The Experts below are selected from a list of 27240 Experts worldwide ranked by ideXlab platform
Alex Acero - One of the best experts on this subject based on the ideXlab platform.
-
Rapid development of spoken language understanding Grammars
Speech Communication, 2005Co-Authors: Yeyi Wang, Alex AceroAbstract:To facilitate the development of spoken dialog systems and speech enabled applications, we introduce SGStudio (Semantic Grammar Studio), a Grammar authoring tool that enables regular software developers with little speech/linguistic background to rapidly create quality Semantic Grammars for automatic speech recognition (ASR) and spoken language understanding (SLU). We focus on the underlying technology of SGStudio, including knowledge assisted example-based Grammar learning, Grammar controls and configurable Grammar structures. While the focus of SGStudio is to increase productivity, experimental results show that it also improves the quality of the Grammars being developed.
-
sgstudio rapid Semantic Grammar development for spoken language understanding
Conference of the International Speech Communication Association, 2005Co-Authors: Yeyi Wang, Alex AceroAbstract:SGStudio (Semantic Grammar Studio) is a Grammar authoring tool that facilitates the development of spoken dialog systems and speech enabled applications. It enables regular software developers with little speech/linguistic background to rapidly create quality Semantic Grammars for automatic speech recognition (ASR) and spoken language understanding (SLU). This paper introduces the framework of the tool as well as the component technologies, including knowledge assisted example-based Grammar learning, Grammar controls and configurable Grammar structures. Experimental results show that SGStudio not only greatly increases the productivity, but also improves the quality of the Grammars developed.
-
INTERSPEECH - SGStudio: rapid Semantic Grammar development for spoken language understanding.
2005Co-Authors: Yeyi Wang, Alex AceroAbstract:SGStudio (Semantic Grammar Studio) is a Grammar authoring tool that facilitates the development of spoken dialog systems and speech enabled applications. It enables regular software developers with little speech/linguistic background to rapidly create quality Semantic Grammars for automatic speech recognition (ASR) and spoken language understanding (SLU). This paper introduces the framework of the tool as well as the component technologies, including knowledge assisted example-based Grammar learning, Grammar controls and configurable Grammar structures. Experimental results show that SGStudio not only greatly increases the productivity, but also improves the quality of the Grammars developed.
-
combination of cfg and n gram modeling in Semantic Grammar learning
Conference of the International Speech Communication Association, 2003Co-Authors: Yeyi Wang, Alex AceroAbstract:SGStudio is a Grammar authoring tool that eases Semantic Grammar development. It is capable of integrating different information sources and learning from annotated examples to induct CFG rules. In this paper, we investigate a modification to its underlying model by replacing CFG rules with n-gram statistical models. The new model is a composite of HMM and CFG. The advantages of the new model include its built-in robust feature and its scalability to an n-gram classifier when the understanding does not involve slot filling. We devised a decoder for the model. Preliminary results show that the new model achieved 32% error reduction in high resolution understanding.
-
INTERSPEECH - Combination of CFG and n-gram modeling in Semantic Grammar learning.
2003Co-Authors: Yeyi Wang, Alex AceroAbstract:SGStudio is a Grammar authoring tool that eases Semantic Grammar development. It is capable of integrating different information sources and learning from annotated examples to induct CFG rules. In this paper, we investigate a modification to its underlying model by replacing CFG rules with n-gram statistical models. The new model is a composite of HMM and CFG. The advantages of the new model include its built-in robust feature and its scalability to an n-gram classifier when the understanding does not involve slot filling. We devised a decoder for the model. Preliminary results show that the new model achieved 32% error reduction in high resolution understanding.
Yeyi Wang - One of the best experts on this subject based on the ideXlab platform.
-
Rapid development of spoken language understanding Grammars
Speech Communication, 2005Co-Authors: Yeyi Wang, Alex AceroAbstract:To facilitate the development of spoken dialog systems and speech enabled applications, we introduce SGStudio (Semantic Grammar Studio), a Grammar authoring tool that enables regular software developers with little speech/linguistic background to rapidly create quality Semantic Grammars for automatic speech recognition (ASR) and spoken language understanding (SLU). We focus on the underlying technology of SGStudio, including knowledge assisted example-based Grammar learning, Grammar controls and configurable Grammar structures. While the focus of SGStudio is to increase productivity, experimental results show that it also improves the quality of the Grammars being developed.
