@inproceedings{oguz-vu-2020-two,
title = "A Two-stage Model for Slot Filling in Low-resource Settings: Domain-agnostic Non-slot Reduction and Pretrained Contextual Embeddings",
author = "Oguz, Cennet and
Vu, Ngoc Thang",
editor = "Moosavi, Nafise Sadat and
Fan, Angela and
Shwartz, Vered and
Glava{\v{s}}, Goran and
Joty, Shafiq and
Wang, Alex and
Wolf, Thomas",
booktitle = "Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.sustainlp-1.10",
doi = "10.18653/v1/2020.sustainlp-1.10",
pages = "73--82",
abstract = "Learning-based slot filling - a key component of spoken language understanding systems - typically requires a large amount of in-domain hand-labeled data for training. In this paper, we propose a novel two-stage model architecture that can be trained with only a few in-domain hand-labeled examples. The first step is designed to remove non-slot tokens (i.e., O labeled tokens), as they introduce noise in the input of slot filling models. This step is domain-agnostic and therefore, can be trained by exploiting out-of-domain data. The second step identifies slot names only for slot tokens by using state-of-the-art pretrained contextual embeddings such as ELMO and BERT. We show that our approach outperforms other state-of-art systems on the SNIPS benchmark dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oguz-vu-2020-two">
<titleInfo>
<title>A Two-stage Model for Slot Filling in Low-resource Settings: Domain-agnostic Non-slot Reduction and Pretrained Contextual Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cennet</namePart>
<namePart type="family">Oguz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngoc</namePart>
<namePart type="given">Thang</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nafise</namePart>
<namePart type="given">Sadat</namePart>
<namePart type="family">Moosavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glavaš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Wolf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Learning-based slot filling - a key component of spoken language understanding systems - typically requires a large amount of in-domain hand-labeled data for training. In this paper, we propose a novel two-stage model architecture that can be trained with only a few in-domain hand-labeled examples. The first step is designed to remove non-slot tokens (i.e., O labeled tokens), as they introduce noise in the input of slot filling models. This step is domain-agnostic and therefore, can be trained by exploiting out-of-domain data. The second step identifies slot names only for slot tokens by using state-of-the-art pretrained contextual embeddings such as ELMO and BERT. We show that our approach outperforms other state-of-art systems on the SNIPS benchmark dataset.</abstract>
<identifier type="citekey">oguz-vu-2020-two</identifier>
<identifier type="doi">10.18653/v1/2020.sustainlp-1.10</identifier>
<location>
<url>https://aclanthology.org/2020.sustainlp-1.10</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>73</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Two-stage Model for Slot Filling in Low-resource Settings: Domain-agnostic Non-slot Reduction and Pretrained Contextual Embeddings
%A Oguz, Cennet
%A Vu, Ngoc Thang
%Y Moosavi, Nafise Sadat
%Y Fan, Angela
%Y Shwartz, Vered
%Y Glavaš, Goran
%Y Joty, Shafiq
%Y Wang, Alex
%Y Wolf, Thomas
%S Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F oguz-vu-2020-two
%X Learning-based slot filling - a key component of spoken language understanding systems - typically requires a large amount of in-domain hand-labeled data for training. In this paper, we propose a novel two-stage model architecture that can be trained with only a few in-domain hand-labeled examples. The first step is designed to remove non-slot tokens (i.e., O labeled tokens), as they introduce noise in the input of slot filling models. This step is domain-agnostic and therefore, can be trained by exploiting out-of-domain data. The second step identifies slot names only for slot tokens by using state-of-the-art pretrained contextual embeddings such as ELMO and BERT. We show that our approach outperforms other state-of-art systems on the SNIPS benchmark dataset.
%R 10.18653/v1/2020.sustainlp-1.10
%U https://aclanthology.org/2020.sustainlp-1.10
%U https://doi.org/10.18653/v1/2020.sustainlp-1.10
%P 73-82
Markdown (Informal)
[A Two-stage Model for Slot Filling in Low-resource Settings: Domain-agnostic Non-slot Reduction and Pretrained Contextual Embeddings](https://aclanthology.org/2020.sustainlp-1.10) (Oguz & Vu, sustainlp 2020)
ACL