@inproceedings{nooralahzadeh-etal-2019-reinforcement,
title = "Reinforcement-based denoising of distantly supervised {NER} with partial annotation",
author = "Nooralahzadeh, Farhad and
L{\o}nning, Jan Tore and
{\O}vrelid, Lilja",
editor = "Cherry, Colin and
Durrett, Greg and
Foster, George and
Haffari, Reza and
Khadivi, Shahram and
Peng, Nanyun and
Ren, Xiang and
Swayamdipta, Swabha",
booktitle = "Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6125",
doi = "10.18653/v1/D19-6125",
pages = "225--233",
abstract = "Existing named entity recognition (NER) systems rely on large amounts of human-labeled data for supervision. However, obtaining large-scale annotated data is challenging particularly in specific domains like health-care, e-commerce and so on. Given the availability of domain specific knowledge resources, (e.g., ontologies, dictionaries), distant supervision is a solution to generate automatically labeled training data to reduce human effort. The outcome of distant supervision for NER, however, is often noisy. False positive and false negative instances are the main issues that reduce performance on this kind of auto-generated data. In this paper, we explore distant supervision in a supervised setup. We adopt a technique of partial annotation to address false negative cases and implement a reinforcement learning strategy with a neural network policy to identify false positive instances. Our results establish a new state-of-the-art on four benchmark datasets taken from different domains and different languages. We then go on to show that our model reduces the amount of manually annotated data required to perform NER in a new domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nooralahzadeh-etal-2019-reinforcement">
<titleInfo>
<title>Reinforcement-based denoising of distantly supervised NER with partial annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Farhad</namePart>
<namePart type="family">Nooralahzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="given">Tore</namePart>
<namePart type="family">Lønning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing named entity recognition (NER) systems rely on large amounts of human-labeled data for supervision. However, obtaining large-scale annotated data is challenging particularly in specific domains like health-care, e-commerce and so on. Given the availability of domain specific knowledge resources, (e.g., ontologies, dictionaries), distant supervision is a solution to generate automatically labeled training data to reduce human effort. The outcome of distant supervision for NER, however, is often noisy. False positive and false negative instances are the main issues that reduce performance on this kind of auto-generated data. In this paper, we explore distant supervision in a supervised setup. We adopt a technique of partial annotation to address false negative cases and implement a reinforcement learning strategy with a neural network policy to identify false positive instances. Our results establish a new state-of-the-art on four benchmark datasets taken from different domains and different languages. We then go on to show that our model reduces the amount of manually annotated data required to perform NER in a new domain.</abstract>
<identifier type="citekey">nooralahzadeh-etal-2019-reinforcement</identifier>
<identifier type="doi">10.18653/v1/D19-6125</identifier>
<location>
<url>https://aclanthology.org/D19-6125</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>225</start>
<end>233</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reinforcement-based denoising of distantly supervised NER with partial annotation
%A Nooralahzadeh, Farhad
%A Lønning, Jan Tore
%A Øvrelid, Lilja
%Y Cherry, Colin
%Y Durrett, Greg
%Y Foster, George
%Y Haffari, Reza
%Y Khadivi, Shahram
%Y Peng, Nanyun
%Y Ren, Xiang
%Y Swayamdipta, Swabha
%S Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F nooralahzadeh-etal-2019-reinforcement
%X Existing named entity recognition (NER) systems rely on large amounts of human-labeled data for supervision. However, obtaining large-scale annotated data is challenging particularly in specific domains like health-care, e-commerce and so on. Given the availability of domain specific knowledge resources, (e.g., ontologies, dictionaries), distant supervision is a solution to generate automatically labeled training data to reduce human effort. The outcome of distant supervision for NER, however, is often noisy. False positive and false negative instances are the main issues that reduce performance on this kind of auto-generated data. In this paper, we explore distant supervision in a supervised setup. We adopt a technique of partial annotation to address false negative cases and implement a reinforcement learning strategy with a neural network policy to identify false positive instances. Our results establish a new state-of-the-art on four benchmark datasets taken from different domains and different languages. We then go on to show that our model reduces the amount of manually annotated data required to perform NER in a new domain.
%R 10.18653/v1/D19-6125
%U https://aclanthology.org/D19-6125
%U https://doi.org/10.18653/v1/D19-6125
%P 225-233
Markdown (Informal)
[Reinforcement-based denoising of distantly supervised NER with partial annotation](https://aclanthology.org/D19-6125) (Nooralahzadeh et al., 2019)
ACL