| 1 |
Brief Stimulus Exposure Fully Remediates Temporal Processing Deficits Induced by Early Hearing Loss
|
|
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Multi-domain joint semantic frame parsing using bi-directional RNN-LSTM,” in INTERSPEECH
|
|
|
|
In: https://www.microsoft.com/en-us/research/wp-content/uploads/2016/06/IS16_MultiJoint.pdf (2016)
|
|
Abstract:
Abstract Sequence-to-sequence deep learning has recently emerged as a new paradigm in supervised learning for spoken language understanding. However, most of the previous studies explored this framework for building single domain models for each task, such as slot filling or domain classification, comparing deep learning based approaches with conventional ones like conditional random fields. This paper proposes a holistic multi-domain, multi-task (i.e. slot filling, domain and intent detection) modeling approach to estimate complete semantic frames for all user utterances addressed to a conversational system, demonstrating the distinctive power of deep learning methods, namely bi-directional recurrent neural network (RNN) with long-short term memory (LSTM) cells (RNN-LSTM) to handle such complexity. The contributions of the presented work are three-fold: (i) we propose an RNN-LSTM architecture for joint modeling of slot filling, intent determination, and domain classification; (ii) we build a joint multi-domain model enabling multi-task deep learning where the data from each domain reinforces each other; (iii) we investigate alternative architectures for modeling lexical context in spoken language understanding. In addition to the simplicity of the single model framework, experimental results show the power of such an approach on Microsoft Cortana real user data over alternative methods based on single domain/task deep learning.
|
|
URL: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1052.8228
|
|
BASE
|
|
Hide details
|
|
|
| 3 |
EVALUATION OF THE SIGNAL-TO-NOISE RATIO REQUIRED TO ACHIEVE THE SAME PERFORMANCE IN ENGLISH AND MANDARIN CHINESE
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Semi-supervised learning of semantic classes for query . . .
|
|
|
|
In: http://research.microsoft.com/pubs/101154/fp0894-wang-webpost.pdf (2009)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Acero: A discriminative training framework using N-best speech recognition transcriptions and scores for spoken utterance classification
|
|
|
|
In: http://www1.icsi.berkeley.edu/~sibel/ICASSP2007SUC.pdf (2007)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
SGStudio: Rapid Semantic Grammar Development for Spoken Language Understanding
|
|
|
|
In: http://research.microsoft.com/pubs/60452/2005-wang-acero-eurospeech.pdf (2005)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Grammar Inference and Statistical Machine Translation
|
|
|
|
In: http://www.is.cs.cmu.edu/papers/speech/phd-thesis/thesis-yyw.ps.gz (1998)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Decoding Algorithm in Statistical Machine Translation
|
|
|
|
In: http://www.ri.cmu.edu/pub_files/pub1/wang_ye_yi_1997_1/wang_ye_yi_1997_1.ps.gz (1997)
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Word Clustering With Parallel Spoken Language Corpora
|
|
|
|
In: http://research.microsoft.com/users/yeyiwang/publications/icslp96.ps (1996)
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Word Clustering With Parallel Spoken Language Corpora
|
|
|
|
In: http://www.ubka.uni-karlsruhe.de/vvv/1996/informatik/66/66.ps.gz (1996)
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Word clustering with parallel spoken language corpora
|
|
|
|
In: http://www.ri.cmu.edu/pub_files/pub1/wang_ye_yi_1996_1/wang_ye_yi_1996_1.pdf (1996)
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Word clustering with parallel spoken language corpora
|
|
|
|
In: http://research.microsoft.com/pubs/75238/1996-yeyiwang-icslp.pdf (1996)
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Word Clustering With Parallel Spoken Language Corpora
|
|
|
|
In: http://www.asel.udel.edu/icslp/cdrom/vol4/687/a687.pdf (1996)
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Improved Language Modeling By Unsupervised Acquisition Of Structure
|
|
|
|
In: ftp://ftp.cs.cmu.edu/afs/cs/project/cmt-38/ries/ftp/ries_buo_wang_icassp95.ps.gz (1995)
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Improved Language Modeling By Unsupervised Acquisition Of Structure
|
|
|
|
In: http://werner.ira.uka.de/papers/speech/1995/ICASSP_95_klaus_ries.ps.gz (1995)
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Connectionist Transfer in Machine Translation
|
|
|
|
In: http://research.microsoft.com/users/yeyiwang/publications/ranlp95.ps (1995)
|
|
BASE
|
|
Show details
|
|
|
| 20 |
Dual-coding theory and connectionist lexical selection
|
|
|
|
In: http://arxiv.org/pdf/cmp-lg/9405035v1.pdf (1994)
|
|
BASE
|
|
Show details
|
|
|
|
|
