Sourabh Deoghare

10 papers · 2022–2026 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+3 more ↓

🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Silver 🐣 Hot Topic Early Bird 🗺️ Taxonomy Completionist (15) 🔬 Deep Specialist (10)

💎 Century Club · Bronze ❓ The Questioner 🔥 Unstoppable · Bronze

Venues

EMNLP (6) ACL (1) COLING (1) EACL (1) NAACL (1)

Top co-authors

Pushpak Bhattacharyya (9) Diptesh Kanojia (7) Frédéric Blain (2) Markus Freitag (2) Tharindu Ranasinghe (2) Chrysoula Zerva (2) Constantin Orasan (2) David Ifeoluwa Adelani (1) Nuno M. Guerreiro (1) Matteo Negri (1)

Research topics

Natural Language Processing (10) Applications (10) Machine Learning (6) Application Areas (3) Learning Types · Machine Learning (3) Artificial Intelligence (2) Learning Paradigms (2) Resources & Methods (2) Deep Learning (1) Architectures (1) Learning Types · Deep Learning (1)

Keywords

quality estimation (7) machine translation (6) automatic post-editing (5) neural machine translation (4) multi-task learning (2) low-resource language (2) multilingual model (2) sentence-level prediction (2) word-level prediction (2) constrained decoding (1) translation editing (1) translation quality (1) encoder-decoder model (1) transfer learning (1) automated post-editing (1) punctuation robustness (1) reference-based metrics (1) domain robustness (1) curriculum training (1) language representation (1)

Papers

Assessing and Improving Punctuation Robustness in English-Marathi Machine Translation EACL 2026 Findings of the WMT25 Shared Task on Automated Translation Evaluation Systems: Linguistic Diversity is Challenging and References Still Help EMNLP 2025 Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing NAACL 2025 Refer to the Reference: Reference-focused Synthetic Automatic Post-Editing Data Generation COLING 2025 Findings of the Quality Estimation Shared Task at WMT 2024: Are LLMs Closing the Gap in QE? EMNLP 2024 Together We Can: Multilingual Automatic Post-Editing for Low-Resource Languages EMNLP 2024 A Multi-task Learning Framework for Quality Estimation ACL 2023 Machine Translation Advancements for Low-Resource Indian Languages in WMT23: CFILT-IITB’s Effort for Bridging the Gap EMNLP 2023 Quality Estimation-Assisted Automatic Post-Editing EMNLP 2023 IIT Bombay’s WMT22 Automatic Post-Editing Shared Task Submission EMNLP 2022