The Experts below are selected from a list of 112368 Experts worldwide ranked by ideXlab platform
Zhenbiao Chen - One of the best experts on this subject based on the ideXlab platform.
-
automatic pronunciation error detection based on Linguistic Knowledge and pronunciation space
International Conference on Acoustics Speech and Signal Processing, 2009Co-Authors: Jie Jiang, Zhenbiao ChenAbstract:This paper presents a new approach that uses Linguistic Knowledge and pronunciation space for automatic detection of typical phone-level errors made by non-native speakers of mandarin. Firstly, Linguistic Knowledge of common learner mistakes is embedded in the calculation of log-posterior probability and the revised log-posterior probability (RLPP) is regarded as the measure of mispronunciation; secondly, a restricted pronunciation space is constructed by using RLPP vectors to describe the characteristics of pronunciation and Support Vector Machine (SVM) classifier is applied into the detection of typical pronunciation errors. Experiments based on a nonnative speaker database of mandarin confirm the promising effectiveness of our methods.
-
ICASSP - Automatic pronunciation error detection based on Linguistic Knowledge and pronunciation space
2009 IEEE International Conference on Acoustics Speech and Signal Processing, 2009Co-Authors: Jie Jiang, Zhenbiao ChenAbstract:This paper presents a new approach that uses Linguistic Knowledge and pronunciation space for automatic detection of typical phone-level errors made by non-native speakers of mandarin. Firstly, Linguistic Knowledge of common learner mistakes is embedded in the calculation of log-posterior probability and the revised log-posterior probability (RLPP) is regarded as the measure of mispronunciation; secondly, a restricted pronunciation space is constructed by using RLPP vectors to describe the characteristics of pronunciation and Support Vector Machine (SVM) classifier is applied into the detection of typical pronunciation errors. Experiments based on a nonnative speaker database of mandarin confirm the promising effectiveness of our methods.
Jie Jiang - One of the best experts on this subject based on the ideXlab platform.
-
automatic pronunciation error detection based on Linguistic Knowledge and pronunciation space
International Conference on Acoustics Speech and Signal Processing, 2009Co-Authors: Jie Jiang, Zhenbiao ChenAbstract:This paper presents a new approach that uses Linguistic Knowledge and pronunciation space for automatic detection of typical phone-level errors made by non-native speakers of mandarin. Firstly, Linguistic Knowledge of common learner mistakes is embedded in the calculation of log-posterior probability and the revised log-posterior probability (RLPP) is regarded as the measure of mispronunciation; secondly, a restricted pronunciation space is constructed by using RLPP vectors to describe the characteristics of pronunciation and Support Vector Machine (SVM) classifier is applied into the detection of typical pronunciation errors. Experiments based on a nonnative speaker database of mandarin confirm the promising effectiveness of our methods.
-
ICASSP - Automatic pronunciation error detection based on Linguistic Knowledge and pronunciation space
2009 IEEE International Conference on Acoustics Speech and Signal Processing, 2009Co-Authors: Jie Jiang, Zhenbiao ChenAbstract:This paper presents a new approach that uses Linguistic Knowledge and pronunciation space for automatic detection of typical phone-level errors made by non-native speakers of mandarin. Firstly, Linguistic Knowledge of common learner mistakes is embedded in the calculation of log-posterior probability and the revised log-posterior probability (RLPP) is regarded as the measure of mispronunciation; secondly, a restricted pronunciation space is constructed by using RLPP vectors to describe the characteristics of pronunciation and Support Vector Machine (SVM) classifier is applied into the detection of typical pronunciation errors. Experiments based on a nonnative speaker database of mandarin confirm the promising effectiveness of our methods.
Jenelle Reeves - One of the best experts on this subject based on the ideXlab platform.
-
a sociocultural perspective on esol teachers Linguistic Knowledge for teaching
Linguistics and Education, 2009Co-Authors: Jenelle ReevesAbstract:Abstract Within a sociocultural frame, teacher Knowledge finds its origin in the entirety of teachers’ lived experiences, not just those experiences within teacher preparation. Teachers’ biographies, including their experiences as language learners, shape their Knowledge base for teaching English to speakers of other languages (ESOL). This study interrogates one element of that Knowledge base: teachers’ Linguistic Knowledge for teaching. Cases studies of two early career ESOL teachers with similar language learner biographies, that of first language (L1) Center English speakers with limited second language (L2) learning experience, provided insight into the ways participants’ language biographies informed their Linguistic Knowledge for teaching. Findings indicated that participants’ L1 Knowledge of English did not provide them with the Linguistic Knowledge they needed for ESOL teaching. Implications for ESOL teacher education include better attuning teacher preparation programs to teacher candidates’ biographies.
