Polyglot: Distributed Word Representations for Multilingual NLP (2013 · 201 citations)
Most NLP systems rely on hand-engineered, language-specific features and are built mainly for English, so porting them to other languages is expensive.
Talk like a Graph: Encoding Graphs for Large Language Models (2023 · 81 citations)
Large language models are increasingly asked to reason about relational data, but no one had systematically studied how to turn a graph into text for a frozen, black-box LLM.

All works

6 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

Polyglot: Distributed Word Representations for Multilingual NLPConference on Computational Natural Language Learning (CoNLL)Rami Al-Rfou', Bryan Perozzi, Steven Skiena2013 · 201 citations
Talk like a Graph: Encoding Graphs for Large Language ModelsarXiv:2310.04560Bahare Fatemi, Jonathan Halcrow, Bryan Perozzi2023 · 81 citations
Understanding Transformer Reasoning Capabilities via Graph Algorithms ↗arXiv:2405.18512 · no summary yetClayton Sanford et al.2024 · 21 citations
Zero-Shot Transfer Learning Within a Heterogeneous Graph Via Knowledge Transfer Networks ↗neural information processing systems · no summary yetMinji Yoon et al.2022 · 5 citations
Graph Generative Model for Benchmarking Graph Neural Networks ↗arXiv (Cornell University) · no summary yetMinji Yoon et al.2022 · 4 citations
Learning Large Graph Property Prediction via Graph Segment Training ↗neural information processing systems · no summary yetKaidi Cao et al.2023 · 2 citations

Co-authors here

2 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 288 times (of the 149,439 papers whose bibliographies we read); 54 citing papers with a page here →.

Updated 2 November 2026