Search Results for author: Ruwan Wickramarachchi

Found 6 papers, 1 papers with code

On the Relationship between Sentence Analogy Identification and Sentence Structure Encoding in Large Language Models

1 code implementation11 Oct 2023 Thilini Wijesiriwardene, Ruwan Wickramarachchi, Aishwarya Naresh Reganti, Vinija Jain, Aman Chadha, Amit Sheth, Amitava Das

Through our analysis, we find that LLMs' ability to identify sentence analogies is positively correlated with their ability to encode syntactic and semantic structures of sentences.

Language Modelling Sentence

A Comprehensive Survey on Rare Event Prediction

no code implementations20 Sep 2023 Chathurangi Shyalika, Ruwan Wickramarachchi, Amit Sheth

This paper comprehensively reviews the current approaches for rare event prediction along four dimensions: rare event data, data processing, algorithmic approaches, and evaluation approaches.

ANALOGICAL -- A Novel Benchmark for Long Text Analogy Evaluation in Large Language Models

no code implementations8 May 2023 Thilini Wijesiriwardene, Ruwan Wickramarachchi, Bimal G. Gajera, Shreeyash Mukul Gowaikar, Chandan Gupta, Aman Chadha, Aishwarya Naresh Reganti, Amit Sheth, Amitava Das

Over the past decade, analogies, in the form of word-level analogies, have played a significant role as an intrinsic measure of evaluating the quality of word embedding methods such as word2vec.

Negation Sentence

Knowledge-based Entity Prediction for Improved Machine Perception in Autonomous Systems

no code implementations30 Mar 2022 Ruwan Wickramarachchi, Cory Henson, Amit Sheth

Knowledge-based entity prediction (KEP) is a novel task that aims to improve machine perception in autonomous systems.

Autonomous Driving

Neuro-symbolic Architectures for Context Understanding

no code implementations9 Mar 2020 Alessandro Oltramari, Jonathan Francis, Cory Henson, Kaixin Ma, Ruwan Wickramarachchi

Computational context understanding refers to an agent's ability to fuse disparate sources of information for decision-making and is, therefore, generally regarded as a prerequisite for sophisticated machine reasoning capabilities, such as in artificial intelligence (AI).

Decision Making

An Evaluation of Knowledge Graph Embeddings for Autonomous Driving Data: Experience and Practice

no code implementations29 Feb 2020 Ruwan Wickramarachchi, Cory Henson, Amit Sheth

With the expectation that neuro-symbolic fusion through KGEs will improve scene understanding, this research explores the generation and evaluation of KGEs for autonomous driving data.

Autonomous Driving Knowledge Graph Embeddings +2

Cannot find the paper you are looking for? You can Submit a new open access paper.