Papers by Nisansa de Silva

5 papers
Exploiting Node Content for Multiview Graph Convolutional Network and Adversarial Regularization (2020.coling-main)

Copied to clipboard

Challenge: Existing graph autoencoders and its variants have been used for node embedding . a new method is proposed to model consistency across different views of networks .
Approach: They propose a network embedding method which enforces latent representations to be consistent across different views of networks by incorporating a multiview adversarial regularization module.
Outcome: The proposed method compares favorably with the state-of-the-art methods on benchmark datasets and on a real-world application.
Semantic Oppositeness Assisted Deep Contextual Modeling for Automatic Rumor Detection in Social Networks (2021.eacl-main)

Copied to clipboard

Challenge: Social networks face a major challenge in the form of rumors and fake news . rumor detection is suboptimal due to its rapidity and spread of information .
Approach: They propose a semantic oppositeness model that captures elements of discord . they show that it is more resistant to variances introduced by randomness .
Outcome: The proposed model achieves state-of-the-art on rumor detection task with extensive experiments on recent data sets.
Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP World (2022.aacl-main)

Copied to clipboard

Challenge: Linguistic disparity in the NLP world is widely acknowledged, but the reasons behind it are rarely discussed within the field.
Approach: They propose to categorise languages based on speaker population and vitality . they also analyse the distribution of language data resources and amount of NLP/CL research .
Outcome: The proposed model identifies the reasons for the disparity and suggests ways to overcome it.
Improving the Quality of Web-mined Parallel Corpora of Low-Resource Languages using Debiasing Heuristics (2025.emnlp-main)

Copied to clipboard

Challenge: Parallel Data Curation (PDC) techniques aim to filter out noisy parallel sentences from web-mined corpora.
Approach: They propose to rank parallel sentences using similarity scores on sentence embeddings derived from Pre-trained Multilingual Language Models (multiPLMs) . previous research has shown that the choice of multiPLM significantly impacts the quality of the filtered parallel corpus.
Outcome: The proposed methods reduce disparities between multiPLMs while producing better results.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations