Growing Semantic Grammars
Marsal Gavalda,Alex Waibel +1 more
- Vol. 1, pp 451-456
TLDR
GSG is presented: an empathic computer system for the rapid deployment of NLU front-ends and their dynamic customization by non-expert end-users and three learning methods are employed in the acquisition of semantic mappings from unseen data.Abstract:
A critical path in the development of natural language understanding (NLU) modules lies in the difficulty of defining a mapping from words to semantics: Usually it takes in the order of years of highly-skilled labor to develop a semantic mapping, e.g., in the form of a semantic grammar, that is comprehensive enough for a given domain. Yet, due to the very nature of human language, such mapping invariably fail to achieve full coverage on unseen data. Acknowledging the impossibility of stating a priori all the surface forms by which a concept can be expressed, we present GSG: an empathic computer system for the rapid deployment of NLU front-ends and their dynamic customization by non-expert end-users. Given a new domain for which an NLU front-end is to be developed, two stages are involved. In the authoring stage, GSG aids the developer in the construction of a simple domain model and a kernel analysis grammar. Then, in the run-time stage, GSG provides the end-user with an interactive environment in which the kernel grammar is dynamically extended. Three learning methods are employed in the acquisition of semantic mappings from unseen data: (i) parser predictions, (ii) hidden understanding model, and (iii) end-user paraphrases. A baseline version of GSG has been implemented and preliminary experiments show promising results.read more
Citations
More filters
Proceedings ArticleDOI
Smart Sight: a tourist assistant system
TL;DR: The system is equipped with a unique combination of sensors and software that supports natural language processing, speech recognition, machine translation, handwriting recognition and multimodal fusion.
Journal ArticleDOI
AutoTutor and Family: A Review of 17 Years of Natural Language Tutoring
TL;DR: AutoTutor as discussed by the authors is a natural language tutoring system that has produced learning gains across multiple domains (e.g., computer literacy, physics, critical thinking) by co-constructed explanations, feedback, conversational scaffolding, and subject matter content.
Proceedings ArticleDOI
Is word error rate a good indicator for spoken language understanding accuracy
TL;DR: It is a conventional wisdom in the speech community that better speech recognition accuracy is a good indicator for better spoken language understanding accuracy, but the findings in this work reveal that this is not always the case.
AutoTutor and Family: A Review of 17 Years of Natural Language Tutoring.
TL;DR: This paper summarizes and integrates significant findings produced by studies using AutoTutor and related systems, and considers advances in pedagogical agent roles and in tutoring technologies, such semantic processing and tutoring delivery platforms.
Journal ArticleDOI
Multilinguality in speech and spoken language systems
TL;DR: A modular grammar design is introduced to maximize reusability and portability in speech recognition and speech translation and using a task-oriented Interlingua allows to build a system with N languages with linear, rather than quadratic effort.
References
More filters
Journal Article
TINA: a natural language system for spoken language applications
TL;DR: A new natural language system, TINA, has been developed for applications involving spoken language tasks that provides an automatic sentence generation capability that has been effective for identifying overgeneralization problems as well as in producing a word-pair language model for a recognizer.
Proceedings ArticleDOI
Hidden understanding models of natural language
TL;DR: This work describes and evaluates hidden understanding models, a statistical learning approach to natural language understanding that determines the most likely meaning for the string of words.
Proceedings ArticleDOI
Janus-III: speech-to-speech translation in multiple languages
Alon Lavie,Alex Waibel,Lori Levin,Michael Finke,Donna Gates,Marsal Gavalda,T. Zeppenfeld,Puming Zhan +7 more
TL;DR: JANUS-III, the most recent version of the JANUS speech-to-speech translation system, is described and an overview of the system is presented and focus on how system design facilitates speech translation between multiple languages, and allows for easy adaptation to new source and target languages.
Book
Adaptive Parsing: Self-Extending Natural Language Interfaces
TL;DR: This work focuses on the development of a model for least-deviant-first parsing and knowledge representation in CHAMP, and the effects of adaptation on performance in real user interactions.
Proceedings ArticleDOI
Linguistic knowledge acquisition from parsing failures
Masaki Kiyono,Jun'ichi Tsujii +1 more
TL;DR: A semi-automatic procedure of linguistic knowledge acquisition is proposed, which combines corpus-based techniques with the conventional rule-based approach and will be used for adapting or re-using existing linguistic resources for new application domains.