A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5467–5471 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 5467 A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling Haihong E∗, Peiqing Niu∗, Zhongfu Chen∗, Meina Song Beijing University of Posts and Telecommunications, Beijing, China {ehaihong,niupeiqing,chenzhongfu,mnsong}@bupt.edu.cn Abstract A spoken language understanding (SLU) sys- tem includes two main tasks, slot filling (SF) and intent detection (ID). The joint model for the two tasks is becoming a tendency in SLU. But the bi-directional interrelated connections between the intent and slots are not established in the existing joint models. In this paper, we propose a novel bi-directional interrelated model for joint intent detection and slot fill- ing. We introduce an SF-ID network to es- tablish direct connections for the two tasks to help them promote each other mutually. Besides, we design an entirely new iteration mechanism inside the SF-ID network to en- hance the bi-directional interrelated connec- tions. The experimental results show that the relative improvement in the sentence-level se- mantic frame accuracy of our model is 3.79% and 5.42% on ATIS and Snips datasets, respec- tively, compared to the state-of-the-art model. 1 Introduction Spoken language understanding plays an impor- tant role in spoken dialogue system. SLU aims at extracting the semantics from user utterances. Concretely, it identifies the intent and captures se- mantic constituents. These two tasks are known as intent detection and slot filling (Tur and De Mori, 2011), respectively. For instance, the sentence ‘what flights leave from phoenix’ sampled from the ATIS corpus is shown in Table 1. It can be seen that each word in the sentence corresponds to one slot label, and a specific intent is assigned for the whole sentence. Sentence what flights leave from phoenix Slots O O O O B-fromloc Intent atis flight Table 1: An example sentence from the ATIS corpus ∗ Authors contributed equally. Traditional pipeline approaches manage the two mentioned tasks separately. Intent detection is seen as a semantic classification problem to pre- dict the intent label. General approaches such as support vector machine (SVM) (Haffner et al., 2003) and recurrent neural network (RNN) (Lai et al., 2015) can be applied. Slot filling is re- garded as a sequence labeling task. Popular ap- proaches include conditional random field (CRF) (Raymond and Riccardi, 2007), long short-term memory (LSTM) networks (Yao et al., 2014). Considering the unsatisfactory performance of pipeline approaches caused by error propagation, the tendency is to develop a joint model (Chen et al., 2016a; Zhang and Wang, 2016) for intent de- tection and slot filling tasks. Liu and Lane (2016) proposed an attention-based RNN model. How- ever, it just applied a joint loss function to link the two tasks implicitly. Hakkani-T¨ur et al. (2016) in- troduced a RNN-LSTM model where the explicit relationships between the slots and intent are not established. Goo et al. (2018) proposed a slot- gated model which applies the intent information to slot filling task and …

Content truncated to 500 words