@inproceedings{goruganthu-etal-2024-adaptive,
title = "Adaptive Open-Set Active Learning with Distance-Based Out-of-Distribution Detection for Robust Task-Oriented Dialog System",
author = "Goruganthu, Sai Keerthana and
Oruche, Roland R. and
Calyam, Prasad",
editor = "Kawahara, Tatsuya and
Demberg, Vera and
Ultes, Stefan and
Inoue, Koji and
Mehri, Shikib and
Howcroft, David and
Komatani, Kazunori",
booktitle = "Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2024",
address = "Kyoto, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sigdial-1.32",
doi = "10.18653/v1/2024.sigdial-1.32",
pages = "357--369",
abstract = "The advancements in time-efficient data collection techniques such as active learning (AL) has become salient for user intent classification performance in task-oriented dialog systems (TODS). In realistic settings, however, traditional AL techniques often fail to efficiently select targeted in-distribution (IND) data when encountering newly acquired out-of-distribution (OOD) user intents in the unlabeled pool. In this paper, we introduce a novel AL framework viz., AOSAL for TODS that combines a distance-based OOD detector using adaptive false positive rate threshold with an informativeness measure (e.g., entropy) to strategically select informative IND data points in the unlabeled pool. Specifically, we utilize the adaptive OOD detector to classify and filter out OOD samples from the unlabeled pool, then prioritize the acquisition of classified IND instances based on their informativeness scores. To validate our approach, we conduct experiments that display our framework{'}s flexibility and performance over multiple distance-based approaches and informativeness measures against deep AL baselines on benchmark text datasets. The results suggest that our AOSAL approach consistently outperforms the baselines on IND classification and OOD detection, advancing knowledge on improving robustness of task-oriented dialog systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goruganthu-etal-2024-adaptive">
<titleInfo>
<title>Adaptive Open-Set Active Learning with Distance-Based Out-of-Distribution Detection for Robust Task-Oriented Dialog System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Keerthana</namePart>
<namePart type="family">Goruganthu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roland</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Oruche</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prasad</namePart>
<namePart type="family">Calyam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikib</namePart>
<namePart type="family">Mehri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Howcroft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Komatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyoto, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The advancements in time-efficient data collection techniques such as active learning (AL) has become salient for user intent classification performance in task-oriented dialog systems (TODS). In realistic settings, however, traditional AL techniques often fail to efficiently select targeted in-distribution (IND) data when encountering newly acquired out-of-distribution (OOD) user intents in the unlabeled pool. In this paper, we introduce a novel AL framework viz., AOSAL for TODS that combines a distance-based OOD detector using adaptive false positive rate threshold with an informativeness measure (e.g., entropy) to strategically select informative IND data points in the unlabeled pool. Specifically, we utilize the adaptive OOD detector to classify and filter out OOD samples from the unlabeled pool, then prioritize the acquisition of classified IND instances based on their informativeness scores. To validate our approach, we conduct experiments that display our framework’s flexibility and performance over multiple distance-based approaches and informativeness measures against deep AL baselines on benchmark text datasets. The results suggest that our AOSAL approach consistently outperforms the baselines on IND classification and OOD detection, advancing knowledge on improving robustness of task-oriented dialog systems.</abstract>
<identifier type="citekey">goruganthu-etal-2024-adaptive</identifier>
<identifier type="doi">10.18653/v1/2024.sigdial-1.32</identifier>
<location>
<url>https://aclanthology.org/2024.sigdial-1.32</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>357</start>
<end>369</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adaptive Open-Set Active Learning with Distance-Based Out-of-Distribution Detection for Robust Task-Oriented Dialog System
%A Goruganthu, Sai Keerthana
%A Oruche, Roland R.
%A Calyam, Prasad
%Y Kawahara, Tatsuya
%Y Demberg, Vera
%Y Ultes, Stefan
%Y Inoue, Koji
%Y Mehri, Shikib
%Y Howcroft, David
%Y Komatani, Kazunori
%S Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2024
%8 September
%I Association for Computational Linguistics
%C Kyoto, Japan
%F goruganthu-etal-2024-adaptive
%X The advancements in time-efficient data collection techniques such as active learning (AL) has become salient for user intent classification performance in task-oriented dialog systems (TODS). In realistic settings, however, traditional AL techniques often fail to efficiently select targeted in-distribution (IND) data when encountering newly acquired out-of-distribution (OOD) user intents in the unlabeled pool. In this paper, we introduce a novel AL framework viz., AOSAL for TODS that combines a distance-based OOD detector using adaptive false positive rate threshold with an informativeness measure (e.g., entropy) to strategically select informative IND data points in the unlabeled pool. Specifically, we utilize the adaptive OOD detector to classify and filter out OOD samples from the unlabeled pool, then prioritize the acquisition of classified IND instances based on their informativeness scores. To validate our approach, we conduct experiments that display our framework’s flexibility and performance over multiple distance-based approaches and informativeness measures against deep AL baselines on benchmark text datasets. The results suggest that our AOSAL approach consistently outperforms the baselines on IND classification and OOD detection, advancing knowledge on improving robustness of task-oriented dialog systems.
%R 10.18653/v1/2024.sigdial-1.32
%U https://aclanthology.org/2024.sigdial-1.32
%U https://doi.org/10.18653/v1/2024.sigdial-1.32
%P 357-369
Markdown (Informal)
[Adaptive Open-Set Active Learning with Distance-Based Out-of-Distribution Detection for Robust Task-Oriented Dialog System](https://aclanthology.org/2024.sigdial-1.32) (Goruganthu et al., SIGDIAL 2024)
ACL