Regina Barzilay · page 2

29 papers in our library · 1997–2021 · page 2 of 2

Papers

The most cited first (OpenAlex and our library).

Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment (2014 · 45 citations)
PP attachment chooses which candidate head a prepositional phrase depends on. The paper scores each candidate by composing the word vectors of the head, the preposition and the child in a small neural network, trained on attachment decisions. The English data are the Penn Treebank converted to dependencies (sections…
Neural Decipherment via Minimum-Cost Flow: From Ugaritic to Linear B (2019 · 44 citations)
The paper deciphers a lost language without parallel text: the words of the lost language are aligned with cognates in a known, related language.
Unsupervised Morphology Rivals Supervised Morphology for Arabic MT (2012 · 30 citations)
The question is whether an unsupervised Arabic segmenter (the Lee et al. Bayesian model) can match supervised segmenters such as MADA and Sakhr when it feeds a hierarchical string-to-tree MT system. The authors add maximum marginal decoding (MM) over 25 Gibbs-sampling runs. Sampling alone changes 13% of token…
Deciphering Undersegmented Ancient Scripts Using Phonetic Prior (2021 · 29 citations)
The paper asks how to match an unsegmented or undersegmented script against the vocabulary of a known language when the language family of the lost script is not known.