TY - GEN
T1 - Empowering AAC Users
T2 - 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual, CustomNLP4U 2024
AU - Pal, Sayantan
AU - Das, Souvik
AU - Srihari, Rohini K.
AU - Higginbotham, Jeffery
AU - Bizovi, Jenna
N1 - Publisher Copyright:
©2024 Association for Computational Linguistics.
PY - 2024
Y1 - 2024
N2 - Communication barriers have long posed challenges for users of Alternate and Augmentative Communication (AAC). In AAC, effective conversational aids are not solely about harnessing Artificial Intelligence (AI) capabilities but more about ensuring these technologies resonate deeply with AAC user's unique communication challenges. We aim to bridge the gap between generic outputs and genuine human interactions by integrating advanced Conversational AI with personal narratives. While existing solutions offer generic responses, a considerable gap in tailoring outputs reflecting an AAC user's intent must be addressed. Thus, we propose to create a custom conversational dataset centered on the experiences and words of a primary AAC user to fine-tune advanced language models. Additionally, we employ a Retrieval-Augmented Generation (RAG) method, drawing context from a summarized version of authored content by the AAC user. This combination ensures that responses are contextually relevant and deeply personal. Preliminary evaluations underscore its transformative potential, with automated metrics and human assessments showcasing significantly enhanced response quality.
AB - Communication barriers have long posed challenges for users of Alternate and Augmentative Communication (AAC). In AAC, effective conversational aids are not solely about harnessing Artificial Intelligence (AI) capabilities but more about ensuring these technologies resonate deeply with AAC user's unique communication challenges. We aim to bridge the gap between generic outputs and genuine human interactions by integrating advanced Conversational AI with personal narratives. While existing solutions offer generic responses, a considerable gap in tailoring outputs reflecting an AAC user's intent must be addressed. Thus, we propose to create a custom conversational dataset centered on the experiences and words of a primary AAC user to fine-tune advanced language models. Additionally, we employ a Retrieval-Augmented Generation (RAG) method, drawing context from a summarized version of authored content by the AAC user. This combination ensures that responses are contextually relevant and deeply personal. Preliminary evaluations underscore its transformative potential, with automated metrics and human assessments showcasing significantly enhanced response quality.
UR - https://www.scopus.com/pages/publications/85214749925
M3 - Conference contribution
AN - SCOPUS:85214749925
T3 - 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual, CustomNLP4U 2024 - Proceedings of the Workshop
SP - 12
EP - 25
BT - 1st Workshop on Customizable NLP
A2 - Kumar, Sachin
A2 - Balachandran, Vidhisha
A2 - Park, Chan Young
A2 - Shi, Weijia
A2 - Hayati, Shirley Anugrah
A2 - Tsvetkov, Yulia
A2 - Smith, Noah A.
A2 - Hajishirzi, Hannaneh
A2 - Kang, Dongyeop
A2 - Jurgens, David
PB - Association for Computational Linguistics (ACL)
Y2 - 16 November 2024
ER -