Name: Denis Emelin
Type: User
Company: @EdinburghNLP
Bio: PhD candidate at the University of Edinburgh, working on natural language processing (NMT, NLG, NLU). I do other stuff, too.
Twitter: emelin_denis
Location: Edinburgh, Scotland
Blog: https://demelin.github.io
Denis Emelin's Projects
(Partial) Reimplementations of AI papers
A python 3 interface for BabelNet https://babelnet.org/
Beyond the Imitation Game collaborative benchmark for enormous language models
Personal website.
Repository containing the experimental code for the publication 'Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks' (Emelin, Denis, Ivan Titov, and Rico Sennrich, EMNLP 2020).
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Selected submissions written for hackerrank.com, mostly for AI and ML exercises.
Information density reduction using generative adversarial networks
Toy exercises completed purely for fun as part of exploring and learning pyTorch.
Cleaned up code from deep reinforcement learning tutorials, replicated for personal practice.
Data and code for the "Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences" (Emelin et al., 2021) paper.
NEMATODE is a light-weight neural machine translation toolkit built around the transformer model. Implemented in TensorFlow.
Open-Source Neural Machine Translation in Theano
Materials for the second assignment of INFR 11157.
Re-implementation of the Noise Contrastive Estimation algorithm for pyTorch, following "Noise-contrastive estimation: A new estimation principle for unnormalized statistical models." (Gutmann and Hyvarinen, AISTATS 2010)
Re-implementation of the Shortcut Transformer in fairseq and the accompanying experimental code.
Re-implementation of Mueller's et al., "Siamese Recurrent Architectures for Learning Sentence Similarity." (AAAI, 2016)
🎓 Easily create a beautiful academic résumé or educational website using Hugo, GitHub, and Netlify
Codebase accompanying the paper 'Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts', (Emelin, Denis, Ivan Titov, and Rico Sennrich, Fourth Conference on Machine Translation, Florence, 2019.)
Supplementary materials for the paper "Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution" (Emelin et al., 2021)