Hi! I’m a Researcher at the Data-knowledge Integration Research Team, Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology (AIST). My field of study is natural language processing and, in particular, machine translation (MT). The topic of my thesis was MT system combination, but apart from that, I’ve also done work on neural MT and multi-word expressions in MT.
In my spare time, I ride bicycles, swim, run, take photos, and do small software and hardware hacking projects. I also like technology and gadgets, rock music, Yu-Gi-Oh trading cards, anime and traveling.
On this website, I maintain a set of my favorite photos that I have taken over the years. Once or twice per year, some get added and others get removed. A wider range of my photos can be found in Keda.
Education:
- Doctor of Computer Science, University of Latvia, 2019
- Master of Computer Science, University of Latvia, 2014
- Bachelor of Computer Science, University of Latvia, 2012
Research Interests:
- Natural Language Processing, Computational Linguistics
- Machine Translation, Neural MT, Document-level MT
- Machine Learning, Neural Networks, Sequence-to-Sequence Models
Publications:
- 2024
- M. Rikters, M. Miwa “Entity-aware Multi-task Training Helps Rare Word Machine Translation.” INLG 24
- M. Rikters, S. Reinsone. “Strategic Insights in Human and Large Language Model Tactics at Word Guessing Games.” Wordplay 2024
- M. Rikters, T. Nakazawa. “Revisiting context choices for context-aware machine translation.” LREC-COLING 2024
- M. Rikters, E. Marrese-Taylor, R. Vīksna. “Annotations for Exploring Food Tweets From Multiple Aspects.” LREC-COLING 2024
- M. G. Sohrab, M. Asada, M. Rikters, M. Miwa “Non-autoregressive Pre-trained Sequence-to-Sequence Modeling with BERT-NAR-BERT.” 言語処理学会第30回年次大会
- 2023
- M. G. Sohrab, M. Asada, M. Rikters, M. Miwa “BERT-NAR-BERT: A Non-autoregressive Pre-trained Sequence-to-Sequence Model Leveraging BERT Checkpoints.” IEEE Access
- M. Rikters, M. Miwa “AIST AIRC Submissions to the WMT23 Shared Task.” WMT 23
- M. Rikters, M. Kāle “The Future of Meat: Sentiment Analysis of Food Tweets.” SocialNLP 2023
- M. Kāle, M. Rikters. “Exploring the Sentiment of Latvian Twitter Food Posts in Various Weather Conditions.” DHNB 2023
- M. G. Sohrab, M. Rikters, M. Miwa “Language Understanding with Non-Autoregressive BERT-to-BERT Autoencoder.” 言語処理学会第29回年次大会
- M. Kāle, M. Rikters. “What Food Do We Tweet about on a Rainy Day?” 言語処理学会第29回年次大会
- 2022
- M. Rikters, S. Reinsone. “How Masterly Are People at Playing with Their Vocabulary?” Baltic HLT 2022
- V. Ernštreits, M. Fishel, M. Rikters, M. Tomingas, T. Tuisk. “Language resources and tools for Livonian.” Journal of Estonian and Finno-Ugric Linguistics
- M. Rikters, M. Tomingas, T. Tuisk, V. Ernštreits, M. Fishel. “Machine Translation for Livonian: Catering to 20 Speakers.” ACL 2022
- 2021
- M. Kāle, J. Šķilters, M. Rikters. “Tracing Multisensory Food Experiences on Twitter.” International Journal of Food Design
- M. Kāle, M. Rikters. “Fragmented and Valuable: Following Sentiment Changes in Food Tweets.” Smell, Taste, and Temperature Interfaces CHI 2021 Workshop
- M. Rikters, R. Ri, T. Li, T. Nakazawa. “Japanese-English Conversation Parallel Corpus for Promoting Context-aware Machine Translation Research.” Journal of Natural Language Processing
- M. Rikters, T. Nakazawa. “Revisiting context choices for context-aware machine translation” arXiv preprint
- 中澤敏明, 李凌寒, M. Rikters 「ビジネスシーン対話対訳コーパスの構築と対話翻訳の課題.」言語処理学会第27回年次大会
- 2020
- M. Rikters, R. Ri, T. Nakazawa. “The University of Tokyo’s Submissions to the WAT 2020 Shared Task.” WAT 20
- M. Rikters, R. Ri, T. Li, T. Nakazawa. “Document-aligned Japanese-English Conversation Parallel Corpus.” WMT 20
- R. M. Dominguez, M. Rikters, A. Vasilevskis, M. Pinnis, P. Reichenberg. “Customized Neural Machine Translation Systems for the Swiss Legal Domain.” AMTA 2020.