-
sgstudio rapid Semantic Grammar development for spoken language understanding
Conference of the International Speech Communication Association, 2005Co-Authors: Yeyi Wang, Alex AceroAbstract:SGStudio (Semantic Grammar Studio) is a Grammar authoring tool that facilitates the development of spoken dialog systems and speech enabled applications. It enables regular software developers with little speech/linguistic background to rapidly create quality Semantic Grammars for automatic speech recognition (ASR) and spoken language understanding (SLU). This paper introduces the framework of the tool as well as the component technologies, including knowledge assisted example-based Grammar learning, Grammar controls and configurable Grammar structures. Experimental results show that SGStudio not only greatly increases the productivity, but also improves the quality of the Grammars developed.
-
INTERSPEECH - SGStudio: rapid Semantic Grammar development for spoken language understanding.
2005Co-Authors: Yeyi Wang, Alex AceroAbstract:SGStudio (Semantic Grammar Studio) is a Grammar authoring tool that facilitates the development of spoken dialog systems and speech enabled applications. It enables regular software developers with little speech/linguistic background to rapidly create quality Semantic Grammars for automatic speech recognition (ASR) and spoken language understanding (SLU). This paper introduces the framework of the tool as well as the component technologies, including knowledge assisted example-based Grammar learning, Grammar controls and configurable Grammar structures. Experimental results show that SGStudio not only greatly increases the productivity, but also improves the quality of the Grammars developed.
-
combination of cfg and n gram modeling in Semantic Grammar learning
Conference of the International Speech Communication Association, 2003Co-Authors: Yeyi Wang, Alex AceroAbstract:SGStudio is a Grammar authoring tool that eases Semantic Grammar development. It is capable of integrating different information sources and learning from annotated examples to induct CFG rules. In this paper, we investigate a modification to its underlying model by replacing CFG rules with n-gram statistical models. The new model is a composite of HMM and CFG. The advantages of the new model include its built-in robust feature and its scalability to an n-gram classifier when the understanding does not involve slot filling. We devised a decoder for the model. Preliminary results show that the new model achieved 32% error reduction in high resolution understanding.
-
INTERSPEECH - Combination of CFG and n-gram modeling in Semantic Grammar learning.
2003Co-Authors: Yeyi Wang, Alex AceroAbstract:SGStudio is a Grammar authoring tool that eases Semantic Grammar development. It is capable of integrating different information sources and learning from annotated examples to induct CFG rules. In this paper, we investigate a modification to its underlying model by replacing CFG rules with n-gram statistical models. The new model is a composite of HMM and CFG. The advantages of the new model include its built-in robust feature and its scalability to an n-gram classifier when the understanding does not involve slot filling. We devised a decoder for the model. Preliminary results show that the new model achieved 32% error reduction in high resolution understanding.
Steve Young - One of the best experts on this subject based on the ideXlab platform.
-
spoken language understanding using the hidden vector state model
Speech Communication, 2006Co-Authors: Steve YoungAbstract:Abstract The Hidden Vector State (HVS) Model is an extension of the basic discrete Markov model in which context is encoded as a stack-oriented state vector. State transitions are factored into a stack shift operation similar to those of a push-down automaton followed by the push of a new preterminal category label. When used as a Semantic parser, the model can capture hierarchical structure without the use of treebank data for training and it can be trained automatically using expectation-maximization (EM) from only-lightly annotated training data. When deployed in a system, the model can be continually refined as more data becomes available. In this paper, the practical application of the model in a spoken language understanding system (SLU) is described. Through a sequence of experiments, the issues of robustness to noise and portability to similar and extended domains are investigated. The end-to-end performance obtained from experiments in the ATIS domain show that the system is comparable to existing SLU systems which rely on either hand-crafted Semantic Grammar rules or statistical models trained on fully annotated training corpora. Experiments using data which have been artificially corrupted with varying levels of additive noise show that the HVS-based parser is relatively robust, and experiments using data sets from other domains indicate that the overall framework allows adaptation to related domains, and scaling to cover enlarged domains. In summary, it is argued that constrained statistical parsers such as the HVS model allow robust spoken dialogue systems to be built at relatively low cost, and which can be automatically adapted as new data is acquired both to improve performance and extend coverage.
