Samuel Louvan
I am an applied scientist at Amazon Alexa AI, Cambridge, UK. Before joining Amazon, I earned my PhD from the University of Trento. During my PhD, I was also affiliated with the NLP Research Unit at Fondazione Bruno Kessler (FBK) working with Bernardo Magnini. For my PhD, I worked on transfer learning and data augmentation for low resource Natural Language Understanding tasks for task-oriented dialogue systems. —
Publication
- Bernardo Magnini and Samuel Louvan .Understanding Dialogue for Human Communication. Handbook of Cognitive Mathematics, Springer 2022 (book chapter)
- Rahmad Mahendra, Alham Fikri Aji, Samuel Louvan, Fahrurrozi Rahman, Clara Vania.IndoNLI: A Natural Language Inference Dataset for Indonesian. EMNLP 2021
- Samuel Louvan , Silvia Casola, and Bernardo Magnini.Investigating Continued Pretraining for Zero-Shot Cross-Lingual Spoken Language Understanding. CLiC-it 2021.
- Samuel Louvan and Bernardo Magnini.Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey. COLING 2020
- Samuel Louvan and Bernardo Magnini. How Far Can We Go with Data Selection? A Case Study on Semantic Sequence Tagging Tasks. 1st Workshop on Insights from Negative Results in NLP (collocated with EMNLP 2020)
- Samuel Louvan and Bernardo Magnini. Simple is Better! Lightweight Data Augmentation for Low Resource Slot Filling and Intent Classification. PACLIC 2020.
- Samuel Louvan and Bernardo Magnini. Leveraging Non-Conversational Tasks for Low Resource Slot Filling: Does it help? SIGDIAL 2019 [pdf] [poster]
- Samuel Louvan and Bernardo Magnini. From General to Specific : Leveraging Named Entity Recognition for Slot Filling in Conversational Language Understanding In the Fifth Italian Conference on Computational Linguistics CLic-it 2018 [pdf]
- Kemal Kurniawan and Samuel Louvan. Empirical Evaluation of Character-Based Model on Neural Named-EntityRecognition in Indonesian Conversational Texts. In the 4th Workshop on Noisy User-generated Text (W-NUT) at EMNLP 2018 [pdf]
- Samuel Louvan, Chetan Naik, Sadhana Kumaravel, Heeyoung Kwon, Niranjan Balasubramanian,and Peter Clark. Cross-Sentence Inference for Process Knowledge EMNLP 2016 [pdf] [poster]
Education
- PhD, Computer Science, University of Trento/Fondazione Bruno Kessler (2018-2022)
- MSc in Computer Science, State University of New York (SUNY) at Stony Brook (2013-2016)
- MSc in Computer Science, Technische Universiteit Eindhoven (2007-2009)
- BEng in Informatics Engineering, Institut Teknologi Bandung (2001-2005)
Work Experience
- Applied Scientist, Amazon Alexa AI, Cambridge, UK (August 2021 - now)
- Applied Scientist Intern, Amazon Alexa AI, Boston, US (Sept 2020 - March 2021)
- Part-time Researcher, Kata.ai, Jakarta, (Aug 2017- Dec 2017)
- Junior Lecturer, Universitas Indonesia, (2010 - 2013, 2017)
- Teaching Assistant, Stony Brook University, (Aug 2016 - Dec 2016)
Awards/Services
- Co-chair ACL 2022 Student Research Workshop
- ACL 2019 Student Volunteer
- ACL 2018 Reviewer
- Fondazione Bruno Kessler PhD Scholarship 2018 - 2022
- Search-oriented Conversational AI (SCAI 2018) Travel Grant Award
- LxMLS, Lisbon Machine Learning Summer School Scholarship 2018
- Fulbright Scholarship, 2013 - 2016
- TU/e-Henk Bodt Scholarship, 2007-2009
Personal
- I like to watch, re-watch, and over-analyze badminton matches. My favorite players are Taufik Hidayat and Kevin Sanjaya of Indonesia.
- I like to eat Kentucky Fried Chicken (KFC) and have visited their outlets around the world.