Looking for a job

Archana S Krishnan

@archanaskrishnan

Message

I build high-quality Malayalam language data for NLP and machine translation.

India

Message

What I'm looking for

I'm looking to contribute rigorous linguistic judgment and language-data quality expertise to NLP, machine translation, corpus annotation, language engineering, or NLP evaluation work, especially for Malayalam and other low-resource languages.

At ICFOSS, I contribute to the Government of India’s Bhashini DL-DiscoMT project, building and validating Malayalam language data for NLP and machine translation.

I’ve developed annotation guidelines for POS, chunk, NER, and dependency parsing, and I review junior annotators’ work for consistency. I also created a morph-level Malayalam verb tagset and support research on Malayalam verb classification.

Previously, I validated parallel corpora, annotated discourse, anaphora, semantic roles, and syntax, and developed PDTB-based benchmark datasets for discourse-aware machine translation. My work includes validating multilingual glossaries across six domains and Malayalam dialect speech-and-text data.

I’m a published researcher in Malayalam-to-English machine translation with an MA in Linguistics, UGC NET, and GATE qualifications. Alongside language-data work, I train spoken-English learners and provide academic writing feedback.

Experience

Work history, roles, and key accomplishments

Current

Freelance Spoken English Trainer

Current

Speakeazy English Academy

May 2026 - Present (4 months)

Delivered live online spoken-English coaching focusing on fluency, pronunciation, and conversational confidence.

Spoken English Coaching Online Teaching Fluency Pronunciation

Current

Research Assistant

Current

International Centre for Free and Open Source Software (ICFO

Apr 2026 - Present (5 months)

Authored annotation guidelines for POS, Chunk, NER, and Dependency Parsing; developed a Morph-Level Malayalam Verb Tagset; reviewed and validated annotation output; mentored interns and delivered training.

NER Annotations LaTeX Ubuntu Mentor

Junior Language Editor

International Centre for Free and Open Source Software (ICFO

Jul 2024 - Apr 2026 (1 year 9 months)

Validated and edited English–Malayalam parallel corpora; performed POS, NER, Chunk, Dependency, anaphora, and discourse tagging; developed benchmark datasets using PDTB framework; validated glossaries across six domains.

NER Semantic Role Labeling WX Notation Glossary Validation Malayalam English

Freelance Language Consultant

Trivium Educations

Jan 2023 - Feb 2026 (3 years 1 month)

Reviewed and edited academic essays for university students, providing linguistic feedback on grammar, structure, and clarity.

Editing Proofreading Grammar Academic Writing Feedback

Language Analyst

International Centre for Free and Open Source Software (ICFO

Jan 2024 - Jul 2024 (6 months)

Developed foundational Malayalam–English language datasets for NLP model training; authored language rules and ran quality assurance checks on datasets.

Datasets Rules Quality Assurance Malayalam English