@inproceedings{sahay-etal-2021-semi,
title = "Semi-supervised Interactive Intent Labeling",
author = "Sahay, Saurav and
Okur, Eda and
Hakim, Nagib and
Nachman, Lama",
editor = "Dragut, Eduard and
Li, Yunyao and
Popa, Lucian and
Vucetic, Slobodan",
booktitle = "Proceedings of the Second Workshop on Data Science with Human in the Loop: Language Advances",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.dash-1.5",
doi = "10.18653/v1/2021.dash-1.5",
pages = "31--40",
abstract = "Building the Natural Language Understanding (NLU) modules of task-oriented Spoken Dialogue Systems (SDS) involves a definition of intents and entities, collection of task-relevant data, annotating the data with intents and entities, and then repeating the same process over and over again for adding any functionality/enhancement to the SDS. In this work, we showcase an Intent Bulk Labeling system where SDS developers can interactively label and augment training data from unlabeled utterance corpora using advanced clustering and visual labeling methods. We extend the Deep Aligned Clustering work with a better backbone BERT model, explore techniques to select the seed data for labeling, and develop a data balancing method using an oversampling technique that utilizes paraphrasing models. We also look at the effect of data augmentation on the clustering process. Our results show that we can achieve over 10{\%} gain in clustering accuracy on some datasets using the combination of the above techniques. Finally, we extract utterance embeddings from the clustering model and plot the data to interactively bulk label the samples, reducing the time and effort for data labeling of the whole dataset significantly.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sahay-etal-2021-semi">
<titleInfo>
<title>Semi-supervised Interactive Intent Labeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saurav</namePart>
<namePart type="family">Sahay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eda</namePart>
<namePart type="family">Okur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nagib</namePart>
<namePart type="family">Hakim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lama</namePart>
<namePart type="family">Nachman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Data Science with Human in the Loop: Language Advances</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Dragut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucian</namePart>
<namePart type="family">Popa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slobodan</namePart>
<namePart type="family">Vucetic</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>Building the Natural Language Understanding (NLU) modules of task-oriented Spoken Dialogue Systems (SDS) involves a definition of intents and entities, collection of task-relevant data, annotating the data with intents and entities, and then repeating the same process over and over again for adding any functionality/enhancement to the SDS. In this work, we showcase an Intent Bulk Labeling system where SDS developers can interactively label and augment training data from unlabeled utterance corpora using advanced clustering and visual labeling methods. We extend the Deep Aligned Clustering work with a better backbone BERT model, explore techniques to select the seed data for labeling, and develop a data balancing method using an oversampling technique that utilizes paraphrasing models. We also look at the effect of data augmentation on the clustering process. Our results show that we can achieve over 10% gain in clustering accuracy on some datasets using the combination of the above techniques. Finally, we extract utterance embeddings from the clustering model and plot the data to interactively bulk label the samples, reducing the time and effort for data labeling of the whole dataset significantly.</abstract>
<identifier type="citekey">sahay-etal-2021-semi</identifier>
<identifier type="doi">10.18653/v1/2021.dash-1.5</identifier>
<location>
<url>https://aclanthology.org/2021.dash-1.5</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>31</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semi-supervised Interactive Intent Labeling
%A Sahay, Saurav
%A Okur, Eda
%A Hakim, Nagib
%A Nachman, Lama
%Y Dragut, Eduard
%Y Li, Yunyao
%Y Popa, Lucian
%Y Vucetic, Slobodan
%S Proceedings of the Second Workshop on Data Science with Human in the Loop: Language Advances
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F sahay-etal-2021-semi
%X Building the Natural Language Understanding (NLU) modules of task-oriented Spoken Dialogue Systems (SDS) involves a definition of intents and entities, collection of task-relevant data, annotating the data with intents and entities, and then repeating the same process over and over again for adding any functionality/enhancement to the SDS. In this work, we showcase an Intent Bulk Labeling system where SDS developers can interactively label and augment training data from unlabeled utterance corpora using advanced clustering and visual labeling methods. We extend the Deep Aligned Clustering work with a better backbone BERT model, explore techniques to select the seed data for labeling, and develop a data balancing method using an oversampling technique that utilizes paraphrasing models. We also look at the effect of data augmentation on the clustering process. Our results show that we can achieve over 10% gain in clustering accuracy on some datasets using the combination of the above techniques. Finally, we extract utterance embeddings from the clustering model and plot the data to interactively bulk label the samples, reducing the time and effort for data labeling of the whole dataset significantly.
%R 10.18653/v1/2021.dash-1.5
%U https://aclanthology.org/2021.dash-1.5
%U https://doi.org/10.18653/v1/2021.dash-1.5
%P 31-40
Markdown (Informal)
[Semi-supervised Interactive Intent Labeling](https://aclanthology.org/2021.dash-1.5) (Sahay et al., DaSH 2021)
ACL
- Saurav Sahay, Eda Okur, Nagib Hakim, and Lama Nachman. 2021. Semi-supervised Interactive Intent Labeling. In Proceedings of the Second Workshop on Data Science with Human in the Loop: Language Advances, pages 31–40, Online. Association for Computational Linguistics.