Aarne I'm a part-time doctoral researcher in Language Technology at University of Helsinki supervised by Jörg Tiedemann. My research focuses on computational semantics and natural language understanding. I'm currently working on my PhD thesis on natural language inference. Since May 2021 I've worked full-time at Huawei as a Speech Recognition Researcher (through Silo AI).

I hold an MSc in Computational Linguistics and Formal Grammar from King's College London (2007) and a BSc in Philosophy from London School fo Economics (2005).

I have over 16 years of industry experience in software development, architecture, management consulting, startup business, AI/ML and NLP development and academic research.

News

  • Our paper "How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets" was accepted to *SEM 2022.
  • Our paper "NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model Performance" was accepted to NoDaLiDa 2021.
  • Our paper "Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations" was accepted to NoDaLiDa 2019.
  • I was a lab monitor at 2019 Lisbon Machine Learning School LxMLS 2019
  • I was a TA for two courses in spring 2019: Machine Learning for Linguists (Bachelor's level) and A Practical Introduction to Modern Neural Machine Translation (Master's level).

Papers

  1. Aarne Talman, Marianna Apidianaki, Stergios Chatzikyriakidis, Jörg Tiedemann. 2022. How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets. Proceedings of The 11th Joint Conference on Lexical and Computational Semantics (*SEM). [bibtex] [pdf] [data and code]
  2. Aarne Talman, Marianna Apidianaki, Stergios Chatzikyriakidis, Jörg Tiedemann. 2021. NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model Performance. Proceedings of NoDaLiDa 2021. [bibtex] [pdf] [data and code]
  3. Aarne Talman, Antti Suni, Hande Celikkanat, Sofoklis Kakouros, Jörg Tiedemann and Martti Vainio. 2019. Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations. Proceedings of NoDaLiDa 2019. [bibtex] [pdf] [data and code]
  4. Aarne Talman, Umut Sulubacak, Raúl Vázquez, Yves Scherrer, Sami Virpioja, Alessandro Raganato, Arvi Hurskainen, and Jörg Tiedemann. 2019. The University of Helsinki submissions to the WMT19 news translation task. Proceedings of the Fourth Conference on Machine Translation: Shared Task Papers. [bibtex] [pdf]
  5. Aarne Talman and Stergios Chatzikyriakidis. 2019. Testing the Generalization Power of Neural Network Models Across NLI Benchmarks. Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. [bibtex] [pdf]
  6. Aarne Talman, Anssi Yli-Jyrä and Jörg Tiedemann. 2019. Sentence Embeddings in NLI with Iterative Refinement Encoders. Natural Language Engineering 25(4). [bibtex] [pdf] [code]

Talks

  1. How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets. 14 July 2022, The 11th Joint Conference on Lexical and Computational Semantics (*SEM 2022).
  2. NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model Performance. 2 June 2021, The 23rd Nordic Conference on Computational Linguistics, Reykjavik. [pdf]
  3. Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations. 14 November 2019, Research Seminar in Language Technology, University of Helsinki. [pdf]
  4. Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations. 2 October 2019, NoDaLiDa 2019, Turku. [pdf]
  5. Neural Network models of NLI fail to capture the general notion of inference, 8 March 2019, CLASP Seminar, University of Gothenburg. [pdf]
  6. State-of-the-Art Natural Language Inference Systems Fail to Capture the Semantics of Inference, 25 October 2018, Research Seminar in Language Technology, University of Helsinki. [pdf]
  7. Natural Language Inference with Hierarchical BiLSTM’s, 28 September 2018, FoTran 2018. [pdf]

Curriculum Vitae

Download the full CV: pdf.

Education

Employment

  • 2022 - present, Lead AI Engineer, Silo AI
  • 2021 - 2022, Senior AI Engineer, Silo AI
  • 2019 - present, Founder, Basement AI Basement AI is a Nordic artificial intelligence research lab specializing in natural language processing and machine learning.
  • 2018 - present, Doctoral Researcher, Language Technology, University of Helsinki
    Working on computational semantics and natural language processing.
    2018-2019 full-time, 2020-present part-time.
  • 2020 - 2021, Global AI/ML Practice Lead and UK CTO, Nordcloud
  • 2015 - 2018, Associate Director, Consulting, Gartner
  • 2012 - 2015, Consultant, Accenture
  • 2011 - 2012, Research Student, London School of Economics
  • 2009 - 2011, Product Manager, Nokia
  • 2008 - 2009, Manager, Nokia
  • 2006 - 2008, Systems Analyst, Tieto
  • 2006 - 2006, Software Developer, Valuatum

Copyright © 2022 Aarne Talman  |  Valid xhtml and css