interface...
  • 4
  • 394
  • 0
Báo cáo khoa học: " Extending Latent Semantic Analysis with features for dialogue act classification" pot

Báo cáo khoa học: " Extending Latent Semantic Analysis with features for dialogue act classification" pot

Ngày tải lên : 08/03/2014, 04:22
... state- ment, question, answer) plus the two tags ‘‘%’’ for abandoned sentences and ‘‘x’’ for noise. CallHome Spanish is further annotated for dialogue games and activities. Dialogue game annotation is based ... Feature Latent Semantic Analysis (FLSA) as an extension to Latent Seman- tic Analysis (LSA). LSA can be thought as repre- senting the meaning of a word as a kind of average of the meanings of all ... rates between 33% and 52%, and FLSA reduces error rates between 60% and 78%. LSA is an attractive method for this task because it is straightforward to train and use. More impor- tantly, although...
  • 8
  • 409
  • 0
Báo cáo khoa học: "Utilizing Statistical Dialogue Act Processing in Verbmobil" pptx

Báo cáo khoa học: "Utilizing Statistical Dialogue Act Processing in Verbmobil" pptx

Ngày tải lên : 08/03/2014, 07:20
... ers dialogue acts which can appear at any point of the dialogue, as e.g. DELIBERATE and clarification dialogues (CLARIFY_QUERY and CLARIFY-ANSWER). We handle these dialogue acts by means ... independent dialogue acts and the transition networks which define admis- sible sequences of dialogue acts. In addition to the dialogue acts in the main dialogue network, there are five dialogue acts, ... spotter. Additional dialogue act readings can be proposed and the dialogue history can be changed accordingly. Currently, the dialogue component processes more than 200 annotated dialogues from...
  • 6
  • 225
  • 0
Báo cáo khoa học: "Dialogue Act Tagging for Instant Messaging Chat Sessions" potx

Báo cáo khoa học: "Dialogue Act Tagging for Instant Messaging Chat Sessions" potx

Ngày tải lên : 17/03/2014, 06:20
... Australia edwardi@csse.unimelb.edu.au Abstract Instant Messaging chat sessions are real- time text-based conversations which can be analyzed using dialogue- act models. We describe a statistical approach for modelling and detecting dialogue ... previous dialogue act or previ- ous 2 dialogue acts in the case of the trigram model. 1 Due to space constraints, the dialogue act transition ta- ble has been omitted from this paper and is made ... messages. Utterance boundaries and their respective dialogue acts are denoted by U n . 2 Issues in Instant Messaging Dialogue There are several differences between IM and tran- scribed spoken dialogue. ...
  • 6
  • 314
  • 0
Báo cáo khoa học: "Data-Driven Strategies for an Automated Dialogue System" potx

Báo cáo khoa học: "Data-Driven Strategies for an Automated Dialogue System" potx

Ngày tải lên : 23/03/2014, 19:20
... of human-human dialogues and from dialogues gathered using a text-based version of the human-computer system. Using this version we collected around 100 dialogues and annotated important domain-specific ... real human-human calls. For advanced speech recognition, we hope to train our ASR on new acoustic data. We also plan to expand our dialogue act classification so that the system can recognize ... transcribed, labeled human-human calls, and we have used vector- based classification techniques. Two differences from the task identifier are 1) an utterance may have multiple correct classifications,...
  • 8
  • 336
  • 0
Báo cáo khoa học: "An Improved Extraction Pattern Representation Model for Automatic IE Pattern Acquisition" ppt

Báo cáo khoa học: "An Improved Extraction Pattern Representation Model for Automatic IE Pattern Acquisition" ppt

Ngày tải lên : 23/03/2014, 19:20
... compar- ing the performance of the earlier extraction pattern models to the proposed Subtree Model (SUBT). The compared models are the direct predicate-argument model (PA) 9 , and the Chain model (CH) in ... Satoshi Sekine, and Ralph Grishman. 2001. Automatic Pattern Acquisition for Japanese In- formation Extraction. In Proceedings of the Human Language Technology Conference (HLT2001). Roman Yangarber, ... Stage 3: Ranking Pattern Candidates Given the dependency trees of parsed sentences in the relevant document set, all the possible subtrees can be candidates for extraction patterns. The rank- ing...
  • 8
  • 209
  • 0

Xem thêm