Nithin Holla — accepted AI-conference papers

2021

Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation

Yingjun Du, Nithin Holla, Xiantong Zhen, Cees Snoek, Ekaterina Shutova

ACL 2021long

A critical challenge faced by supervised word sense disambiguation (WSD) is the lack of large annotated datasets with sufficient coverage of words in their diversity of senses. This inspired recent research on few-shot WSD using meta-learning. While such work has successfully applied meta-learning t…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗

2021

Towards a robust experimental framework and benchmark for lifelong language learning

Aman Hussain, Nithin Holla, Pushkar Mishra, Helen Yannakoudakis, Ekaterina Shutova

NeurIPS 2021poster

In lifelong learning, a model learns different tasks sequentially throughout its lifetime. State-of-the-art deep learning models, however, struggle to generalize in this setting and suffer from catastrophic forgetting of old tasks when learning new ones. While a number of approaches have been develo…

Cited by 10 Source ↗Scholar ↗