A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery

7 Mar 2023  ·  Masoud Akbari, Ali Mohades, M. Hassan Shirali-Shahreza ·

Intent Detection is one of the tasks of the Natural Language Understanding (NLU) unit in task-oriented dialogue systems. Out of Scope (OOS) and Out of Domain (OOD) inputs may run these systems into a problem. On the other side, a labeled dataset is needed to train a model for Intent Detection in task-oriented dialogue systems. The creation of a labeled dataset is time-consuming and needs human resources. The purpose of this article is to address mentioned problems. The task of identifying OOD/OOS inputs is named OOD/OOS Intent Detection. Also, discovering new intents and pseudo-labeling of OOD inputs is well known by Intent Discovery. In OOD intent detection part, we make use of a Variational Autoencoder to distinguish between known and unknown intents independent of input data distribution. After that, an unsupervised clustering method is used to discover different unknown intents underlying OOD/OOS inputs. We also apply a non-linear dimensionality reduction on OOD/OOS representations to make distances between representations more meaning full for clustering. Our results show that the proposed model for both OOD/OOS Intent Detection and Intent Discovery achieves great results and passes baselines in English and Persian languages.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Intent Discovery ATIS k-PCA + HDBSCAN ARI 74.94 # 1
Out of Distribution (OOD) Detection ATIS BERT + VAE F1 - macro 86.79 # 1
Intent Discovery Persian-ATIS k-PCA + HDBSCAN ARI 11.97 # 1
Out of Distribution (OOD) Detection Persian-ATIS BERT + VAE F1 Macro 79.03 # 1
Intent Discovery SNIPS k-PCA + HDBSCAN ARI 59.23 # 1
Out of Distribution (OOD) Detection SNIPS BERT + VAE F1 Macro 92.32 # 1