VLDB 2026 Research / reviewers in the wild / expert
Meghana Moorthy Bhat
dblp:234/8670 · also Meghana Bhat, Meghana Moorthy
· DBLP profile ↗
2ranked-venue papers
1as first author
1since 2021 · last 2021
—ORCID · none
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 2 · 1 first-author · 1 since 2021
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
1 paper |
Transfer learning and domain adaptation · 54% Trustworthy machine learning · 23% Language models and text generation · 23% |
Topics — the 5 heaviest of 5, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Machine learning › Transfer learning and domain adaptation
few-shot learning |
0.5 | 1 | 2021 | Self-training with Few-shot Rationalization · EMNLP (1) 2021 |
Machine learning › Trustworthy machine learning
interpretability |
0.5 | 1 | 2021 | Self-training with Few-shot Rationalization · EMNLP (1) 2021 |
Natural language and speech › Language models and text generation
rationale generation |
0.5 | 1 | 2021 | Self-training with Few-shot Rationalization · EMNLP (1) 2021 |
Machine learning › Transfer learning and domain adaptation › domain adaptation › unsupervised domain adaptation
self-training |
0.5 | 1 | 2021 | Self-training with Few-shot Rationalization · EMNLP (1) 2021 |
Machine learning › Transfer learning and domain adaptation
low-resource learning |
0.1 | 1 | 2021 | Self-training with Few-shot Rationalization · EMNLP (1) 2021 |
Methods — techniques the papers use, named apart from their topics
self-training · 0.5sample selection · 0.5multi-task teacher-student · 0.5
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2021 | Self-training with Few-shot RationalizationabstractWhile pre-trained language models have obtained state-of-the-art performance for several natural language understanding tasks, they are quite opaque in terms of their decision-making process.While some recent works focus on rationalizing neural predictions by highlighting salient concepts in text as justifications or rationales, they rely on thousands of labeled training examples for both task labels as well as annotated rationales for every instance.Such extensive large-scale annotations are infeasible to obtain for many tasks.To this end, we develop a multi-task teacher-student framework based on self-training language models with limited task-specific labels and rationales, and judicious sample selection to learn from informative pseudo-labeled examples 1 .We study several characteristics of what constitutes a good rationale and demonstrate that the neural model performance can be significantly improved by making it aware of its rationalized predictions particularly in low-resource settings.Extensive experiments in several benchmark datasets demonstrate the effectiveness of our approach. Meghana Moorthy Bhat, Alessandro Sordoni, Subhabrata Mukherjee |
EMNLP (1) | 1 |
| 2019 | Fake News Detection via NLP is Vulnerable to Adversarial AttacksabstractNews plays a significant role in shaping people's beliefs and opinions. Fake news has always been a problem, which wasn't exposed to the mass public until the past election cycle for the 45th President of the United States. While quite a few detection methods have been proposed to combat fake news since 2015, they focus mainly on linguistic aspects of an article without any fact checking. In this paper, we argue that these models have the potential to misclassify fact-tampering fake news as well as under-written real news. Through experiments on Fakebox, a state-of-the-art fake news detector, we show that fact tampering attacks can be effective. To address these weaknesses, we argue that fact checking should be adopted in conjunction with linguistic characteristics analysis, so as to truly separate fake news from real news. A crowdsourced knowledge graph is proposed as a straw man solution to collecting timely facts about news events. Zhixuan Zhou, Huankang Guan, Meghana Moorthy Bhat, Justin Hsu |
ICAART (2) | 3 |