Search Results for author:
Found 11 papers, 0 papers with code
Principles for Developing a Knowledge Graph of InterlinkedEvents from News Headlines on Twitter
The ever-growing datasets published on Linked Open Data mainly contain encyclopedic information.
Analyzing and learning the language for different types of harassment
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.
Towards Geocoding Spatial Expressions
Imprecise composite location references formed using ad hoc spatial expressions in English text makes the geocoding task challenging for both inference and evaluation.
Predicting Early Indicators of Cognitive Decline from Verbal Utterances
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.
Discourse over Discourse: The Need for an Expanded Pragmatic Focus in Conversational AI
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.
Long-form analogies generated by chatGPT lack human-like psycholinguistic properties
Psycholinguistic analyses provide a means of evaluating large language model (LLM) output and making systematic comparisons to human-generated text.
Why Do We Need Neuro-symbolic AI to Model Pragmatic Analogies?
A hallmark of intelligence is the ability to use a familiar domain to make inferences about a less familiar domain, known as analogical reasoning.
Evaluating the Deductive Competence of Large Language Models
Moreover, we find that performance interacts with presentation format and content in unexpected ways that differ from human performance.
Expanding the Set of Pragmatic Considerations in Conversational AI
Despite considerable performance improvements, current conversational AI systems often fail to meet user expectations.
Improving Contextual Congruence Across Modalities for Effective Multimodal Marketing using Knowledge-infused Learning
The prevalence of smart devices with the ability to capture moments in multiple modalities has enabled users to experience multimodal information online.
Grounding from an AI and Cognitive Science Lens
Grounding is a challenging problem, requiring a formal definition and different levels of abstraction.
