Enriching Word Vectors with Subword Information

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Continuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. Popular models that learn such representations ignore the morphology of words, by assigning a distinct vector to each word. This is a limitation, especially for languages with large vocabularies and many rare words. In this paper, we propose a new approach based on the skipgram model, where each word is represented as a bag of character n-grams. A vector representation is associated to each character n-gram; words being represented as the sum of these representations. Our method is fast, allowing to train models on large corpora quickly and allows us to compute word representations for words that did not appear in the training data. We evaluate our word representations on nine different languages, both on word similarity and analogy tasks. By comparing to recently proposed morphological word representations, we show that our vectors achieve state-of-the-art performance on these tasks.

Last synced 2026-08-22 14:19 UTC

• PKSF: A Task-Aware Prior Knowledge Selection and Fusion Framework for TextVQA

  Electronics 2026 · 0 citations

• Encoder Language Models for Zero-Shot Recommender Systems: Cross-Domain and Cross-Lingual Evaluation

  Computers 2026 · 0 citations

• Improving automatic essay score classification accuracy with low-resource multilingual languages using data augmentation

  International Journal of Testing 2026 · 0 citations

• Character-Level Feature Engineering for Bangla Sentence Similarity Using Classical Machine Learning

  Engineering Technology & Applied Science Research 2026 · 0 citations

• Benchmarking fastText, word2vec, and BERT on the MAQASID Dataset: A Closed-Domain Religious Resource

  Engineering Technology & Applied Science Research 2026 · 0 citations

• Arabic WordNet Enrichment: A Comprehensive Survey

  ACM Transactions on Asian and Low-Resource Language Information Processing 2026 · 0 citations

• Research Progress on Multimodal Named Entity Recognition with Multi-Task Learning

  電腦學刊 2026 · 0 citations