Open-world Learning and Application to Product Classification

Xu, Hongwu; Liu, Bing; Shu, Lei; Yu, Peilin

doi:10.1145/3308558.3313644

Cited by 99 publications

(49 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, most of these methods are computationally expensive either in training or inference, and cannot take full advantage of unlabeled data to improve the OOD detection performance. Some of these methods also require a tremendous amount of memories as the number of classes increases [33]. All these disadvantages limit the feasibility of these methods in practical applications.…”

Section: Related Workmentioning

confidence: 99%

Out-of-Domain Detection for Natural Language Understanding in Dialog Systems

Zheng

Chen

Huang

2020

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Natural Language Understanding (NLU) is a vital component of dialogue systems, and its ability to detect Out-of-Domain (OOD) inputs is critical in practical applications, since the acceptance of the OOD input that is unsupported by the current system may lead to catastrophic failure. However, most existing OOD detection methods rely heavily on manually labeled OOD samples and cannot take full advantage of unlabeled data. This limits the feasibility of these models in practical applications.In this paper, we propose a novel model to generate highquality pseudo OOD samples that are akin to IN-Domain (IND) input utterances, and thereby improves the performance of OOD detection. To this end, an autoencoder is trained to map an input utterance into a latent code. and the codes of IND and OOD samples are trained to be indistinguishable by utilizing a generative adversarial network. To provide more supervision signals, an auxiliary classifier is introduced to regularize the generated OOD samples to have indistinguishable intent labels. Experiments show that these pseudo OOD samples generated by our model can be used to effectively improve OOD detection in NLU. Besides, we also demonstrate that the effectiveness of these pseudo OOD data can be further improved by efficiently utilizing unlabeled data.

show abstract

Section: Related Workmentioning

confidence: 99%

Out-of-Domain Detection for Natural Language Understanding in Dialog Systems

Zheng

Chen

Huang

2020

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…Rios and Kavuluru (2018) developed a few-shot text classification model for multi-label text classification where there was a known structure over the label space. Xu et al (2019) proposed a open-world learning model to deal with the unseen classes in the product classification problem. We solve the few-shot learning problem from a different perspective and propose a dynamic routing induction method to encapsulate the abstract class representation from samples, achieving state-of-the-art performances on two datasets.…”

Section: Few-shot Learningmentioning

confidence: 99%

Induction Networks for Few-Shot Text Classification

Geng¹,

Li²,

Li³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

170

122

View full text Add to dashboard Cite

Text classification tends to struggle when data is deficient or when it needs to adapt to unseen classes. In such challenging scenarios, recent studies have used meta-learning to simulate the few-shot task, in which new queries are compared to a small support set at the samplewise level. However, this sample-wise comparison may be severely disturbed by the various expressions in the same class. Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries. In this paper, we propose a novel Induction Network to learn such a generalized class-wise representation, by innovatively leveraging the dynamic routing algorithm in meta-learning. In this way, we find the model is able to induce and generalize better. We evaluate the proposed model on a well-studied sentiment classification dataset (English) and a real-world dialogue intent classification dataset (Chinese). Experiment results show that on both datasets, the proposed model significantly outperforms the existing state-of-the-art approaches, proving the effectiveness of class-wise generalization in few-shot text classification. * * Corresponding authors: Y.Li and P.Jian.

show abstract

“…Few-shot text classification Few-shot classification (Fei-Fei et al, 2006;Vinyals et al, 2016b) has been applied to text classification tasks (Deng et al, 2019;Geng et al, 2019;Xu et al, 2019), and few-shot intent detection is also studied but without OOS (Luo et al, 2018;Casanueva et al, 2020). There are two common scenarios: 1) learning with plenty of examples and then generalizing to unseen classes with a few examples, and 2) learning with a few examples for all seen classes.…”

Section: Call For Better Embeddingsmentioning

confidence: 99%

Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference

Zhang¹,

Hashimoto²,

Liu³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Intent detection is one of the core components of goal-oriented dialog systems, and detecting out-of-scope (OOS) intents is also a practically important skill. Few-shot learning is attracting much attention to mitigate data scarcity, but OOS detection becomes even more challenging. In this paper, we present a simple yet effective approach, discriminative nearest neighbor classification with deep self-attention. Unlike softmax classifiers, we leverage BERTstyle pairwise encoding to train a binary classifier that estimates the best matched training example for a user input. We propose to boost the discriminative ability by transferring a natural language inference (NLI) model. Our extensive experiments on a large-scale multi-domain intent detection task show that our method achieves more stable and accurate in-domain and OOS detection accuracy than RoBERTa-based classifiers and embeddingbased nearest neighbor approaches. More notably, the NLI transfer enables our 10-shot model to perform competitively with 50-shot or even full-shot classifiers, while we can keep the inference time constant by leveraging a faster embedding retrieval model.

show abstract

Open-world Learning and Application to Product Classification

Cited by 99 publications

References 22 publications

Out-of-Domain Detection for Natural Language Understanding in Dialog Systems

Out-of-Domain Detection for Natural Language Understanding in Dialog Systems

Induction Networks for Few-Shot Text Classification

Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference

Contact Info

Product

Resources

About