Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Michael Elhadad

Michael Elhadad

15 paper cards in Mova's library · 1996–2020

Michael Elhadad wrote 15 of the papers Mova reads, in 1996–2020, most of them on Dependency parsing, Semantic role labeling, Part-of-speech tagging; often with Yoav Goldberg, Meni Adler, Yael Dahan Netzer.

OpenAlex · ORCID · h-index 25 · 3695 citations · 137 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: Dependency parsing 2 · Semantic role labeling 2 · Part-of-speech tagging 2 · Treebanks 1 · Machine translation 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. Building a Hebrew Semantic Role Labeling Lexical Resource from Parallel Movie Subtitles (2020)
    The authors build the first Hebrew semantic role resource by projecting English SRL, produced by SEMAFOR, onto aligned Hebrew sentences from OpenSubtitles 2016.
  2. The Hebrew FrameNet Project (2016)
    The authors describe a Hebrew FrameNet built as a semi-automatic translation of English FrameNet 1.5.1. They chose the 200 frames that cover the most frequent English words, and found that English lexical units cover about 66% of their Hebrew corpus of 1.75M sentences. Dictionary translations (about 49K pairs) speed…
  3. Word Segmentation, Unknown-word Resolution, and Morphological Agreement in a Hebrew Parsing System (2013)
    The paper builds a constituency parser for Modern Hebrew on the BerkeleyParser (PCFG with latent annotations) and extends it for a small treebank of 6,220 sentences.
  4. Multi-document multilingual summarization corpus preparation, Part 2: Czech, Hebrew and Spanish (2013)
    This is the second part of the report on the MultiLing 2013 corpus, which covers ten languages; this part covers Czech, Hebrew and Spanish.
  5. Effect of Out Of Vocabulary Terms on Inferring Eligibility Criteria for a Retrospective Study in Hebrew EHR (2013)
    The authors classify Hebrew clinical notes from a paediatric neurology unit (894 visits by 516 patients in 2009, about 226K tokens) as eligible or not for a retrospective epilepsy study.
  6. Joint Hebrew Segmentation and Parsing using a PCFGLA Lattice Parser (2011)
    Hebrew function words are written attached to the next word, so one space-delimited token can have several segmentations, and a pipeline that segments first cannot use the syntax to choose.
  7. Easy-First Dependency Parsing of Modern Hebrew (2010)
    The authors apply their easy-first, non-directional dependency parser to the Hebrew dependency treebank, a small treebank of a language with rich morphology and free word order.
  8. Hebrew Dependency Parsing: Initial Results (2009)
    The authors derive a Hebrew dependency treebank (DepTB) from version 2 of the Hebrew constituency treebank.
  9. Tagging a Hebrew Corpus: the Case of Participles (2008)
    The authors build a part-of-speech and morphology corpus of Modern Hebrew news (about 40M tokens, with a 200K-token sample tagged by hand).
  10. SVM Model Tampering and Anchored Learning: A Case Study in Hebrew NP Chunking (2007)
    The paper studies an SVM chunker for Hebrew Simple NPs (about 4,500 training sentences, 500 test, 27K chunks) and opens the trained model in two ways.
  11. An Unsupervised Morpheme-Based HMM for Hebrew Morphological Disambiguation (2006)
    Adler and Elhadad disambiguate Hebrew morphology with an unsupervised HMM. The only resource is a morphological analyser, with no tagged corpus. Because the morphemes of a word cannot be seen, only the words they form, each morpheme slot in the sentence is a lattice node that records its possible predecessors and…
  12. Noun Phrase Chunking in Hebrew: Influence of Lexical and Morphological Features (2006)
    The traditional base-NP definition (non-recursive NPs, as in English) gives tiny, one-word chunks on the Hebrew Treebank, so the authors define "Simple NPs" instead.
  13. Generating Determiners and Quantifiers in Hebrew (1998)
    The paper is one part of HUGG, a Hebrew generation grammar built to share an input specification with the English grammar SURGE.
  14. Generation of Noun Compounds in Hebrew: Can Syntactic Knowledge Be Fully Encapsulated? (1998)
    Hebrew smixut, the marked noun-noun construct (ben ha-melekh, "son of the king", against ben melekh), is very productive and makes up about 40% of noun modifiers in the authors' corpus.
  15. An Overview of SURGE: a Reusable Comprehensive Syntactic Realization Component (1996)
    A short demo paper on SURGE, a syntactic realisation front-end for generators, written in FUF, a functional unification formalism that carries a systemic grammar of English.

Co-authors (12)

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