Corpus ID: 5801166

No Evidence Left Behind: Understanding Semantics in Dialogs using Relational Evidence Based Learning

@inproceedings{elikyilmaz2014NoEL,
  title={No Evidence Left Behind: Understanding Semantics in Dialogs using Relational Evidence Based Learning},
  author={A. Çelikyilmaz and D. Hakkani-Tur and Minwoo Jeong},
  year={2014}
}
  • A. Çelikyilmaz, D. Hakkani-Tur, Minwoo Jeong
  • Published 2014
  • Computer Science
  • We describe a new structural learning approach to semantic analysis of utterances from conversational dialogs of low-resource domains. Typically an utterance is represented with a multi-layered semantic tag schema: a higher level global context (tag) defines the user’s intent, and associated arguments or slot tags define the local context. To deal with the low resource domains, the existing models encode prior information on either the global or the local context, but not on both. Because these… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 26 REFERENCES
    Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
    • 10,635
    • Highly Influential
    • PDF
    Spoken Language Understanding: Systems for Extracting Semantic Information from Speech
    • 377
    • PDF
    Prototype-Driven Learning for Sequence Models
    • 211
    • Highly Influential
    • PDF
    Posterior Regularization for Structured Latent Variable Models
    • 436
    • PDF
    A Joint Model of Text and Aspect Ratings for Sentiment Summarization
    • 632
    • PDF
    Learning query intent from regularized click graphs
    • 326
    Joint Parsing and Named Entity Recognition
    • 177
    • PDF
    Guiding Semi-Supervision with Constraint-Driven Learning
    • 205
    • PDF
    Structured Models for Fine-to-Coarse Sentiment Analysis
    • 301
    • PDF
    Sentence simplification for spoken language understanding
    • 50
    • PDF