Approximate Inference for Domain Detection in Spoken Language Understanding
نویسندگان
چکیده
This paper presents a semi-latent topic model for semantic domain detection in spoken language understanding systems. We use labeled utterance information to capture latent topics, which directly correspond to semantic domains. Additionally, we introduce an ’informative prior’ for Bayesian inference that can simultaneously segment utterances of known domains into classes and divide them from out-of-domain utterances. We show that our model generalizes well on the task of classifying spoken language utterances and compare its results to those of an unsupervised topic model, which does not use labeled information.
منابع مشابه
Comprehension across Application Domains and Languages
This work demonstrates that our natural language understanding framework can be applied across application domains and languages with ease. Approaches towards language understanding generally involve much handcrafting, e.g. in writing grammars or annotating corpora, hence portability is a desirable trait in the development of language understanding systems. Our framework for natural language un...
متن کاملThe Impact of Language Learning Activities on the Spoken Language Development of 5-6-Year-Old Children in Private Preschool Centers of Langroud
The Impact of Language Learning Activities on the Spoken Language Development of 5-6-Year-Old Children in Private Preschool Centers of Langroud N. Bagheri, M.A. E. Abbasi, Ph.D. M. GeramiPour, Ph.D. The present study was conducted to investigate the impact of language learning activities on development of spoken language in 5-6-year-old children at private preschool center...
متن کاملA Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
This paper introduces the Multi-Genre Natural Language Inference (MultiNLI) corpus, a dataset designed for use in the development and evaluation of machine learning models for sentence understanding. In addition to being one of the largest corpora available for the task of NLI, at 433k examples, this corpus improves upon available resources in its coverage: it offers data from ten distinct genr...
متن کاملLearning Bidirectional Intent Embeddings by Convolutional Deep Structured Semantic Models for Spoken Language Understanding
The recent surge of intelligent personal assistants motivates spoken language understanding of dialogue systems. Considering high-level semantics, intent embeddings can be viewed as the universal representations that help derive a more flexible intent schema to overcome the domain constraint and the genre mismatch. A convolutional deep structured semantic model (CDSSM) is applied to jointly lea...
متن کاملJointly Modeling Inter-Slot Relations by Random Walk on Knowledge Graphs for Unsupervised Spoken Language Understanding
A key challenge of designing coherent semantic ontology for spoken language understanding is to consider inter-slot relations. In practice, however, it is difficult for domain experts and professional annotators to define a coherent slot set, while considering various lexical, syntactic, and semantic dependencies. In this paper, we exploit the typed syntactic dependency theory for unsupervised ...
متن کامل