Zero-shot semantic parser for spoken language understanding

Ferreira, Emmanuel; Jabaian, Bassam; Lefèvre, Fabrice

doi:10.21437/interspeech.2015-57

Cited by 26 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compatibility models (Chen, Hakkani-Tür, and He 2016;Kumar et al 2017) attempt to learn a shared semantic space for label names and utterances, and then perform intent detection by measuring the intent-utterance similarity in this space. There are also studies resorting to external knowledge, e.g., label ontologies (Ferreira, Jabaian, and Lefevre 2015;Ferreira, Jabaian, and Lefèvre 2015) or human-defined attributes (Yazdani and Henderson 2015;Zhang, Lertvittayakumjorn, and Guo 2019), which, however, are laborious to obtain.…”

Section: Related Workmentioning

confidence: 99%

Learning Class-Transductive Intent Representations for Zero-shot Intent Detection

Liu

et al. 2020

Preprint

View full text Add to dashboard Cite

Zero-shot intent detection (ZSID) aims to deal with the continuously emerging intents without annotated training data. However, existing ZSID systems suffer from two limitations: 1) They are not good at modeling the relationship between seen and unseen intents, when the label names are given in the form of raw phrases or sentences. 2) They cannot effectively recognize unseen intents under the generalized intent detection (GZSID) setting. A critical factor behind these limitations is the representations of unseen intents, which cannot be learned in the training stage. To address this problem, we propose a class-transductive framework that utilizes unseen class labels to learn Disentangled Intent Representations (DIR). Specifically, we allow the model to predict unseen intents in the training stage, with the corresponding label names serving as input utterances. Under this framework, we introduce a multi-task learning objective, which encourages the model to learn the distinctions among intents, and a similarity scorer, which estimates the connections among intents more accurately based on the learned intent representations. Since the purpose of DIR is to provide better intent representations, it can be easily integrated with existing ZSID and GZSID methods. Experiments on two real-world datasets show that the proposed framework brings consistent improvement to the baseline systems, regardless of the model architectures or zero-shot learning strategies.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning Class-Transductive Intent Representations for Zero-shot Intent Detection

Liu

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…To overcome the OOV problem of semantic labels, we first map them to atomic exemplars with a little of human effort. Zero-shot learning of SLU Besides data augmentation, zero-shot learning of SLU (Ferreira et al, 2015;Yazdani and Henderson, 2015) is also related, which can adapt to unseen semantic labels. Yazdani and Henderson (2015) exploit a binary classifier for each possible act-slot-value triple to predict whether it exists in the input sentence.…”

Section: Related Workmentioning

confidence: 99%

Data Augmentation with Atomic Templates for Spoken Language Understanding

Zhao

Zhu

2019

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

View full text Add to dashboard Cite

Spoken Language Understanding (SLU) converts user utterances into structured semantic representations. Data sparsity is one of the main obstacles of SLU due to the high cost of human annotation, especially when domain changes or a new domain comes. In this work, we propose a data augmentation method with atomic templates for SLU, which involves minimum human efforts. The atomic templates produce exemplars for fine-grained constituents of semantic representations. We propose an encoder-decoder model to generate the whole utterance from atomic exemplars. Moreover, the generator could be transferred from source domains to help a new domain which has little data. Experimental results show that our method achieves significant improvements on DSTC 2&3 dataset which is a domain adaptation setting of SLU.

show abstract

“…Dadashkarimi et al (2018) proposed a transfer learning approach where a domain label is predicted first and then the parse. Ferreira et al (2015) and Herzig and Berant (2018) proposed slot-filling methods for semantic parsing based on general word embeddings. Bapna et al (2017) focuses on zero-shot frame semantic parsing by leveraging the description of slots to be filled.…”

Section: Related Workmentioning

confidence: 99%

Look-up and Adapt: A One-shot Semantic Parser

Arabshahi

Labutov

et al. 2019

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

View full text Add to dashboard Cite

Computing devices have recently become capable of interacting with their end users via natural language. However, they can only operate within a limited "supported" domain of discourse and fail drastically when faced with an out-of-domain utterance, mainly due to the limitations of their semantic parser. In this paper, we propose a semantic parser that generalizes to out-of-domain examples by learning a general strategy for parsing an unseen utterance through adapting the logical forms of seen utterances, instead of learning to generate a logical form from scratch. Our parser maintains a memory consisting of a representative subset of the seen utterances paired with their logical forms. Given an unseen utterance, our parser works by looking up a similar utterance from the memory and adapting its logical form until it fits the unseen utterance. Moreover, we present a data generation strategy for constructing utterance-logical form pairs from different domains. Our results show an improvement of up to 68.8% on one-shot parsing under two different evaluation settings compared to the baselines.

show abstract

Zero-shot semantic parser for spoken language understanding

Cited by 26 publications

References 15 publications

Learning Class-Transductive Intent Representations for Zero-shot Intent Detection

Learning Class-Transductive Intent Representations for Zero-shot Intent Detection

Data Augmentation with Atomic Templates for Spoken Language Understanding

Look-up and Adapt: A One-shot Semantic Parser

Contact Info

Product

Resources

About