Maksim Tkachenko's Homepage

Look into my CV (February 2023).

My LinkedIn for general trivia (and photo), it's also more colorful! 🤗

I am a Research Scientist at Rakuten Institute of Technology.

Previously, I was Data Science and Operations Research Advisor at FedEx Express, Research Scientist with Preferred.AI, a research group at School of Computing and Information Systems (Singapore Management University). My research advisor is Hady W. Lauw.

Research interests: text mining, natural language processing, machine learning, information extraction, graphical models, statistics, machine translation

It is always good to air our research to the interested parties, talks (with videos):

Evolution of Language Models: From N-Grams to Transformers @ DataScience SG (Singapore)
Learning User Preferences from Multi-Modal Data:

Avito Data Science Meetup (Moscow, Russia)
Computer Science Club (Saint Petersburg, Russia)

SentiVec: Sentiment-Infused Word Embeddings @ DataScience SG (Singapore)
Searching for the X-Factor: Exploring Corpus Subjectivity for Word Embeddings @ ACL (Melbourne, Australia)

Attaining high standards of reproducibility, I try to publish all the research and project-related prototypes:

Simple-ml, a bunch of online classifiers;
Tree-svm, tree kernels for SVM;
Plrmm, Plackett-Luce Regression Mixture Model;
SentiVec, sentiment-infused word embeddings;
Venom, a focused crawler for the deep web;
CompareLDA, a topic model for document comparison;
Neural Network Lab, a web-based interactive visual development environment for deep learning models;
SnappyBuyer, a platform that allows you to make better and faster decisions when buying electronic products;

Looking for publications? Google Scholar | DBLP (I find it is better at assigning the dates)

"Robust Bidirectional Poly-Matching" (Ween Jiann Lee, Maksim Tkachenko, and Hady W. Lauw), In IEEE TKDE, 2023 (Accepted for Publication)

"Sakura at SemEval-2023 Task 2: Data Augmentation via Translation" (Alberto Poncelas, Maksim Tkachenko, and Ohnmar Htun), Proc. SemEval (ACL), Workshop Paper, 2023 (Accepted for Publication)

"Morphologically-Aware Vocabulary Reduction of Word Embeddings" (Chong Cher Chia, Maksim Tkachenko, and Hady Wirawan Lauw), Proc. IEEE/WIC/ACM WI-IAT, 2022

"Robust BiPoly-Matching for Multi-Granular Entities" (Ween Jiann Lee, Maksim Tkachenko, and Hady W. Lauw), Proc. IEEE ICDM, Short Paper, 2021

"CompareLDA: A Topic Model for Document Comparison" (Maksim Tkachenko and Hady W. Lauw), Proc. AAAI, 2019 / Get paper in PDF

"Comparison Mining from Text" (Maksim Tkachenko), PhD Dissertation, Singapore Management University, 2018 / Get dissertation in PDF

"Searching for the X-Factor: Exploring Corpus Subjectivity for Word Embeddings" (Maksim Tkachenko, Chong Cher Chia, and Hady W. Lauw), Proc. ACL, 2018 / Get paper in PDF

"Comparative Relation Generative Model" (Maksim Tkachenko and Hady W. Lauw), In IEEE TKDE, 2017 / Get paper in PDF

"Plackett-Luce Regression Mixture Model for Heterogeneous Rankings" (Maksim Tkachenko and Hady W. Lauw), Proc. CIKM, 2016 / Get paper in PDF

"A Convolution Kernel Approach to Identifying Comparisons in Text" (Maksim Tkachenko and Hady W. Lauw), Proc. ACL, 2015 / Get paper in PDF

"Generative Modeling of Entity Comparisons in Text" (Maksim Tkachenko and Hady W. Lauw), Proc. CIKM, 2014 / Get paper in PDF

"Introducing Baselines for Russian Named Entity Recognition" (Rinat Gareev, Maksim Tkachenko, Valery D. Solovyev, Andrey Simanovsky, Vladimir Ivanov), Proc. CICLing, 2013

"Named Entity Recognition: Exploring Features" (Maksim Tkachenko and Andrey Simanovsky), Proc. KONVENS, 2012 / Get paper in PDF

"Selecting Features for Domain-Independent Named Entity Recognition" (Maksim Tkachenko and Andrey Simanovsky), Proc. KONVENS, Short Paper, 2012 / Get paper in PDF

"Classifying Wikipedia Entities into Fine-Grained Classes", (Maksim Tkachenko, Alexander Ulanov, Andrey Simanovsky), Proc. ICDE, Workshop Paper, 2011