Neural sentence embedding using only in-domain sentences for out-of-domain sentence detection in dialog systems
By Seonghan Ryu, Seokhwan Kim, Junhwi Choi, Hwanjo Yu, G. G. Lee. 2017
56 citations recorded by the source corpus.
Only in-domain sentences are used to train out-of-domain sentence detection.A long short-term memory network is used to extract features from sentences.Domain-category analysis is used as an auxiliary task.A two-channel approach is applied to word representations.An autoencoder is used for one-class classification. To ensure satisfactory user experience, dialog systems must be able to determine whether an input sentence is in-domain (ID) or out-of-domain (OOD). We assume that only ID sentences are available as training data because collecting enough OOD sentences in an unbiased way is a laborious and time-consuming job. This paper proposes a novel neural sentence embedding method that represents sentences in a low-dimensional continuous vector space that emphasizes aspects that distinguish ID cases from OOD cases. We first used a large set of unlabeled text to pre-train word representations that are used to initialize neural sentence embedding. Then we used domain-category analysis as an auxiliary task to train neural sentence embedding for OOD sentence detection. After the sentence representations were learned, we used them to train an autoencoder aimed at OOD sentence detection. We evaluated our method by experimentally comparing it to the state-of-the-art methods in an eight-domain dialog system; our proposed method achieved the highest accuracy in all tests.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Greg Van Houdt
- Hwanjo Yu
- Minlie Huang
- Carlos Mosquera
- G. G. Lee
- Gonzalo Nápoles
- Joo-Kyung Kim
- Sangjun Koo
Citations in the corpus
- Out-of-Domain Detection for Natural Language Understanding in Dialog Systems (2019, background): “Popular approaches include modeling the probability density [8], [25], computing reconstruction losses [7], [26],”
- Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates (2018, methodology): “Also, the methods are evaluated either based on IND recall and OOD recall [5] or Equal Error Rate (ERR), where thresholding is used to match FAR and FRR to be the same [4, 6].”
- Out-of-domain Detection based on Generative Adversarial Network (2018, methodology): “Ryu et al. (2017) proposed an autoencoder – based method.”
- A review on the long short-term memory model (2020, methodology): “In Ryu et al. (2017) a binary classifier was built using two LSTM layers.”