Aleksandr Drozd
9 papers · 2016–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (4) π Academic Marathon (9) π§ Keyword Pioneer π£ Hot Topic Early Bird
π
Renaissance Researcher
(5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(25)
π₯
Mega-Team
(41)
β
The Questioner
Conferences
EMNLP (3)
NAACL (3)
COLING (2)
ACL (1)
Top co-authors
Keywords
word embedding
(3)
catastrophic forgetting
(1)
text classification
(1)
embedding learning
(1)
natural language inference
(1)
code generation
(1)
ai safety
(1)
model interpretability
(1)
semantic similarity
(1)
convolutional neural network
(1)
recurrent neural network
(1)
language model
(1)
model generalization
(1)
continual pre-training
(1)
frequency analysis
(1)
continual pretraining
(1)
cosine similarity
(1)
multilingual model
(1)
out-of-vocabulary word
(1)
character-level model
(1)
Papers
Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code
COLING 2025
Outlier Dimensions that Disrupt Transformers are Driven by Frequency
EMNLP 2022
Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics
EMNLP 2021
Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP
NAACL 2019
Subword-level Composition Functions for Learning Word Embeddings
NAACL 2018
Subcharacter Information in Japanese Embeddings: When Is It Worth It?
ACL 2018
Investigating Different Syntactic Context Types and Context Representations for Learning Word Embeddings
EMNLP 2017
Word Embeddings, Analogies, and Machine Learning: Beyond king - man + woman = queen
COLING 2016
Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesnβt.
NAACL 2016