Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Seth Kulick

Seth Kulick

9 paper cards in Mova's library · 2006–2022

Seth Kulick wrote 9 of the papers Mova reads, in 2006–2022, most of them on Treebanks, Part-of-speech tagging; often with Beatrice Santorini, Ann Bies, Anthony Kroch.

OpenAlex · ORCID · h-index 15 · 1132 citations · 139 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: Treebanks 4 · Part-of-speech tagging 1

Papers

  1. Penn-Helsinki Parsed Corpus of Early Modern English: First Parsing Results and Analysis (2022)
    The PPCEME is a 1.7-million-word treebank of English from 1500 to 1712. It has a much larger POS set than the Penn Treebank and uses function tags (SBJ, OB1, MAT, THT and others) where the PTB uses tree structure. The authors train a self-attentive constituency parser on eight cross-validation splits, with four kinds…
  2. Parsing Early Modern English for Linguistic Search (2022)
    The question is whether a neural constituency parser is accurate enough for syntactic research on Early Modern English.
  3. The Penn Parsed Corpus of Modern British English: First Parsing Results and Analysis (2014)
    The PPCMBE is a historical treebank of British English from 1700 to 1914. After seven legal files are left out, 94 files with 1,018,736 tokens remain. Its annotation is close to the Penn Treebank but has flatter clauses (no VP level) and different coordination and NP structure. The authors train the Berkeley parser…
  4. Parser Evaluation Using Derivation Trees: A Complement to evalb (2014)
    The standard metric for constituency parsers, evalb, scores matching brackets, so it cannot say which construction went wrong.
  5. Further Developments in Treebank Error Detection Using Derivation Trees (2012)
    Treebank annotators sometimes bracket the same word sequence in different ways. The paper finds these cases automatically. Each tree is cut into small tree-adjoining units, and for each word sequence (a "nucleus") every instance is compared with the others in the same internal context. Instances whose reduced…
  6. Simultaneous Tokenization and Part-Of-Speech Tagging for Arabic without a Morphological Analyzer (2010)
    Kulick tokenizes and tags Arabic in one step, without a full morphological analyzer. He splits the words into closed-class and open-class items. Closed-class words are matched by regular expressions taken from the ATB morphological guidelines. Open-class words are matched by generic affix templates, and a CRF…
  7. Construct State Modification in the Arabic Treebank (2008)
    The Arabic Treebank (ATB) marks a construct-state (iDafa) noun phrase as a NOUN with an NP complement, and the NP can nest.
  8. Diacritic Annotation in the Arabic Treebank and its Impact on Parser Evaluation (2008)
    The Arabic Treebank is released in a vocalized and an unvocalized form of each file, and most parsing work used the unvocalized trees as "real-world" input.
  9. Fully Parsing the Penn Treebank (2006)
    The authors build a two-stage parser that recovers full Penn Treebank trees, including function tags and empty categories, which earlier parsers left out.

Co-authors (9)

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