-
A data-driven spoken language understanding system
2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721), 1Co-Authors: Steve YoungAbstract:The paper presents a purely data-driven spoken language understanding (SLU) system. It consists of three major components, a speech recognizer, a Semantic parser, and a dialog act decoder. A novel feature of the system is that the understanding components are trained directly from data without using explicit Semantic Grammar rules or fully-annotated corpus data. Despite this, the system is nevertheless able to capture hierarchical structure in user utterances and handle long range dependencies. Experiments have been conducted on the ATIS corpus and 16.1% and 12.6% utterance understanding error rates were obtained for spoken input using the ATIS-3 1993 and 1994 test sets. These results show that our system is comparable to existing SLU systems which rely on either handcrafted Semantic Grammar rules or statistical models trained on fully-annotated training corpora, but it has greatly reduced build cost.
Arash Eshghi - One of the best experts on this subject based on the ideXlab platform.
-
Bootstrapping incremental dialogue systems from minimal data: the generalisation power of dialogue Grammars
arXiv: Computation and Language, 2017Co-Authors: Arash Eshghi, Igor Shalyminov, Oliver LemonAbstract:We investigate an end-to-end method for automatically inducing task-based dialogue systems from small amounts of unannotated dialogue data. It combines an incremental Semantic Grammar - Dynamic Syntax and Type Theory with Records (DS-TTR) - with Reinforcement Learning (RL), where language generation and dialogue management are a joint decision problem. The systems thus produced are incremental: dialogues are processed word-by-word, shown previously to be essential in supporting natural, spontaneous dialogue. We hypothesised that the rich linguistic knowledge within the Grammar should enable a combinatorially large number of dialogue variations to be processed, even when trained on very few dialogues. Our experiments show that our model can process 74% of the Facebook AI bAbI dataset even when trained on only 0.13% of the data (5 dialogues). It can in addition process 65% of bAbI+, a corpus we created by systematically adding incremental dialogue phenomena such as restarts and self-corrections to bAbI. We compare our model with a state-of-the-art retrieval model, MemN2N. We find that, in terms of Semantic accuracy, MemN2N shows very poor robustness to the bAbI+ transformations even when trained on the full bAbI dataset.
-
EMNLP - Bootstrapping incremental dialogue systems from minimal data: the generalisation power of dialogue Grammars
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017Co-Authors: Arash Eshghi, Igor Shalyminov, Oliver LemonAbstract:We investigate an end-to-end method for automatically inducing task-based dialogue systems from small amounts of unannotated dialogue data. It combines an incremental Semantic Grammar - Dynamic Syntax and Type Theory with Records (DS-TTR) - with Reinforcement Learning (RL), where language generation and dialogue management are a joint decision problem. The systems thus produced are incremental: dialogues are processed word-by-word, shown previously to be essential in supporting natural, spontaneous dialogue. We hypothesised that the rich linguistic knowledge within the Grammar should enable a combinatorially large number of dialogue variations to be processed, even when trained on very few dialogues. Our experiments show that our model can process 74% of the Facebook AI bAbI dataset even when trained on only 0.13% of the data (5 dialogues). It can in addition process 65% of bAbI+, a corpus we created by systematically adding incremental dialogue phenomena such as restarts and self-corrections to bAbI. We compare our model with a state-of-the-art retrieval model, MEMN2N. We find that, in terms of Semantic accuracy, the MEMN2N model shows very poor robustness to the bAbI+ transformations even when trained on the full bAbI dataset.
