• Publications
  • Influence
Building DNN acoustic models for large vocabulary speech recognition
TLDR
Deep neural networks (DNNs) are now a central component of nearly all state-of-the-art speech recognition systems. Expand
  • 58
  • 3
  • PDF
Proceedings of the 23rd International Conference on Computational Linguistics: Posters
TLDR
You will find in this volume papers from the 23rd International Conference on Computational Linguistics (COLING 2010) held in Beijing, China on August 23-27, 2010 under the auspices of the ICCL, and organized by the Chinese Information Processing Society (CIPS). Expand
  • 12
  • 1
Spelling Correction and theNoisy Channel
ALGERNON: But my own sweet Cecily, I have never written you any letters. CECILY: You need hardly remind me of that, Ernest. I remember only too well that I was forced to write your letters for you. IExpand
  • 7
  • 1
  • PDF
Assessing the accuracy of automatic speech recognition for psychotherapy
TLDR
We show that automatic speech recognition is feasible in psychotherapy, but further improvements are needed before widespread use. Expand
  • 7
Classification : Naive Bayes , Logistic Regression , Sentiment
Numquam ponenda est pluralitas sine necessitate 'Plurality should never be proposed unless needed' William of Occam Classification lies at the heart of both human and machine intelligence. DecidingExpand
  • 9
  • PDF
Issues in relating syntax and semantics
TLDR
The design of a natural language understanding system is dependent on a rich and structured knowledge representation. Expand
  • 6
Querying Complex Networks in Vector Space
TLDR
We introduce a framework to make predictions about conjunctive logical queries---i.e., subgraph relationships---on heterogeneous network data, which can involve the logical conjunction of several edge relationships. Expand
  • 6
Cognition and Function in Language
TLDR
Preface 1. From core to periphery: a study on the directionality of syntactic change in Japanese 2. On the extension of body- part nouns to object-part nouns and spatial adpositions 3. Noun classes: language change and learning 4. Multifunctionality: the developmental path of the quotative tte in Japanese 5. Suppletion in the paradigms of copula verbs. Expand
  • 35
Latent semantic analysis as a tool to improve automatic speech recognition performance
TLDR
This thesis explores the use of Latent Semantic Analysis to augment an N-gram language model to improve the accuracy of a large vocabulary speech recognition system. Expand
  • 6
UNL based Document Summarization based on Level of Users
The primary goal is to develop an NLP system to perform automatic document summarization by converting the English sentences into the expressions of an Interlingua called Universal NetworkingExpand
  • 4