Abstract
Speaker intent detection and semantic slot filling are two critical tasks in spoken language understanding (SLU) for dialogue systems. In this paper, we describe a recurrent neural network (RNN) model that jointly performs intent detection, slot filling, and language modeling. The neural network model keeps updating the intent estimation as word in the transcribed utterance arrives and uses it as contextual features in the joint model. Evaluation of the language model and online SLU model is made on the ATIS benchmarking data set. On language modeling task, our joint model achieves 11.8% relative reduction on perplexity comparing to the independent training language model. On SLU tasks, our joint model outperforms the independent task training model by 22.3% on intent detection error rate, with slight degradation on slot filling F1 score. The joint model also shows advantageous performance in the realistic ASR settings with noisy speech input.
Highlights
As a critical component in spoken dialogue systems, spoken language understanding (SLU) system interprets the semantic meanings conveyed by speech signals
If the recurrent neural network (RNN) output ht is connected to each task output directly via linear projection without using multilayer perceptrons (MLPs), performance drops for intent classification and slot filling
Model performance is evaluated in terms of automatic speech recognition (ASR) word error rate (WER), intent classification error, and slot filling F1 score
Summary
As a critical component in spoken dialogue systems, spoken language understanding (SLU) system interprets the semantic meanings conveyed by speech signals. Major components in SLU systems include identifying speaker’s intent and extracting semantic constituents from the natural language query, two tasks that are often referred to as intent detection and slot filling. Intent detection can be treated as a semantic utterance classification problem, and slot filling can be treated as a sequence labeling task. These two tasks are usually processed separately by different models. A major task in spoken language understanding (SLU) is to extract semantic constituents by searching input text to fill in values for predefined slots in a semantic frame (Mesnil et al, 2015), which is often referred to as slot filling. The slot filling task can be viewed as assigning an appropriate semantic label to each word in the given input text. Other words in the example utterance that carry no semantic meaning are assigned “O” label
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
