Title :
Joint semantic utterance classification and slot filling with recursive neural networks
Author :
Guo, Daniel ; Tur, Gokhan ; Wen-tau Yih ; Zweig, Geoffrey
Abstract :
In recent years, continuous space models have proven to be highly effective at language processing tasks ranging from paraphrase detection to language modeling. These models are distinctive in their ability to achieve generalization through continuous space representations, and compositionality through arithmetic operations on those representations. Examples of such models include feed-forward and recurrent neural network language models. Recursive neural networks (RecNNs) extend this framework by providing an elegant mechanism for incorporating both discrete syntactic structure and continuous-space word and phrase representations into a powerful compositional model. In this paper, we show that RecNNs can be used to perform the core spoken language understanding (SLU) tasks in a spoken dialog system, more specifically domain and intent determination, concurrently with slot filling, in one jointly trained model. We find that a very simple RecNN model achieves competitive performance on the benchmark ATIS task, as well as on a Microsoft Cortana conversational understanding task.
Keywords :
feedforward neural nets; neural nets; recurrent neural nets; speech processing; Microsoft Cortana conversational understanding task; RecNN model; continuous-space word; core spoken language understanding task; discrete syntactic structure; feedforward neural network language model; joint semantic utterance classification; language modeling; language processing task; paraphrase detection; phrase representations; recurrent neural network language model; recursive neural networks; slot filling; spoken dialog system; Joints; Recurrent neural networks; Semantics; Syntactics; Training; Vectors; Dialog Systems; Domain Classification; Intent Determination; Recursive Neural Networks; Slot Filling;
Conference_Titel :
Spoken Language Technology Workshop (SLT), 2014 IEEE
DOI :
10.1109/SLT.2014.7078634