Toward zero-shot Entity Recognition in Task-oriented Conversational Agents

Guerini, Marco; Magnolini, Simone; Balaraman, Vevake; Magnini, Bernardo

doi:10.18653/v1/w18-5036

Cited by 22 publications

(19 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al (2017) reduced the search space of semantic parsers by using coarse macro grammars. Different from the previous work, we apply the idea of coarse-to-fine into cross-domain slot filling to handle unseen slot types by separating the slot filling task into two steps (Zhai et al, 2017;Guerini et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling

Liu¹,

Winata²,

Xu³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

As an essential task in task-oriented dialog systems, slot filling requires extensive training data in a certain domain. However, such data are not always available. Hence, cross-domain slot filling has naturally arisen to cope with this data scarcity problem. In this paper, we propose a Coarse-to-fine approach (Coach) for cross-domain slot filling. Our model first learns the general pattern of slot entities by detecting whether the tokens are slot entities or not. It then predicts the specific types for the slot entities. In addition, we propose a template regularization approach to improve the adaptation robustness by regularizing the representation of utterances based on utterance templates. Experimental results show that our model significantly outperforms state-of-theart approaches in slot filling. Furthermore, our model can also be applied to the cross-domain named entity recognition task, and it achieves better adaptation performance than other existing baselines. The code is available at https:

show abstract

Section: Related Workmentioning

confidence: 99%

Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling

Liu¹,

Winata²,

Xu³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…Jointly modeling multiple slots for the task is an interesting future direction. Another possible direction is to incorporate zero-shot entity recognition (Guerini et al, 2018), thereby eliminating the need for example values during inference.…”

Section: Discussionmentioning

confidence: 99%

Robust Zero-Shot Cross-Domain Slot Filling with Example Values

Shah¹,

Gupta²,

Fayazi³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Task-oriented dialog systems increasingly rely on deep learning-based slot filling models, usually needing extensive labeled training data for target domains. Often, however, little to no target domain training data may be available, or the training and target domain schemas may be misaligned, as is common for web forms on similar websites. Prior zero-shot slot filling models use slot descriptions to learn concepts, but are not robust to misaligned schemas. We propose utilizing both the slot description and a small number of examples of slot values, which may be easily available, to learn semantic representations of slots which are transferable across domains and robust to misaligned schemas. Our approach outperforms state-ofthe-art models on two multi-domain datasets, especially in the low-data setting.

show abstract

“…Although deep learning shows promising NER performance (particularly in place extraction), the in-availability of sufficient annotated data is very limiting, especially for novel and evolving events. To mitigate the challenge, Guerini et al (2018) proposed a domain portable zero-shot learning approach for entity recognition, which does not assume any annotated sentences at training time. More specifically, they trained a 3-layer Bi-LSTM model based only on available gazetteers and synthesized examples.…”

Section: Related Workmentioning

confidence: 99%

“…The third approach is statistical learning (Finkel, Grenager, and Manning 2005;Kumar and Singh 2019), tagging the place names mainly according to the contextual features of the place names, such as Stanza (Qi et al 2020) and Neu-roTPR (Wang, Hu, and Joseph 2020). However, they require a considerable amount of annotated sentences which makes those approaches ineffective in most practical situations (Guerini et al 2018). Moreover, according to the experimental results, intrinsic features of place names are more important than contextual features in detecting the place names from microblogs due to the weak contextual cures in microblogs caused by dramatic variation of the writing styles and numerous grammar errors in microblogs (Ritter et al 2011).…”

Section: Introductionmentioning

confidence: 99%

GazPNE: annotation-free deep learning for place name extraction from microblogs leveraging gazetteer and synthetic data by rules

Al-Olimat

Kersten

et al. 2021

International Journal of Geographical Information Science

View full text Add to dashboard Cite

Place name extraction refers to the task of detecting precise location information in texts like microblogs. It is a vital task to assist disaster response, revealing where the damages are, where people need assistance, and where help can be found. All current approaches for extracting the place names from microblogs face crucial problems: rule-based methods do not generalize, gazetteer-based methods do not detect unknown multi-word place names, and machine learning methods lack sufficient data, which is costly to annotate on scale. We propose a hybrid method that avoids these problems, named GazPNE, which fuses rules, gazetteers, and deep learning methods to achieve state-of-the-art-performance without requiring any manually annotated data.Specifically, we utilize C-LSTM, a fusion of Convolutional and Long Short-Term Memory Neural Networks, to decide if an n-gram in a microblog text is a place name or not. The C-LSTM is trained on 4.6 million positive examples extracted from OpenStreetMap and GeoNames and 220 million negative examples synthesized by rules and evaluated on 4,500 disaster-related tweets, including 9,026 place names from three floods: 2016 in Louisiana (US), 2016 in Houston (US), and 2015 in Chennai (India). Our method improves the previous state-of-the-art by 6%, achieving an F1 of 0.86.

show abstract

Toward zero-shot Entity Recognition in Task-oriented Conversational Agents

Cited by 22 publications

References 15 publications

Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling

Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling

Robust Zero-Shot Cross-Domain Slot Filling with Example Values

GazPNE: annotation-free deep learning for place name extraction from microblogs leveraging gazetteer and synthetic data by rules

Contact Info

Product

Resources

About