Abstract
Stress has long been established as a major cue in word segmentation for English infants. We show that enabling a current state-of-the-art Bayesian word segmentation model to take advantage of stress cues noticeably improves its performance. We find that the improvements range from 10 to 4%, depending on both the use of phonotactic cues and, to a lesser extent, the amount of evidence available to the learner. We also find that in particular early on, stress cues are much more useful for our model than phonotactic cues by themselves, consistent with the finding that children do seem to use stress cues before they use phonotactic cues. Finally, we study how the model’s knowledge about stress patterns evolves over time. We not only find that our model correctly acquires the most frequent patterns relatively quickly but also that the Unique Stress Constraint that is at the heart of a previously proposed model does not need to be built in but can be acquired jointly with word segmentation.
Highlights
Among the first tasks a child language learner has to solve is picking out words from the fluent speech that constitutes its linguistic input.1 For English, stress has long been claimed to be a useful cue in infant word segmentation (Jusczyk et al, 1993; Jusczyk et al, 1999b), following the demonstra-tion of its effectiveness in adult speech processing (Cutler et al, 1986)
We find that stress cues add roughly 6% token f-score to a model that does not account for phonotactics and 4% to a model that already incorporates phonotactics
And in line with the finding that stress cues are used by infants before phonotactic cues (Jusczyk et al, 1999a), we observe that phonotactic cues require more input than stress cues to be used efficiently
Summary
Among the first tasks a child language learner has to solve is picking out words from the fluent speech that constitutes its linguistic input. For English, stress has long been claimed to be a useful cue in infant word segmentation (Jusczyk et al, 1993; Jusczyk et al, 1999b), following the demonstra-tion of its effectiveness in adult speech processing (Cutler et al, 1986). A brief summary of the key findings is as follows: English infants treat stressed syllables as cues for the beginnings of words from roughly 7 months of age, suggesting that the role played by stress needs to be acquired, and that this requires antecedent segmentation by nonstress-based means (Thiessen and Saffran, 2007). They exhibit a preference for low-pass filtered stress-initial words from this age, suggesting that it is stress and not other phonetic or phonotactic properties that are treated as a cue for wordbeginnings (Jusczyk et al, 1993). Phontactic cues seem to be used later than stress cues (Jusczyk et al, 1999a) and seem to be outweighed by stress cues (Mattys and Jusczyk, 2000)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Transactions of the Association for Computational Linguistics
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
