Deriving local relational surface forms from dependency-based entity embeddings for unsupervised spoken language understanding

Recent works showed the trend of leveraging web-scaled structured semantic knowledge resources such as Freebase for open domain spoken language understanding (SLU). Knowledge graphs provide sufficient but ambiguous relations for the same entity, which can be used as statistical background knowledge to infer possible relations for interpretation of user utterances. This paper proposes an approach to capture the relational surface forms by mapping dependency-based contexts of entities from the text domain to the spoken domain. Relational surface forms are learned from dependency-based entity embeddings, which encode the contexts of entities from dependency trees in a deep learning model. The derived surface forms carry functional dependency to the entities and convey the explicit expression of relations. The experiments demonstrate the efficiency of leveraging derived relational surface forms as local cues together with prior background knowledge.

[1]  Dan Klein,et al.  Learning and Inference for Hierarchically Split PCFGs , 2007, AAAI.

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

[3]  Gökhan Tür,et al.  Learning Weighted Entity Lists from Web Click Logs for Spoken Language Understanding , 2011, INTERSPEECH.

[4]  Gökhan Tür,et al.  Towards Unsupervised Spoken Language Understanding: Exploiting Query Click Logs for Slot Filling , 2011, INTERSPEECH.

[5]  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).

[6]  Jason Weston,et al.  Learning Structured Embeddings of Knowledge Bases , 2011, AAAI.

[7]  Omer Levy,et al.  Dependency-Based Word Embeddings , 2014, ACL.

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

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

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

[11]  Dilek Z. Hakkani-Tür,et al.  Spoken language understanding , 2008, IEEE Signal Processing Magazine.

[12]  Fabrice Lefèvre,et al.  Cross-lingual spoken language understanding from unaligned data using discriminative classification models and machine translation , 2010, INTERSPEECH.

[13]  Gökhan Tür,et al.  A weakly-supervised approach for discovering new user intents from search query logs , 2013, INTERSPEECH.

[14]  Gökhan Tür.  Multitask Learning for Spoken Language Understanding , 2006, ICASSP.

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

[16]  Richard Johansson,et al.  Extended Constituent-to-Dependency Conversion for English , 2007, NODALIDA.

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

[18]  Praveen Paritosh,et al.  Freebase: a collaboratively created graph database for structuring human knowledge , 2008, SIGMOD Conference.

[19]  Gökhan Tür,et al.  Using a knowledge graph and query click logs for unsupervised learning of relation detection , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[20]  Gökhan Tür,et al.  Leveraging knowledge graphs for web-scale unsupervised semantic parsing , 2013, INTERSPEECH.

[21]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[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.