Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Regina Barzilay

Regina Barzilay

7 paper cards in Mova's library · 2001–2021

Regina Barzilay wrote 7 of the papers Mova reads, in 2001–2021, most of them on Machine translation, Akkadian and cuneiform NLP, Treebanks; often with Jiaming Luo, Tao Lei, Yuan Cao.

OpenAlex · ORCID · h-index 93 · 36278 citations · 422 works — openalex, 2026-10-18

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology · ORCID

Topics: Machine translation 4 · Akkadian and cuneiform NLP 1 · Treebanks 1

Ideas Mova took (1)

From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave.

Papers

  1. Deciphering Undersegmented Ancient Scripts Using Phonetic Prior (2021)
    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.
  2. Neural Decipherment via Minimum-Cost Flow: From Ugaritic to Linear B (2019)
    The paper deciphers a lost language without parallel text: the words of the lost language are aligned with cognates in a known, related language.
  3. Style Transfer from Non-Parallel Text by Cross-Alignment (2017)
    The paper transfers style between two corpora that share one content distribution but no sentence pairs. An encoder maps a sentence, together with its style label, to a style-free latent content vector; a style-conditioned decoder renders it back. Training aligns populations rather than pairs: sentences transferred…
  4. Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment (2014)
    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…
  5. Unsupervised Morphology Rivals Supervised Morphology for Arabic MT (2012)
    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…
  6. Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment (2003)
    The paper addresses sentence-level paraphrase, which is harder than word or phrase paraphrase, using comparable news corpora: different sources reporting the same events.
  7. Extracting Paraphrases from a Parallel Corpus (2001)
    The paper extracts paraphrases from several English translations of the same foreign source text, a comparable corpus that differs in wording but not in meaning.

Co-authors (15)

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/regina-barzilay/