Jiri Navratil
Research Subjects
Jiri Navratil has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Ganesh N. Ramaswamy
Conversational Biometrics and Multimedia Mining Group, Human Language Technologies Department, IBM T.J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, NY, USA 10598
3 shared publications - Jason Pelecanos
IBM Thomas J. Watson Research Center
3 shared publications Alan King
IBM Research
1 shared publication- Alan King
IBM Research
1 shared publication - Andres Codas
Microsoft Research
1 shared publication Andrés Codas
IBM Research
1 shared publication
Latest Publications
- Open Access
Uncertainty Prediction for Deep Sequential Regression Using Meta Models
Generating high quality uncertainty estimates for sequential regression, particularly deep recurrent networks, remains a challenging and open problem. Existing approaches often make restrictive assumptions (such as stationarity) yet still perform poorly in practice, particularly in presence of real world non-stationary signals and drift. This paper describes a flexible method that can generate symmetric and asymmetric uncertainty estimates, makes no assumptions about stationarity, and outperforms competitive baselines on both drift and non drift scenarios. This work helps make sequential regression more effective and practical for use in real-world applications, and is a powerful new addition to the modeling toolbox for sequential uncertainty quantification in general.
Open AccessUncertainty Prediction for Deep Sequential Regression Using Meta Models
Generating high quality uncertainty estimates for sequential regression, particularly deep recurrent networks, remains a challenging and open problem. Existing approaches often make restrictive assumptions (such as stationarity) yet still perform poorly in practice, particularly in presence of real world non-stationary signals and drift. This paper describes a flexible method that can generate symmetric and asymmetric uncertainty estimates, makes no assumptions about stationarity, and outperforms competitive baselines on both drift and non drift scenarios. This work helps make sequential regression more effective and practical for use in real-world applications, and is a powerful new addition to the modeling toolbox for sequential uncertainty quantification in general.
- Open Access
- 20 September 2019
- Published by Frontiers Media SA in Frontiers in Big Data
- Vol. 2
Accelerating Physics-Based Simulations Using End-to-End Neural Network Proxies: An Application in Oil Reservoir Modeling
We develop a proxy model based on deep learning methods to accelerate the simulations of oil reservoirs–by three orders of magnitude–compared to industry-strength physics-based PDE solvers. This paper describes a new architectural approach to this task modeling a simulator as an end-to-end black box, accompanied by a thorough experimental evaluation on a publicly available reservoir model. We demonstrate that in a practical setting a speedup of more than 2000X can be achieved with an average sequence error of about 10% relative to the simulator. The task involves varying well locations and varying geological realizations. The end-to-end proxy model is contrasted with several baselines, including upscaling, and is shown to outperform these by two orders of magnitude. We believe the outcomes presented here are extremely promising and offer a valuable benchmark for continuing research in oil field development optimization. Due to its domain-agnostic architecture, the presented approach can be extended to many applications beyond the field of oil and gas exploration.
- 20 September 2019
- Published by Frontiers Media SA in Frontiers in Big Data
- Vol. 2
Open AccessAccelerating Physics-Based Simulations Using End-to-End Neural Network Proxies: An Application in Oil Reservoir Modeling
We develop a proxy model based on deep learning methods to accelerate the simulations of oil reservoirs–by three orders of magnitude–compared to industry-strength physics-based PDE solvers. This paper describes a new architectural approach to this task modeling a simulator as an end-to-end black box, accompanied by a thorough experimental evaluation on a publicly available reservoir model. We demonstrate that in a practical setting a speedup of more than 2000X can be achieved with an average sequence error of about 10% relative to the simulator. The task involves varying well locations and varying geological realizations. The end-to-end proxy model is contrasted with several baselines, including upscaling, and is shown to outperform these by two orders of magnitude. We believe the outcomes presented here are extremely promising and offer a valuable benchmark for continuing research in oil field development optimization. Due to its domain-agnostic architecture, the presented approach can be extended to many applications beyond the field of oil and gas exploration.
- Open Access
Accelerating Physics-Based Simulations Using Neural Network Proxies: An Application in Oil Reservoir Modeling
We develop a proxy model based on deep learning methods to accelerate the simulations of oil reservoirs--by three orders of magnitude--compared to industry-strength physics-based PDE solvers. This paper describes a new architectural approach to this task, accompanied by a thorough experimental evaluation on a publicly available reservoir model. We demonstrate that in a practical setting a speedup of more than 2000X can be achieved with an average sequence error of about 10\% relative to the oil-field simulator. The proxy model is contrasted with a high-quality physics-based acceleration baseline and is shown to outperform it by several orders of magnitude. We believe the outcomes presented here are extremely promising and offer a valuable benchmark for continuing research in oil field development optimization. Due to its domain-agnostic architecture, the presented approach can be extended to many applications beyond the field of oil and gas exploration.
Open AccessAccelerating Physics-Based Simulations Using Neural Network Proxies: An Application in Oil Reservoir Modeling
We develop a proxy model based on deep learning methods to accelerate the simulations of oil reservoirs--by three orders of magnitude--compared to industry-strength physics-based PDE solvers. This paper describes a new architectural approach to this task, accompanied by a thorough experimental evaluation on a publicly available reservoir model. We demonstrate that in a practical setting a speedup of more than 2000X can be achieved with an average sequence error of about 10\% relative to the oil-field simulator. The proxy model is contrasted with a high-quality physics-based acceleration baseline and is shown to outperform it by several orders of magnitude. We believe the outcomes presented here are extremely promising and offer a valuable benchmark for continuing research in oil field development optimization. Due to its domain-agnostic architecture, the presented approach can be extended to many applications beyond the field of oil and gas exploration.
