#### Filter Results:

- Full text PDF available (10)

#### Publication Year

2006

2012

- This year (0)
- Last 5 years (6)
- Last 10 years (9)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

#### Key Phrases

Learn More

- Darcey Riley, Daniel Gildea
- ACL
- 2012

Bayesian approaches have been shown to reduce the amount of overfitting that occurs when running the EM algorithm, by placing prior probabilities on the model parameters. We apply one such Bayesian technique, variational Bayes, to the IBM models of word alignment for statistical machine translation. We show that using variational Bayes improves the… (More)

- D. Riley, X. Koutsoukos, K. Riley
- 2007 Mediterranean Conference on Control…
- 2007

Modeling and analysis of chemical reactions are critical problems because they can provide new insights into the complex interactions between systems of reactions and chemicals. One such set of chemical reactions defines the creation of biodiesel from soybean oil and methanol. Modeling and analyzing the biodiesel creation process is a challenging problem… (More)

- Kenji Sagae, Maider Lehr, +16 authors Darcey Riley
- 2012 IEEE International Conference on Acoustics…
- 2012

This paper investigates semi-supervised methods for discriminative language modeling, whereby n-best lists are “hallucinated” for given reference text and are then used for training n-gram language models using the perceptron algorithm. We perform controlled experiments on a very strong baseline English CTS system, comparing three methods for… (More)

- Arda Çelebi, Hasim Sak, +19 authors Darcey Riley
- 2012 IEEE International Conference on Acoustics…
- 2012

We present our work on semi-supervised learning of discriminative language models where the negative examples for sentences in a text corpus are generated using confusion models for Turkish at various granularities, specifically, word, sub-word, syllable and phone levels. We experiment with different language models and various sampling strategies to select… (More)

Bayesian approaches have been shown to reduce the amount of overfitting that occurs when running the EM algorithm, by placing prior probabilities on the model parameters. We apply one such Bayesian technique, variational Bayes, to GIZA++, a widely-used piece of software that computes word alignments for statistical machine translation. We show that using… (More)

- D Riley, X Koutsoukos, K Riley
- IET systems biology
- 2009

Modelling and analysis of biochemical systems such as sugar cataract development (SCD) are critical because they can provide new insights into systems, which cannot be easily tested with experiments; however, they are challenging problems due to the highly coupled chemical reactions that are involved. The authors present a stochastic hybrid system (SHS)… (More)

- Puyang Xu, Sanjeev Khudanpur, +16 authors Darcey Riley
- 2012 IEEE International Conference on Acoustics…
- 2012

Discriminative language modeling is a structured classification problem. Log-linear models have been previously used to address this problem. In this paper, the standard dot-product feature representation used in log-linear models is replaced by a non-linear function parameterized by a neural network. Embeddings are learned for each word and features are… (More)

- X. Koutsoukos, D. Riley
- 2006 Proceeding of the Thirty-Eighth Southeastern…
- 2006

Stochastic hybrid system models can be used to analyze and design complex embedded systems that operate in the presence of uncertainty and variability. Verification of safety properties of such systems is a critical problem because of the interaction between the discrete and continuous stochastic dynamics. In this paper, we propose a probabilistic method… (More)

- Damianos Karakos, Brian Roark, +17 authors Darcey Riley
- INTERSPEECH
- 2012

The perceptron algorithm was used in [1] to estimate discriminative language models which correct errors in the output of ASR systems. In its simplest version, the algorithm simply increases the weight of n-gram features which appear in the correct (oracle) hypothesis and decreases the weight of n-gram features which appear in the 1-best hypothesis. In this… (More)

- Darcey Riley
- 2012

Parsing is the process of inferring the syntactic structure of a sentence, based on a model of syntax that specifies which sentences are possible or likely. The field of statistical parsing concerns itself with learning probabilistic syntactic models from corpora. Ideally, it should be possible to parse any grammatical sentence of any natural language.… (More)

- ‹
- 1
- ›