Papers by Sourabh Deoghare

4 papers
Together We Can: Multilingual Automatic Post-Editing for Low-Resource Languages (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing studies on multilingual automatic post-editing systems for low-resource Indo-Aryan languages have focused on different models for different language pairs.
Approach: They propose to use a multilingual automatic post-editing system to improve machine translations for low-resource Indo-Aryan languages.
Outcome: The proposed model outperforms English-Hindi and English-Marathi models by 2.5 and 2.39 TER points.
Quality Estimation-Assisted Automatic Post-Editing (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing APE and QE combination strategies have not shown significant performance gains in the field of automatic post-editing (APE).
Approach: They propose to train a model on APE and QE tasks to improve the APE performance by using a multi-task learning methodology that treats both tasks as a 'bargaining game' they also investigate various existing combination strategies and show that their approach achieves state-of-the-art performance for a ‘distant’ language pair, viz., English-Marathi.
Outcome: The proposed model improves on two different language pairs, viz., English-Marathi and English-German.
A Multi-task Learning Framework for Quality Estimation (2023.findings-acl)

Copied to clipboard

Challenge: Conventional approaches to QE involve training separate models at different levels of granularity viz., word-level, sentence-level and document-level .
Approach: They propose to train a single model for sentence-level and word-level QE tasks in a multi-task learning framework and compare them to baseline models.
Outcome: The proposed model improves on the single-pair, multi-patch, and zero-shot settings.
Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing (2025.naacl-short)

Copied to clipboard

Challenge: Existing methods to improve automatic post-editing (APE) systems struggle with over-correction, despite the principle of minimal editing.
Approach: They propose a method that incorporates word-level Quality Estimation (QE) information during the decoding process.
Outcome: The proposed method improves on English-German, English-Hindi, and English-Marathi language pairs, with TER gains of 0.65, 1.86, and 1.44 points, respectively.

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