- Open Access
Improved Answer Selection with Pre-Trained Word Embeddings
This paper evaluates existing and newly proposed answer selection methods based on pre-trained word embeddings. Word embeddings are highly effective in various natural language processing tasks and their integration into traditional information retrieval (IR) systems allows for the capture of semantic relatedness between questions and answers. Empirical results on three publicly available data sets show significant gains over traditional term frequency based approaches in both supervised and unsupervised settings. We show that combining these word embedding features with traditional learning-to-rank techniques can achieve similar performance to state-of-the-art neural networks trained for the answer selection task.
Open AccessImproved Answer Selection with Pre-Trained Word Embeddings
This paper evaluates existing and newly proposed answer selection methods based on pre-trained word embeddings. Word embeddings are highly effective in various natural language processing tasks and their integration into traditional information retrieval (IR) systems allows for the capture of semantic relatedness between questions and answers. Empirical results on three publicly available data sets show significant gains over traditional term frequency based approaches in both supervised and unsupervised settings. We show that combining these word embedding features with traditional learning-to-rank techniques can achieve similar performance to state-of-the-art neural networks trained for the answer selection task.
- Open Access
- 1 January 2013
- Published by Association for Computational Linguistics (ACL)
- p. 29-38
Graph-Based Unsupervised Learning of Word Similarities Using Heterogeneous Feature Types
Avneesh Saluja, Jiří Navrátil. Proceedings of TextGraphs-8 Graph-based Methods for Natural Language Processing. 2013.
- 1 January 2013
- Published by Association for Computational Linguistics (ACL)
- p. 29-38
Open AccessGraph-Based Unsupervised Learning of Word Similarities Using Heterogeneous Feature Types
Avneesh Saluja, Jiří Navrátil. Proceedings of TextGraphs-8 Graph-based Methods for Natural Language Processing. 2013.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (15206149) , IV-229-229
On Linear DETs
This paper investigates the properties of a popular ROC variant - the detection error trade-off plot (DET). In particular, we derive a set of conditions on the underlying probability distributions to produce linear DET plots in a generalized setting. We show that the linear DETs on a normal deviate scale are not exclusively produced by normal distributions, however, that normal distributions do play an unique role in the threshold behavior as one moves along the DET line. An interesting connection between linear DETs and the Kullback-Leibler divergence is also discussed.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (15206149) , IV-229-229
On Linear DETs
This paper investigates the properties of a popular ROC variant - the detection error trade-off plot (DET). In particular, we derive a set of conditions on the underlying probability distributions to produce linear DET plots in a generalized setting. We show that the linear DETs on a normal deviate scale are not exclusively produced by normal distributions, however, that normal distributions do play an unique role in the threshold behavior as one moves along the DET line. An interesting connection between linear DETs and the Kullback-Leibler divergence is also discussed.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (15206149) , IV-293-293
Text-Independent Speaker Verification in Embedded Environments
A low-resource, text-independent speaker verification (SV) system with an efficient voice model compression technique is described, including its implementation exclusively with integer arithmetic. We describe and discuss the individual algorithmic steps, the integer implementation issues and its error analysis. Performance of the system is evaluated on data collected with iPaq devices and the impact of model compression as well as integer approximation on the accuracy is discussed.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (15206149) , IV-293-293
Text-Independent Speaker Verification in Embedded Environments
A low-resource, text-independent speaker verification (SV) system with an efficient voice model compression technique is described, including its implementation exclusively with integer arithmetic. We describe and discuss the individual algorithmic steps, the integer implementation issues and its error analysis. Performance of the system is evaluated on data collected with iPaq devices and the impact of model compression as well as integer approximation on the accuracy is discussed.
- 1 June 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Advanced Language Recognition using Cepstra and Phonotactics: MITLL System Performance on the NIST 2005 Language Recognition Evaluation
This paper presents a description of the MIT Lincoln Laboratory submissions to the 2005 NIST Language Recognition Evaluation (LRE05). As was true in 2003, the 2005 submissions were combinations of core cepstral and phonotactic recognizers whose outputs were fused to generate final scores. For the 2005 evaluation, Lincoln Laboratory had five submissions built upon fused combinations of six core systems. Major improvements included the generation of phone streams using lattices, SVM-based language models using lattice-derived phonotactics, and binary tree language models. In addition, a development corpus was assembled that was designed to test robustness to unseen languages and sources. Language recognition trends based on NIST evaluations conducted since 1996 show a steady improvement in language recognition performance
- 1 June 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Advanced Language Recognition using Cepstra and Phonotactics: MITLL System Performance on the NIST 2005 Language Recognition Evaluation
This paper presents a description of the MIT Lincoln Laboratory submissions to the 2005 NIST Language Recognition Evaluation (LRE05). As was true in 2003, the 2005 submissions were combinations of core cepstral and phonotactic recognizers whose outputs were fused to generate final scores. For the 2005 evaluation, Lincoln Laboratory had five submissions built upon fused combinations of six core systems. Major improvements included the generation of phone streams using lattices, SVM-based language models using lattice-derived phonotactics, and binary tree language models. In addition, a development corpus was assembled that was designed to test robustness to unseen languages and sources. Language recognition trends based on NIST evaluations conducted since 1996 show a steady improvement in language recognition performance