@inproceedings{ravi-kozareva-2021-soda,
title = "{S}o{DA}: On-device Conversational Slot Extraction",
author = "Ravi, Sujith and
Kozareva, Zornitsa",
editor = "Li, Haizhou and
Levow, Gina-Anne and
Yu, Zhou and
Gupta, Chitralekha and
Sisman, Berrak and
Cai, Siqi and
Vandyke, David and
Dethlefs, Nina and
Wu, Yan and
Li, Junyi Jessy",
booktitle = "Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = jul,
year = "2021",
address = "Singapore and Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sigdial-1.7",
doi = "10.18653/v1/2021.sigdial-1.7",
pages = "56--65",
abstract = "We propose a novel on-device neural sequence labeling model which uses embedding-free projections and character information to construct compact word representations to learn a sequence model using a combination of bidirectional LSTM with self-attention and CRF. Unlike typical dialog models that rely on huge, complex neural network architectures and large-scale pre-trained Transformers to achieve state-of-the-art results, our method achieves comparable results to BERT and even outperforms its smaller variant DistilBERT on conversational slot extraction tasks. Our method is faster than BERT models while achieving significant model size reduction{--}our model requires 135x and 81x fewer model parameters than BERT and DistilBERT, respectively. We conduct experiments on multiple conversational datasets and show significant improvements over existing methods including recent on-device models. Experimental results and ablation studies also show that our neural models preserve tiny memory footprint necessary to operate on smart devices, while still maintaining high performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ravi-kozareva-2021-soda">
<titleInfo>
<title>SoDA: On-device Conversational Slot Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sujith</namePart>
<namePart type="family">Ravi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haizhou</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gina-Anne</namePart>
<namePart type="family">Levow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chitralekha</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berrak</namePart>
<namePart type="family">Sisman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vandyke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Dethlefs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore and Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a novel on-device neural sequence labeling model which uses embedding-free projections and character information to construct compact word representations to learn a sequence model using a combination of bidirectional LSTM with self-attention and CRF. Unlike typical dialog models that rely on huge, complex neural network architectures and large-scale pre-trained Transformers to achieve state-of-the-art results, our method achieves comparable results to BERT and even outperforms its smaller variant DistilBERT on conversational slot extraction tasks. Our method is faster than BERT models while achieving significant model size reduction–our model requires 135x and 81x fewer model parameters than BERT and DistilBERT, respectively. We conduct experiments on multiple conversational datasets and show significant improvements over existing methods including recent on-device models. Experimental results and ablation studies also show that our neural models preserve tiny memory footprint necessary to operate on smart devices, while still maintaining high performance.</abstract>
<identifier type="citekey">ravi-kozareva-2021-soda</identifier>
<identifier type="doi">10.18653/v1/2021.sigdial-1.7</identifier>
<location>
<url>https://aclanthology.org/2021.sigdial-1.7</url>
</location>
<part>
<date>2021-07</date>
<extent unit="page">
<start>56</start>
<end>65</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SoDA: On-device Conversational Slot Extraction
%A Ravi, Sujith
%A Kozareva, Zornitsa
%Y Li, Haizhou
%Y Levow, Gina-Anne
%Y Yu, Zhou
%Y Gupta, Chitralekha
%Y Sisman, Berrak
%Y Cai, Siqi
%Y Vandyke, David
%Y Dethlefs, Nina
%Y Wu, Yan
%Y Li, Junyi Jessy
%S Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2021
%8 July
%I Association for Computational Linguistics
%C Singapore and Online
%F ravi-kozareva-2021-soda
%X We propose a novel on-device neural sequence labeling model which uses embedding-free projections and character information to construct compact word representations to learn a sequence model using a combination of bidirectional LSTM with self-attention and CRF. Unlike typical dialog models that rely on huge, complex neural network architectures and large-scale pre-trained Transformers to achieve state-of-the-art results, our method achieves comparable results to BERT and even outperforms its smaller variant DistilBERT on conversational slot extraction tasks. Our method is faster than BERT models while achieving significant model size reduction–our model requires 135x and 81x fewer model parameters than BERT and DistilBERT, respectively. We conduct experiments on multiple conversational datasets and show significant improvements over existing methods including recent on-device models. Experimental results and ablation studies also show that our neural models preserve tiny memory footprint necessary to operate on smart devices, while still maintaining high performance.
%R 10.18653/v1/2021.sigdial-1.7
%U https://aclanthology.org/2021.sigdial-1.7
%U https://doi.org/10.18653/v1/2021.sigdial-1.7
%P 56-65
Markdown (Informal)
[SoDA: On-device Conversational Slot Extraction](https://aclanthology.org/2021.sigdial-1.7) (Ravi & Kozareva, SIGDIAL 2021)
ACL
- Sujith Ravi and Zornitsa Kozareva. 2021. SoDA: On-device Conversational Slot Extraction. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 56–65, Singapore and Online. Association for Computational Linguistics.