---
title: "Regina Barzilay — papers, page 2 — Elamur Research"
description: "Regina Barzilay, MIT Computer Science and Artificial Intelligence Laboratory: 30 papers on Elamur Research (1997–2021), h-index 91…"
canonical: "https://research.elamur.ai/free/en/authors/regina-barzilay/page/2/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/regina-barzilay/page/2/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Regina Barzilay](https://md.research.elamur.ai/free/en/authors/regina-barzilay/) / page 2

# Regina Barzilay · page 2

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

[The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/regina-barzilay/)

## Papers

The most cited first (OpenAlex and our library).

[← prev](https://md.research.elamur.ai/free/en/authors/regina-barzilay/) [1](https://md.research.elamur.ai/free/en/authors/regina-barzilay/) **2**

26. **[Representation Learning for Grounded Spatial Reasoning](https://md.research.elamur.ai/free/en/papers/janner-2018-representation-learning-grounded-spatial-reasoning/)** *(2018 · 70 citations)* Spatial expressions in instructions only make sense relative to a particular environment, so a system must reason over language and map layout together.
27. **[Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment](https://md.research.elamur.ai/free/en/papers/belinkov-2014-exploring-compositional-architectures-word-vector/)** *(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…
28. **[Neural Decipherment via Minimum-Cost Flow: From Ugaritic to Linear B](https://md.research.elamur.ai/free/en/papers/luo-2019-neural-decipherment-minimum-cost-flow/)** *(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.
29. **[Unsupervised Morphology Rivals Supervised Morphology for Arabic MT](https://md.research.elamur.ai/free/en/papers/stallard-2012-unsupervised-morphology-rivals-supervised-morphology/)** *(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…
30. **[Deciphering Undersegmented Ancient Scripts Using Phonetic Prior](https://md.research.elamur.ai/free/en/papers/luo-2021-deciphering-undersegmented-ancient-scripts-phonetic/)** *(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.

[← prev](https://md.research.elamur.ai/free/en/authors/regina-barzilay/) [1](https://md.research.elamur.ai/free/en/authors/regina-barzilay/) **2**