Exploiting Sentence And Context Representations In Deep Neural Models For Spoken Language Understanding

Abstract

This paper presents a deep learning architecture for the semantic decoder component of a Statistical Spoken Dialogue System. In a slot-filling dialogue, the semantic decoder predicts the dialogue act and a set of slot-value pairs from a set of n-best hypotheses returned by the Automatic Speech Recognition. Most current models for spoken language understanding assume (i) word-aligned semantic annotations as in sequence taggers and (ii) delexicalisation, or a mapping of input words to domain-specific concepts using heuristics that try to capture morphological variation but that do not scale to other domains nor to language variation (e.g., morphology, synonyms, paraphrasing ). In this work the semantic decoder is trained using unaligned semantic annotations and it uses distributed semantic representation learning to overcome the limitations of explicit delexicalisation. The proposed architecture uses a convolutional neural network for the sentence representation and a long-short term mem

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybarahona2016exploiting

Related papers

• From Audio To Semantics: Approaches To End-to-end Spoken Language Understanding (2018)13.23
• Nearly Zero-shot Learning For Semantic Decoding In Spoken Dialogue Systems (2018)0.00
• A Hierarchical Decoding Model For Spoken Language Understanding From Unaligned Data (2019)7.16
• Joint Learning Of Word And Label Embeddings For Sequence Labelling In Spoken Language Understanding (2019)3.58
• Contextualized Spoken Word Representations From Convolutional Autoencoders (2020)0.00
• Recent Advances In End-to-end Spoken Language Understanding (2019)8.09
• Bootstrapping Meaning Through Listening: Unsupervised Learning Of Spoken Sentence Embeddings (2022)2.26
• Learning Semantic Information From Raw Audio Signal Using Both Contextual And Phonetic Representations (2024)0.00