Papers by Rachit Bansal

4 papers
LM-CORE: Language Models with Contextually Relevant External Knowledge (2022.findings-naacl)

Copied to clipboard

Challenge: Large pre-trained language models can capture factual knowledge in their parameters but storing large amounts of knowledge in the model parameters is sub-optimal given the ever-growing amounts of information and resource requirements.
Approach: They propose a framework that provides explicit access to contextually relevant structured knowledge to the model and train it to use that knowledge.
Outcome: The proposed framework outperforms state-of-the-art knowledge-enhanced language models on knowledge probing tasks and can handle knowledge updates.
How Low is Too Low? A Computational Perspective on Extremely Low-Resource Languages (2021.acl-srw)

Copied to clipboard

Challenge: Sumerian is one of the world’s oldest written languages attested from at least the beginning of the 3rd millennium BC.
Approach: They propose to use interpretLR to train attention-based deep learning models in a low-resource language, Sumerian cuneiform, which includes part-of-speech tagging, named entity recognition, and machine translation.
Outcome: The proposed pipeline outperforms the large language model RoBERTa for POS Tagging and NER.
CoSe-Co: Text Conditioned Generative CommonSense Contextualizer (2022.naacl-main)

Copied to clipboard

Challenge: Pre-trained language models (PTLMs) have been shown to perform well on natural language tasks.
Approach: They propose a commonsense contextualizer conditioned on sentences as input to make it generically usable in tasks involving natural language text.
Outcome: The proposed model improves on existing methods on CSQA, ARC, QASC and OBQA datasets.
Evaluating Explanations: How Much Do Explanations from the Teacher Aid Students? (2022.tacl-1)

Copied to clipboard

Challenge: Existing methods to explain predictions by highlighting salient features are often unstated.
Approach: They propose a framework to quantify the value of explanations via the accuracy gains that they confer on a student model trained to simulate a teacher model.
Outcome: The proposed framework allows principled, automatic, model-agnostic evaluation of attributions.

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