no code implementations • 19 Feb 2024 • Goonmeet Bajaj, Srinivasan Parthasarathy, Valerie L. Shalin, Amit Sheth
Grounding is a challenging problem, requiring a formal definition and different levels of abstraction.
no code implementations • 6 Feb 2024 • Trilok Padhi, Ugur Kursuncu, Yaman Kumar, Valerie L. Shalin, Lane Peterson Fronczek
The prevalence of smart devices with the ability to capture moments in multiple modalities has enabled users to experience multimodal information online.
no code implementations • 27 Oct 2023 • S. M. Seals, Valerie L. Shalin
Despite considerable performance improvements, current conversational AI systems often fail to meet user expectations.
no code implementations • 11 Sep 2023 • Spencer M. Seals, Valerie L. Shalin
Moreover, we find that performance interacts with presentation format and content in unexpected ways that differ from human performance.
no code implementations • 2 Aug 2023 • Thilini Wijesiriwardene, Amit Sheth, Valerie L. Shalin, Amitava Das
A hallmark of intelligence is the ability to use a familiar domain to make inferences about a less familiar domain, known as analogical reasoning.
no code implementations • 7 Jun 2023 • S. M. Seals, Valerie L. Shalin
Psycholinguistic analyses provide a means of evaluating large language model (LLM) output and making systematic comparisons to human-generated text.
no code implementations • 27 Apr 2023 • S. M. Seals, Valerie L. Shalin
The summarization of conversation, that is, discourse over discourse, elevates pragmatic considerations as a pervasive limitation of both summarization and other applications of contemporary conversational AI.
no code implementations • 19 Nov 2020 • Swati Padhee, Anurag Illendula, Megan Sadler, Valerie L. Shalin, Tanvi Banerjee, Krishnaprasad Thirunarayan, William L. Romine
Our experiments show that a combination of contextual and psycholinguistic features extracted by a Support Vector Machine improved distinguishing the verbal utterances of elderly controls, people with MCI, possible AD, and probable AD.
no code implementations • 12 Jun 2019 • Hussein S. Al-Olimat, Valerie L. Shalin, Krishnaprasad Thirunarayan, Joy Prakash Sain
Imprecise composite location references formed using ad hoc spatial expressions in English text makes the geocoding task challenging for both inference and evaluation.
no code implementations • 1 Nov 2018 • Mohammadreza Rezvan, Saeedeh Shekarpour, Faisal Alshargi, Krishnaprasad Thirunarayan, Valerie L. Shalin, Amit Sheth
In this paper, we introduce the notion of contextual type to harassment involving five categories: (i) sexual, (ii) racial, (iii) appearance-related, (iv) intellectual and (v) political.
no code implementations • 6 Aug 2018 • Saeedeh Shekarpour, Ankita Saxena, Krishnaprasad Thirunarayan, Valerie L. Shalin, Amit Sheth
The ever-growing datasets published on Linked Open Data mainly contain encyclopedic information.