Dynamically supporting unexplored domains in conversational interactions by enriching semantics with neural word embeddings

Spoken language interfaces are being incorporated into various devices (e.g. smart-phones, smart TVs, etc). However, current technology typically limits conversational interactions to a few narrow predefined domains/topics. For example, dialogue systems for smartphone operation fail to respond when users ask for functions not supported by currently installed applications. We propose to dynamically add application-based domains according to users' requests by using descriptions of applications as a retrieval cue to find relevant applications. The approach uses structured knowledge resources (e.g. Freebase, Wikipedia, FrameNet) to induce types of slots for generating semantic seeds, and enriches the semantics of spoken queries with neural word embeddings, where semantically related concepts can be additionally included for acquiring knowledge that does not exist in the predefined domains. The system can then retrieve relevant applications or dynamically suggest users install applications that support unexplored domains. We find that vendor descriptions provide a reliable source of information for this purpose.

[1]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[2]  Zellig S. Harris,et al.  Distributional Structure , 1954 .

[3]  Ming-Wei Chang,et al.  E2E: An End-to-End Entity Linking System for Short and Noisy Text , 2014, #MSM.

[4]  Gökhan Tür,et al.  Exploiting the Semantic Web for Unsupervised Natural Language Semantic Parsing , 2012, INTERSPEECH.

[5]  Dan Roth,et al.  Relational Inference for Wikification , 2013, EMNLP.

[6]  Christopher Meek,et al.  Semantic Parsing for Single-Relation Question Answering , 2014, ACL.

[7]  Alexander I. Rudnicky,et al.  Leveraging frame semantics and distributional semantics for unsupervised semantic slot induction in spoken dialogue systems , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

[8]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[9]  Gökhan Tür,et al.  Deriving local relational surface forms from dependency-based entity embeddings for unsupervised spoken language understanding , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

[10]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[11]  Dilek Z. Hakkani-Tür,et al.  Exploiting the Semantic Web for unsupervised spoken language understanding , 2012, 2012 IEEE Spoken Language Technology Workshop (SLT).

[12]  Noah A. Smith,et al.  Frame-Semantic Parsing , 2014, CL.

[13]  Richard A. Harshman,et al.  Indexing by Latent Semantic Analysis , 1990, J. Am. Soc. Inf. Sci..

[14]  Geoffrey Zweig,et al.  Linguistic Regularities in Continuous Space Word Representations , 2013, NAACL.

[15]  Geoffrey Zweig,et al.  Probabilistic enrichment of knowledge graph entities for relation detection in conversational understanding , 2014, INTERSPEECH.

[16]  John B. Lowe,et al.  The Berkeley FrameNet Project , 1998, ACL.

[17]  Gökhan Tür,et al.  Extending domain coverage of language understanding systems via intent transfer between domains using knowledge graphs and search query click logs , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[18]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[19]  Doug Downey,et al.  Local and Global Algorithms for Disambiguation to Wikipedia , 2011, ACL.

[20]  C. Fillmore.  FRAME SEMANTICS AND THE NATURE OF LANGUAGE * , 1976 .

[21]  Vysoké Učení,et al.  Statistical Language Models Based on Neural Networks , 2012 .

[22]  Alexander I. Rudnicky,et al.  Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame-semantic parsing , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.