Báo cáo khoa học: "Understanding Unsegmented User Utterances in Real-Time Spoken Dialogue Systems" doc

Báo cáo khoa học: "Understanding Unsegmented User Utterances in Real-Time Spoken Dialogue Systems" doc

Báo cáo khoa học: "Understanding Unsegmented User Utterances in Real-Time Spoken Dialogue Systems" doc

... Understanding Unsegmented User Utterances in Real-Time Spoken Dialogue Systems Mikio Nakano, Noboru Miyazaki, Jun-ichi Hirasawa, Kohji Dohsaka, Takeshi Kawabata* NTT Laboratories 3-1 Morinosato-Wakamiya, ... for incrementally un- derstanding user utterances whose semantic bound- aries are not known and responding in real time even before boundaries are determined. I...
Ngày tải lên : 17/03/2014, 07:20
  • 8
  • 448
  • 0
Báo cáo khoa học: "Automatically Identifying Problematic Dialogues in DARPA Communicator Dialogue Systems" pot

Báo cáo khoa học: "Automatically Identifying Problematic Dialogues in DARPA Communicator Dialogue Systems" pot

... training a Problematic Di- alogue Identifier to classify problematic human-computer dialogues using a corpus of 1242 DARPA Communicator dialogues in the travel planning domain. We show that using ... segment: I’ve got you leaving from Minto, Arkansas on Fri- day, October twelfth in the morning and arriving in newark flying on continental. Is this correct? U16: NO I WANT TO LEAVE FROM MINN...
Ngày tải lên : 08/03/2014, 07:20
  • 8
  • 184
  • 0
Tài liệu Báo cáo khoa học: "UNDERSTANDING NATURAL LANGUAGE INSTRUCTIONS: THE CASE OF PURPOSE CLAUSES" doc

Tài liệu Báo cáo khoa học: "UNDERSTANDING NATURAL LANGUAGE INSTRUCTIONS: THE CASE OF PURPOSE CLAUSES" doc

... one single plan for get x,. in which case go into the other room may in fact help to select the plan the instructor has in mind. 123 plements the two kinds of accommodation described in the ... adjoined to NPs. In contrast, the infinitival clauses I have concentrated on are adjoined to a matrix clause, and are termed rational clauses in syntax; in fact all the data I wil...
Ngày tải lên : 20/02/2014, 21:20
  • 8
  • 458
  • 0
Báo cáo khoa học: "RESPONDING TO USER QUERIES IN A COLLABORATIVE ENVIRONMENT*" docx

Báo cáo khoa học: "RESPONDING TO USER QUERIES IN A COLLABORATIVE ENVIRONMENT*" docx

... be made to the existing plan. 1 Introduction In task-oriented consultation dialogues, the user and ex- pert jointly construct a plan for achieving the user& apos;s goal. In such an environment, ... agents work on developing different plans. We are extending the dialogue under- standing system in [6] to include a system that responds to the user& apos;s utterances in a col...
Ngày tải lên : 31/03/2014, 06:20
  • 3
  • 352
  • 0
Tài liệu Báo cáo khoa học: Domain deletions and substitutions in the modular protein evolution doc

Tài liệu Báo cáo khoa học: Domain deletions and substitutions in the modular protein evolution doc

... at least once in the same protein, most domains have few partner domains, or are even always singletons [3,7–9]. Well-known examples of highly linked domains occur- ring in many different combinations ... neighbouring domains substitution a domain is replaced by another domain that bears no similarity with the original domain shadow domain at a given position, in one protein there is a...
Ngày tải lên : 19/02/2014, 07:20
  • 11
  • 608
  • 0
Tài liệu Báo cáo khoa học: "Neutralizing Linguistically Problematic Annotations in Unsupervised Dependency Parsing Evaluation" doc

Tài liệu Báo cáo khoa học: "Neutralizing Linguistically Problematic Annotations in Unsupervised Dependency Parsing Evaluation" doc

... Parsing. In Proc. of ACL. Valentin I. Spitkovsky, Hiyan Alshawi, Daniel Jurafsky and Christopher D. Manning, 2010c. Viterbi training improves unsupervised dependency parsing. In Proc. of CoNLL. Qin ... Dekang Lin, 2005. Strictly Lexical Dependency Parsing. In IWPT. Qin Iris Wang, Colin Cherry, Dan Lizotte and Dale Schu- urmans, 2006. Improved Large Margin Dependency Parsing via Local Co...
Ngày tải lên : 20/02/2014, 04:20
  • 10
  • 411
  • 0
Tài liệu Báo cáo khoa học: "Co-training for Predicting Emotions with Spoken Dialogue Data" pdf

Tài liệu Báo cáo khoa học: "Co-training for Predicting Emotions with Spoken Dialogue Data" pdf

... Co-training can be highly effective when a good set of features are chosen. 1 Introduction In this paper we investigate the automatic labeling of spoken dialogue data, in order to train a ... Processing applications often require large amounts of annotated training data, which are expensive to obtain. In this paper we investigate the applicability of Co-training to train clas...
Ngày tải lên : 20/02/2014, 16:20
  • 4
  • 381
  • 0
Tài liệu Báo cáo khoa học: Human intrinsic factor expressed in the plant Arabidopsis thaliana doc

Tài liệu Báo cáo khoa học: Human intrinsic factor expressed in the plant Arabidopsis thaliana doc

... Aarhus, Denmark Intrinsic factor (IF) is the gastric protein that promotes the intestinal uptake of vitamin B 12 . Gastric IF from animal sources is used in diagnostic tests and in vitamin pills. However, ... [2–4]. Intrinsic factor (IF) is responsible for intestinal absorption of vitamin B 12 facilitating its internalization [2,3,5]. Lack or malfunction of this Cbl binder hampers the upt...
Ngày tải lên : 21/02/2014, 00:20
  • 6
  • 492
  • 0
Báo cáo khoa học: Adipocyte hyperplasia and RMI1 in the treatment of obesity doc

Báo cáo khoa học: Adipocyte hyperplasia and RMI1 in the treatment of obesity doc

... triacylglycerol droplets in adipose cells, leading to an increased fat mass and ultimately result- ing in obesity. Adipocyte hyperplasia (increase in cell number) and hypertrophy (increase in cell size) ... cell-cycle-related molecules, including cyclins, cyclin-dependent kinases, their inhib- itors and the retinoblastoma protein (RB), as well as E2Fs. E2F and RB family members appear...
Ngày tải lên : 06/03/2014, 01:20
  • 5
  • 558
  • 0
Báo cáo khoa học: "Annotation Schemes and their Influence on Parsing Results" docx

Báo cáo khoa học: "Annotation Schemes and their Influence on Parsing Results" docx

... non-context-free nature of the original annotation. In both tree- banks, punctuation is not included in the trees, furthermore, sentence splitting in both treebanks does not always coincide with the linguistic no- tion ... put into the test set, all other sentences go into the training set. 4.1 Preprocessing the Treebanks Since we want to read the grammars for our parser directly off th...
Ngày tải lên : 17/03/2014, 04:20
  • 6
  • 331
  • 0

Xem thêm

Từ khóa: