Work

A Joint Learning Model of Word Segmentation, Lexical Acquisition, and Phonetic Variability

Year: 2013

Type: conference-paper

Abstract: We present a cognitive model of early lexical acquisition which jointly performs word segmentation and learns an explicit model of phonetic variation.We define the model as a Bayesian noisy channel; we sample segmentations and word forms simultaneously from the posterior, using beam sampling to control the size of the search space.Compared to a pipelined approach in which segmentation is performed first, our model is qualitatively more similar to human learners.On data with variable pronunciations, the pipelined approach learns to treat syllables or morphemes as words.In contrast, our joint model, like infant learners, tends to learn multiword collocations.We also conduct analyses of the phonetic variations that the model learns to accept and its patterns of word recognition errors, and relate these to developmental evidence.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/d13-1005

Authors: Micha Elsner, Sharon Goldwater, Naomi Feldman, Frank Wood

Institutions: The Ohio State University, University of Edinburgh, University of Maryland, College Park, University of Oxford

Language: English

Topic: Language Development and Disorders

Subfield: Developmental and Educational Psychology

Field: Psychology

Domain: Social Sciences

SDG: Quality education

Open Access status: hybrid

Funder: Engineering and Physical Sciences Research Council