@inproceedings{sengupta-etal-2021-robustness,
title = "On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise",
author = "Sengupta, Sailik and
Krone, Jason and
Mansour, Saab",
editor = "Papangelis, Alexandros and
Budzianowski, Pawe{\l} and
Liu, Bing and
Nouri, Elnaz and
Rastogi, Abhinav and
Chen, Yun-Nung",
booktitle = "Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.nlp4convai-1.7",
doi = "10.18653/v1/2021.nlp4convai-1.7",
pages = "68--79",
abstract = "Intent Classification (IC) and Slot Labeling (SL) models, which form the basis of dialogue systems, often encounter noisy data in real-word environments. In this work, we investigate how robust IC/SL models are to noisy data. We collect and publicly release a test-suite for seven common noise types found in production human-to-bot conversations (abbreviations, casing, misspellings, morphological variants, paraphrases, punctuation and synonyms). On this test-suite, we show that common noise types substantially degrade the IC accuracy and SL F1 performance of state-of-the-art BERT-based IC/SL models. By leveraging cross-noise robustness transfer, i.e. training on one noise type to improve robustness on another noise type, we design aggregate data-augmentation approaches that increase the model performance across all seven noise types by $+10.8\%$ for IC accuracy and $+15$ points for SL F1 on average. To the best of our knowledge, this is the first work to present a single IC/SL model that is robust to a wide range of noise phenomena.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sengupta-etal-2021-robustness">
<titleInfo>
<title>On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sailik</namePart>
<namePart type="family">Sengupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Krone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saab</namePart>
<namePart type="family">Mansour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paweł</namePart>
<namePart type="family">Budzianowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elnaz</namePart>
<namePart type="family">Nouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Rastogi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</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>Intent Classification (IC) and Slot Labeling (SL) models, which form the basis of dialogue systems, often encounter noisy data in real-word environments. In this work, we investigate how robust IC/SL models are to noisy data. We collect and publicly release a test-suite for seven common noise types found in production human-to-bot conversations (abbreviations, casing, misspellings, morphological variants, paraphrases, punctuation and synonyms). On this test-suite, we show that common noise types substantially degrade the IC accuracy and SL F1 performance of state-of-the-art BERT-based IC/SL models. By leveraging cross-noise robustness transfer, i.e. training on one noise type to improve robustness on another noise type, we design aggregate data-augmentation approaches that increase the model performance across all seven noise types by +10.8% for IC accuracy and +15 points for SL F1 on average. To the best of our knowledge, this is the first work to present a single IC/SL model that is robust to a wide range of noise phenomena.</abstract>
<identifier type="citekey">sengupta-etal-2021-robustness</identifier>
<identifier type="doi">10.18653/v1/2021.nlp4convai-1.7</identifier>
<location>
<url>https://aclanthology.org/2021.nlp4convai-1.7</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>68</start>
<end>79</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise
%A Sengupta, Sailik
%A Krone, Jason
%A Mansour, Saab
%Y Papangelis, Alexandros
%Y Budzianowski, Paweł
%Y Liu, Bing
%Y Nouri, Elnaz
%Y Rastogi, Abhinav
%Y Chen, Yun-Nung
%S Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F sengupta-etal-2021-robustness
%X Intent Classification (IC) and Slot Labeling (SL) models, which form the basis of dialogue systems, often encounter noisy data in real-word environments. In this work, we investigate how robust IC/SL models are to noisy data. We collect and publicly release a test-suite for seven common noise types found in production human-to-bot conversations (abbreviations, casing, misspellings, morphological variants, paraphrases, punctuation and synonyms). On this test-suite, we show that common noise types substantially degrade the IC accuracy and SL F1 performance of state-of-the-art BERT-based IC/SL models. By leveraging cross-noise robustness transfer, i.e. training on one noise type to improve robustness on another noise type, we design aggregate data-augmentation approaches that increase the model performance across all seven noise types by +10.8% for IC accuracy and +15 points for SL F1 on average. To the best of our knowledge, this is the first work to present a single IC/SL model that is robust to a wide range of noise phenomena.
%R 10.18653/v1/2021.nlp4convai-1.7
%U https://aclanthology.org/2021.nlp4convai-1.7
%U https://doi.org/10.18653/v1/2021.nlp4convai-1.7
%P 68-79
Markdown (Informal)
[On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise](https://aclanthology.org/2021.nlp4convai-1.7) (Sengupta et al., NLP4ConvAI 2021)
ACL