- U. Sproģis, M. Rikters. “What Can We Learn From Almost a Decade of Food Tweets.” Baltic HLT 2020.
- 2019
- M. Rikters, R. Ri, T. Li, T. Nakazawa. “Designing the Business Conversation Corpus.” WAT 2019
- M. Pinnis, R. Krišlauks, M. Rikters. “Tilde’s Machine Translation Systems for WMT 2019.” WMT 19
- M. Rikters. “Hybrid Machine Translation by Combining Output from Multiple Machine Translation Systems.” Baltic Journal of Modern Computing
- 2018
- M. Rikters, M. Pinnis. “Debugging Translations of Transformer-based Neural Machine Translation Systems.” Baltic Journal of Modern Computing
- M. Pinnis, M. Rikters, R. Krišlauks. “Tilde’s Machine Translation Systems for WMT 2018.” WMT 18
- M. Rikters. “Impact of Corpora Quality on Neural Machine Translation.” Baltic HLT 2018
- M. Rikters, M. Pinnis, R. Rozis. “Advancing Estonian Machine Translation.” Baltic HLT 2018
- M. Rikters. “Debugging Neural Machine Translations.” Baltic DB&IS 2018
- T. Miks, M. Pinnis, M. Rikters, R. Krišlauks. “Effective Online Learning Implementation for Statistical Machine Translation.” Baltic DB&IS 2018
- M. Rikters, M. Pinnis, R. Krišlauks. “Training and Adapting Multilingual NMT for Less-resourced and Morphologically Rich Languages.” LREC 2018
- 2017
- M. Rikters, M. Fishel, O. Bojar. “Visualizing Neural Machine Translation Attention.” MT Marathon 2017
- M. Rikters, M. Fishel. “Confidence through Attention.” MT Summit 2017
- M. Rikters, O. Bojar. “Paying Attention to Multi-Word Expressions in Neural Machine Translation.” MT Summit 2017
- M. Rikters, C. Amrhein, M. Fishel, M. Del. “C-3MA: Tartu-Riga-Zurich Translation Systems for WMT17.” WMT 17
- 2016
- M. Rikters. “Neural Network Language Models for Candidate Scoring in Hybrid Multi-System Machine Translation.” HyTra 6
- M. Rikters. “Interactive Multi-System Machine Translation with Neural Language Models.” IOS Press Ebook
- M. Rikters. “Searching for the Best Translation Combination Across All Possible Variants.” Baltic HLT 2016
- M. Rikters. “K-translate – interactive multi-system machine translation.” Baltic DB&IS 2016
- M. Rikters, I. Skadiņa. “Combining machine translated sentence chunks from multiple MT systems.” CICLing 2016
- M. Rikters, I. Skadiņa. “Syntax-based Multi-system Machine Translation.” LREC 2016
- 2015
Participation in Projects:
- Neural Network Modelling for Inflected Natural Languages
- PARSEME (PARSing and Multi-word Expressions)
- Large-scale statistical model optimization techniques for innovative technologies for machine translation
Fun Personal Projects:
- TwitĒdiens – analysis of Latvian tweets about eating and food
- NLP Tools – a set of my NLP tools and/or demos with links to the related GitHub repositories
Social Networks: