Alina Lenhardt

Experience

• 

  National Research University — Higher School of Economics

  Feb 2013 - Dec 2013

  Research Assistant

  Development of the first learner corpora for Russian. I was involved in annotation principles elaboration, data collection and annotation, corpus platform design. I organized workshops for new annotators and supervised student research projects. Experiments with error detection, language identification.

• 

  Eberhard Karls Universität Tübingen

  Jan 2015 - Jun 2016

  Research Assistant

  The EVOLAEMP project aims to investigate processes of cultural language evolution. One of the main goals is to build tools, databases and models using methods of computational linguistics, historical linguistics and bioinformatics.I contibuted to data collection for Indo-European languages database (data review, cleanup). Furthermore, I develop a Java-application for the automatic word alignment and conducted experiments on the data.

• 

  DFG Project: Words, Bones, Genes, Tools

  Apr 2016 - Jul 2016

  Research Assistant

  Research on English language change* Data collection, web scraping and parsing (regex, BeautifulSoup, lxml, NLTK, TreeTagger)* Regression modeling, data visualization (R)

• 

  Transline Deutschland

  Aug 2016 - Apr 2018

  Computational Linguist

  * Tool development for automatic error detection in Translation Memories (.tmx)* Optimization of translation quality assurance processes* Design of automatic quality assurance checks* Technical support for terminology management tool (Termflow)

• 

  Nuance Communications

  May 2018 - Sept 2019

  Language Engineer

  * Research on language identification and text normalization for multiple languages: contributions to process optimization and automation, quality assurance of the models. * Designed tools for data collection, cleanup and annotation. * Implemented product pipeline for fine-tuning resources in music domain (new product from existing data). Designed tools for data cleanup, transformation into required format, automated QA and packaging.

• 

  Cerence Inc.

  Oct 2019 - now

  * Research on multilingual TTS* Project lead (10 project members). Resource planning, data analytics, competitive analysis.* Maintenance of CI/CD pipelines * Designing new features for improving language identification accuracy.* Project management: improved multilingual support for 10 languages (3-5 team members). Offered support and knowledge transfer to new project members, optimized toolchains for data processing, created process documentation, performed E2E evaluation of updated product. * Coordinated web-based platform development for QA (refined user requirements, planned project milestones, release testing)

  • Program Manager

    Sept 2023 - now

  • Senior Speech Scientist

    Jan 2022 - Sept 2023

  • Language Engineer

    Oct 2019 - Dec 2021