@inproceedings{gerhard-young-etal-2022-low,
title = "Low-Resource Adaptation of Open-Domain Generative Chatbots",
author = "Gerhard-Young, Greyson and
Anantha, Raviteja and
Chappidi, Srinivas and
Hoffmeister, Bjorn",
editor = "Feng, Song and
Wan, Hui and
Yuan, Caixia and
Yu, Han",
booktitle = "Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.dialdoc-1.3",
doi = "10.18653/v1/2022.dialdoc-1.3",
pages = "23--30",
abstract = "Recent work building open-domain chatbots has demonstrated that increasing model size improves performance (Adiwardana et al., 2020; Roller et al., 2020). On the other hand, latency and connectivity considerations dictate the move of digital assistants on the device (Verge, 2021). Giving a digital assistant like Siri, Alexa, or Google Assistant the ability to discuss just about anything leads to the need for reducing the chatbot model size such that it fits on the user{'}s device. We demonstrate that low parameter models can simultaneously retain their general knowledge conversational abilities while improving in a specific domain. Additionally, we propose a generic framework that accounts for variety in question types, tracks reference throughout multi-turn conversations, and removes inconsistent and potentially toxic responses. Our framework seamlessly transitions between chatting and performing transactional tasks, which will ultimately make interactions with digital assistants more human-like. We evaluate our framework on 1 internal and 4 public benchmark datasets using both automatic (Perplexity) and human (SSA {--} Sensibleness and Specificity Average) evaluation metrics and establish comparable performance while reducing model parameters by 90{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gerhard-young-etal-2022-low">
<titleInfo>
<title>Low-Resource Adaptation of Open-Domain Generative Chatbots</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greyson</namePart>
<namePart type="family">Gerhard-Young</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raviteja</namePart>
<namePart type="family">Anantha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srinivas</namePart>
<namePart type="family">Chappidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bjorn</namePart>
<namePart type="family">Hoffmeister</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Song</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caixia</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent work building open-domain chatbots has demonstrated that increasing model size improves performance (Adiwardana et al., 2020; Roller et al., 2020). On the other hand, latency and connectivity considerations dictate the move of digital assistants on the device (Verge, 2021). Giving a digital assistant like Siri, Alexa, or Google Assistant the ability to discuss just about anything leads to the need for reducing the chatbot model size such that it fits on the user’s device. We demonstrate that low parameter models can simultaneously retain their general knowledge conversational abilities while improving in a specific domain. Additionally, we propose a generic framework that accounts for variety in question types, tracks reference throughout multi-turn conversations, and removes inconsistent and potentially toxic responses. Our framework seamlessly transitions between chatting and performing transactional tasks, which will ultimately make interactions with digital assistants more human-like. We evaluate our framework on 1 internal and 4 public benchmark datasets using both automatic (Perplexity) and human (SSA – Sensibleness and Specificity Average) evaluation metrics and establish comparable performance while reducing model parameters by 90%.</abstract>
<identifier type="citekey">gerhard-young-etal-2022-low</identifier>
<identifier type="doi">10.18653/v1/2022.dialdoc-1.3</identifier>
<location>
<url>https://aclanthology.org/2022.dialdoc-1.3</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>23</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Low-Resource Adaptation of Open-Domain Generative Chatbots
%A Gerhard-Young, Greyson
%A Anantha, Raviteja
%A Chappidi, Srinivas
%A Hoffmeister, Bjorn
%Y Feng, Song
%Y Wan, Hui
%Y Yuan, Caixia
%Y Yu, Han
%S Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F gerhard-young-etal-2022-low
%X Recent work building open-domain chatbots has demonstrated that increasing model size improves performance (Adiwardana et al., 2020; Roller et al., 2020). On the other hand, latency and connectivity considerations dictate the move of digital assistants on the device (Verge, 2021). Giving a digital assistant like Siri, Alexa, or Google Assistant the ability to discuss just about anything leads to the need for reducing the chatbot model size such that it fits on the user’s device. We demonstrate that low parameter models can simultaneously retain their general knowledge conversational abilities while improving in a specific domain. Additionally, we propose a generic framework that accounts for variety in question types, tracks reference throughout multi-turn conversations, and removes inconsistent and potentially toxic responses. Our framework seamlessly transitions between chatting and performing transactional tasks, which will ultimately make interactions with digital assistants more human-like. We evaluate our framework on 1 internal and 4 public benchmark datasets using both automatic (Perplexity) and human (SSA – Sensibleness and Specificity Average) evaluation metrics and establish comparable performance while reducing model parameters by 90%.
%R 10.18653/v1/2022.dialdoc-1.3
%U https://aclanthology.org/2022.dialdoc-1.3
%U https://doi.org/10.18653/v1/2022.dialdoc-1.3
%P 23-30
Markdown (Informal)
[Low-Resource Adaptation of Open-Domain Generative Chatbots](https://aclanthology.org/2022.dialdoc-1.3) (Gerhard-Young et al., dialdoc 2022)
ACL
- Greyson Gerhard-Young, Raviteja Anantha, Srinivas Chappidi, and Bjorn Hoffmeister. 2022. Low-Resource Adaptation of Open-Domain Generative Chatbots. In Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pages 23–30, Dublin, Ireland. Association for Computational Linguistics.