Elamur Research⌕
☰
home / authors / Kenneth W. Church

Kenneth W. Church

Kenneth W. Church appears on this site through three papers, from 1988 to 1993, that brought corpus statistics to core problems of language processing. They address part-of-speech tagging, the measurement of word association for lexicography, and the alignment of sentences in bilingual texts, each with a simple probabilistic model applied to large amounts of text.

The most cited is Word Association Norms, Mutual Information, and Lexicography, written with Patrick Hanks. Instead of collecting associations from human subjects, it proposes the association ratio, a statistic based on mutual information that compares how often one word precedes another within a short window against chance. A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text trains a tagger on the Tagged Brown Corpus and uses a linear-time dynamic programming search to choose the most probable tag sequence for each sentence, motivated by uses such as speech synthesis.

The latest of the three, A Program for Aligning Sentences in Bilingual Corpora, written with William A. Gale, presents align, which pairs sentences with their translations using only their lengths in characters, a step needed for statistical machine translation and bilingual lexicography. Current bylines list Northeastern University, and earlier ones list Baidu, IBM, Johns Hopkins University and the Massachusetts Institute of Technology.

Kenneth W. Church has 3 papers in our library, in 1988–1993, most of them on Machine translation; often with Patrick Hanks, William A. Gale.

3 papers in our library · 1988–1993

current affiliationNortheastern University, Boston, United States; Nscrypt (United States), Orlando, United States; Sciperio (United States), Orlando, United States

OpenAlex · ORCID · h-index 61 · 348 works · 20 403 citations OpenAlex, 2026-10-14

3 works in our library · 1 583 citations in our library · 7 more works in our library · ⭐ Paper Star rank #351

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

Affiliations

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 8 more institutions on single bylines are not listed.

Topics

Machine translation1

Works by year

1990s

19931 paper19901 paper

1980s

19881 paper

Papers

The most cited first (OpenAlex and our library).

  1. Word Association Norms, Mutual Information, and Lexicography (1990 · 4 363 citations)
    Psycholinguists have traditionally gathered word association norms by asking thousands of people to respond to a few hundred stimulus words, as in Palermo and Jenkins (1964).
  2. A Program for Aligning Sentences in Bilingual Corpora (1993 · 1 284 citations)
    Gale and Church tackle sentence alignment: deciding which sentences in a text correspond to which sentences in its translation.
  3. A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text (1988 · 1 178 citations)
    The paper addresses part-of-speech tagging for arbitrary English text. The motivation comes from applications such as speech synthesis, where pronunciation and stress depend on word class, and from making very large corpora more useful to researchers. Church builds a statistical tagger trained on the hand-annotated…

Also in our library

7 more works of theirs are in our library without a page here yet; they will appear as we publish them.

Co-authors here

2 co-authors with a page, the most papers together first.

Cited by

Papers of our library cite their works 1 583 times (of the 140 884 papers whose bibliographies we read); 105 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/kenneth-w-church/