Papers by Kaushal Maurya

4 papers
DivHSK: Diverse Headline Generation using Self-Attention based Keyword Selection (2023.findings-acl)

Copied to clipboard

Challenge: Diverse headline generation is an NLP task where the goal is to generate multiple headlines that are true to the content of the article but are different among themselves.
Approach: They propose a novel model that generates multiple diverse headlines by using a pre-trained encoder and a cluster-specific keyword set.
Outcome: The proposed model outperforms existing literature and their strong baselines and emerges as a state-of-the-art model.
CharSpan: Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages (2024.eacl-short)

Copied to clipboard

Challenge: Existing models for ELRLs lack parallel corpora and monolingual corporata . authors propose novel character-span noise argumentation model to facilitate cross-lingual transfer .
Approach: They propose a character-span noise argumentation model to facilitate cross-lingual transfer . they use character-size noise argumentations to regularize training data of HRL .
Outcome: The proposed model outperforms baselines on closely related HRL-ELRL pairs from three different language families.
SelectNoise: Unsupervised Noise Injection to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages (2023.findings-emnlp)

Copied to clipboard

Challenge: Currently, MT systems for low-resource languages lack parallel data and monolingual data.
Approach: They propose an unsupervised approach to generate noisy HRLs training data by selective candidate extraction and noise injection.
Outcome: The proposed model outperforms strong baselines on 12 ELRLs in a zero-shot setting .
Meta-XNLG: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation (2022.findings-acl)

Copied to clipboard

Challenge: Existing approaches to learn shareable structures from low-resource languages are limited in the zero-shot setting.
Approach: They propose a meta-learning framework to learn shareable structures from typologically diverse languages based on meta- learning and language clustering.
Outcome: The proposed framework is able to learn shareable structures from typologically diverse languages with limited annotated data.

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