Jennifer Dsouza - One of the best experts on this subject based on the ideXlab platform.
-
classifying temporal relations with rich Linguistic Knowledge
North American Chapter of the Association for Computational Linguistics, 2013Co-Authors: Jennifer DsouzaAbstract:We examine the task of temporal relation classification. Unlike existing approaches to this task, we (1) classify an event-event or eventtime pair as one of the 14 temporal relations defined in the TimeBank corpus, rather than as one of the six relations collapsed from the original 14; (2) employ sophisticated Linguistic Knowledge derived from a variety of semantic and discourse relations, rather than focusing on morpho-syntactic Knowledge; and (3) leverage a novel combination of rule-based and learning-based approaches, rather than relying solely on one or the other. Experiments with the TimeBank corpus demonstrate that our Knowledge-rich, hybrid approach yields a 15‐16% relative reduction in error over a state-of-the-art learning-based baseline system.
Noah A. Smith - One of the best experts on this subject based on the ideXlab platform.
-
Linguistic Knowledge and Transferability of Contextual Representations
arXiv: Computation and Language, 2019Co-Authors: Nelson F. Liu, Matt Gardner, Yonatan Belinkov, Matthew E. Peters, Noah A. SmithAbstract:Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language. To shed light on the Linguistic Knowledge they capture, we study the representations produced by several recent pretrained contextualizers (variants of ELMo, the OpenAI transformer language model, and BERT) with a suite of seventeen diverse probing tasks. We find that linear models trained on top of frozen contextual representations are competitive with state-of-the-art task-specific models in many cases, but fail on tasks requiring fine-grained Linguistic Knowledge (e.g., conjunct identification). To investigate the transferability of contextual word representations, we quantify differences in the transferability of individual layers within contextualizers, especially between recurrent neural networks (RNNs) and transformers. For instance, higher layers of RNNs are more task-specific, while transformer layers do not exhibit the same monotonic trend. In addition, to better understand what makes contextual word representations transferable, we compare language model pretraining with eleven supervised pretraining tasks. For any given task, pretraining on a closely related task yields better performance than language model pretraining (which is better on average) when the pretraining dataset is fixed. However, language model pretraining on more data gives the best results.
-
Linguistic Knowledge and transferability of contextual representations
North American Chapter of the Association for Computational Linguistics, 2019Co-Authors: Nelson F. Liu, Matt Gardner, Yonatan Belinkov, Matthew E. Peters, Noah A. SmithAbstract:Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language. To shed light on the Linguistic Knowledge they capture, we study the representations produced by several recent pretrained contextualizers (variants of ELMo, the OpenAI transformer language model, and BERT) with a suite of sixteen diverse probing tasks. We find that linear models trained on top of frozen contextual representations are competitive with state-of-the-art task-specific models in many cases, but fail on tasks requiring fine-grained Linguistic Knowledge (e.g., conjunct identification). To investigate the transferability of contextual word representations, we quantify differences in the transferability of individual layers within contextualizers, especially between recurrent neural networks (RNNs) and transformers. For instance, higher layers of RNNs are more task-specific, while transformer layers do not exhibit the same monotonic trend. In addition, to better understand what makes contextual word representations transferable, we compare language model pretraining with eleven supervised pretraining tasks. For any given task, pretraining on a closely related task yields better performance than language model pretraining (which is better on average) when the pretraining dataset is fixed. However, language model pretraining on more data gives the best results.
-
NAACL-HLT (1) - Linguistic Knowledge and Transferability of Contextual Representations
Proceedings of the 2019 Conference of the North, 2019Co-Authors: Nelson F. Liu, Matt Gardner, Yonatan Belinkov, Matthew E. Peters, Noah A. SmithAbstract:Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language. To shed light on the Linguistic Knowledge they capture, we study the representations produced by several recent pretrained contextualizers (variants of ELMo, the OpenAI transformer language model, and BERT) with a suite of sixteen diverse probing tasks. We find that linear models trained on top of frozen contextual representations are competitive with state-of-the-art task-specific models in many cases, but fail on tasks requiring fine-grained Linguistic Knowledge (e.g., conjunct identification). To investigate the transferability of contextual word representations, we quantify differences in the transferability of individual layers within contextualizers, especially between recurrent neural networks (RNNs) and transformers. For instance, higher layers of RNNs are more task-specific, while transformer layers do not exhibit the same monotonic trend. In addition, to better understand what makes contextual word representations transferable, we compare language model pretraining with eleven supervised pretraining tasks. For any given task, pretraining on a closely related task yields better performance than language model pretraining (which is better on average) when the pretraining dataset is fixed. However, language model pretraining on more data gives the best results.