-
bootstrapping incremental dialogue systems using linguistic knowledge to learn from minimal data
arXiv: Computation and Language, 2016Co-Authors: Dimitrios Kalatzis, Arash Eshghi, Oliver LemonAbstract:We present a method for inducing new dialogue systems from very small amounts of unannotated dialogue data, showing how word-level exploration using Reinforcement Learning (RL), combined with an incremental and Semantic Grammar - Dynamic Syntax (DS) - allows systems to discover, generate, and understand many new dialogue variants. The method avoids the use of expensive and time-consuming dialogue act annotations, and supports more natural (incremental) dialogues than turn-based systems. Here, language generation and dialogue management are treated as a joint decision/optimisation problem, and the MDP model for RL is constructed automatically. With an implemented system, we show that this method enables a wide range of dialogue variations to be automatically captured, even when the system is trained from only a single dialogue. The variants include question-answer pairs, over- and under-answering, self- and other-corrections, clarification interaction, split-utterances, and ellipsis. This generalisation property results from the structural knowledge and constraints present within the DS Grammar, and highlights some limitations of recent systems built using machine learning techniques only.
-
CMCL - Incremental Grammar Induction from Child-Directed Dialogue Utterances
2013Co-Authors: Arash Eshghi, Julian Hough, Matthew PurverAbstract:We describe a method for learning an incremental Semantic Grammar from data in which utterances are paired with logical forms representing their meaning. Working in an inherently incremental framework, Dynamic Syntax, we show how words can be associated with probabilistic procedures for the incremental projection of meaning, providing a Grammar which can be used directly in incremental probabilistic parsing and generation. We test this on child-directed utterances from the CHILDES corpus, and show that it results in good coverage and Semantic accuracy, without requiring annotation at the word level or any independent notion of syntax.
-
probabilistic induction for an incremental Semantic Grammar
Proceedings of the 10th International Conference on Computational Semantics (IWCS 2013) -- Long Papers, 2013Co-Authors: Arash Eshghi, Matthew Purver, Julian HoughAbstract:We describe a method for learning an incremental Semantic Grammar from a corpus in which sentences are paired with logical forms as predicate-argument structure trees. Working in the framework of Dynamic Syntax, and assuming a set of generally available compositional mechanisms, we show how lexical entries can be learned as probabilistic procedures for the incremental projection of Semantic structure, providing a Grammar suitable for use in an incremental probabilistic parser. By inducing these from a corpus generated using an existing Grammar, we demonstrate that this results in both good coverage and compatibility with the original entries, without requiring annotation at the word level. We show that this Semantic approach to Grammar induction has the novel ability to learn the syntactic and Semantic constraints on pronouns.
Adil El Ghali - One of the best experts on this subject based on the ideXlab platform.
-
TSD - Coupling Grammar and knowledge base: Range Concatenation Grammars and description logics
Text Speech and Dialogue, 2004Co-Authors: Benoît Sagot, Adil El GhaliAbstract:In this paper we introduce a novel framework to compute jointly syntactic parses and Semantic representations of a written sentence. To achieve this goal, we couple a syntactico-Semantic Grammar and a knowledge base. The knowledge base is implemented in Description Logics, in a polynomial variant. The Grammar is a Range Concatenation Grammar, which combines expressive power and polynomial parsing time, and allows external predicate calls. These external calls are sent to the knowledge base, which is able either to answer these calls or to learn new information, this process taking place during parsing. Thus, only Semantically acceptable parses are built, avoiding the costly a posteriori Semantic check of all syntactically correct parses.
-
Coupling Grammar and knowledge base: Range Concatenation Grammars and description logics
Lecture Notes in Computer Science, 2004Co-Authors: Benoît Sagot, Adil El GhaliAbstract:In this paper we introduce a novel framework to compute jointly syntactic parses and Semantic representations of a written sentence. To achieve this goal, we couple a syntactico-Semantic Grammar and a knowledge base. The knowledge base is implemented in Description Logics, in a polynomial variant. The Grammar is a Range Concatenation Grammar, which combines expressive power and polynomial parsing time, and allows external predicate calls. These external calls are sent to the knowledge base, which is able either to answer these calls or to learn new information, this process taking place during parsing. Thus, only Semantically acceptable parses are built, avoiding the costly a posteriori Semantic check of all syntactically correct parses.