Mark Johnson · page 2

28 papers in our library · 1998–2024 · page 2 of 2

Papers

The most cited first (OpenAlex and our library).

A joint model of word segmentation and phonological variation for English word-final /t/-deletion (2013 · 13 citations)
Most unsupervised word segmentation models assume every occurrence of a word is pronounced identically. Real speech does not behave this way. The authors target one well-studied case of variation: English word-final /t/-deletion, as when "west" is spoken as [wEs]. They extend the Bayesian Unigram and Bigram…
A Language-agnostic Model of Child Language Acquisition (2024 · 3 citations)
The authors port Abend et al.'s semantic-bootstrapping learner from English to Hebrew. The learner sees one child-directed utterance at a time, paired with a logical form, and learns a CCG lexicon with EM over Dirichlet-process counts. The Hebrew data are from the CHILDES Hagar corpus (3,295 utterances), converted…
Why is English so easy to segment? (2013 · 3 citations)
Unsupervised word segmentation systems do much better on English than on other languages. This paper asks whether that gap comes from models being tuned to English or from real properties of the languages. The authors compare English and Japanese, using both child-directed and adult-directed phonemic corpora. They…