349 citations
- Bilkent UniversityTR13 papers
- Middle East Technical UniversityTR12 papers
- Hacettepe UniversityTR5 papers
- Istanbul Technical UniversityTR5 papers
- Southern Methodist UniversityUS4 papers
- Amasya ÜniversitesiTR1 paper
- Cardiff UniversityGB1 paper
- École de Technologie SupérieureCA1 paper
- Gazi UniversityTR1 paper
- Heidelberg UniversityDE1 paper
- IBM Research - AlmadenUS1 paper
- Indian Institute of Science BangaloreIN1 paper
Showing cs.CLShow all
3 papers · 1 filter
cs.CL2022★ 69 cited
Impact of Tokenization on Language Models: An Analysis for Turkish
Cagri Toraman, Eyup Halit Yilmaz, Furkan Şahinuç +1
Tokenization is an important text preprocessing step to prepare input tokens for deep language models. WordPiece and BPE are de facto methods employed by important models, such as…
cs.CL2018★ 9 cited
Imparting Interpretability to Word Embeddings while Preserving Semantic Structure
Lutfi Kerem Senel, Ihsan Utlu, Furkan Şahinuç +2
As an ubiquitous method in natural language processing, word embeddings are extensively employed to map semantic properties of words into a dense vector representation. They captur…
cs.CL2017★ 65 cited
Semantic Structure and Interpretability of Word Embeddings
Lutfi Kerem Senel, Ihsan Utlu, Veysel Yucesoy +2
Dense word embeddings, which encode semantic meanings of words to low dimensional vector spaces have become very popular in natural language processing (NLP) research due to their…