CLASSIC Utterance Boundary: A Chunking‐Based Model of Early Naturalistic Word Segmentation

Cabiddu, Francesco; Bott, Lewis; Jones, G.W.; Gambi, Chiara

doi:10.1111/lang.12559

Cited by 2 publications

(7 citation statements)

References 120 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If bi has been discovered as a frequent unit, {bi}{ci…} becomes more probable; if bici is common relative to bi or ci , then {bici} becomes more probable. This basic mechanism is conceptually similar to the mechanism of some other computational models that have similarly argued that an apparent sensitivity to conditional probability variation could emerge without actual computation of conditional probability per se (Cabiddu et al., 2023; Perruchet & Vinter, 1998; see also Wang, Hutton, & Zevin, 2019). Denying that explicit computation of syllabic transitional probability statistics is necessary for statistical learning leaves open several fundamental questions about the nature of the learning.…”

Section: Discussionsupporting

confidence: 63%

See 1 more Smart Citation

Computational Modeling of the Segmentation of Sentence Stimuli From an Infant Word‐Finding Study

Swingley,

Algayres

2024

Cognitive Science

View full text Add to dashboard Cite

Computational models of infant word‐finding typically operate over transcriptions of infant‐directed speech corpora. It is now possible to test models of word segmentation on speech materials, rather than transcriptions of speech. We propose that such modeling efforts be conducted over the speech of the experimental stimuli used in studies measuring infants' capacity for learning from spoken sentences. Correspondence with infant outcomes in such experiments is an appropriate benchmark for models of infants. We demonstrate such an analysis by applying the DP‐Parser model of Algayres and colleagues to auditory stimuli used in infant psycholinguistic experiments by Pelucchi and colleagues. The DP‐Parser model takes speech as input, and creates multiple overlapping embeddings from each utterance. Prospective words are identified as clusters of similar embedded segments. This allows segmentation of each utterance into possible words, using a dynamic programming method that maximizes the frequency of constituent segments. We show that DP‐Parse mimics American English learners' performance in extracting words from Italian sentences, favoring the segmentation of words with high syllabic transitional probability. This kind of computational analysis over actual stimuli from infant experiments may be helpful in tuning future models to match human performance.

show abstract

Section: Discussionsupporting

confidence: 63%

“…This kind of process would not require explicit computation of transitional probabilities. Models with this property include the text‐based computational models of Perruchet and Vinter (1998) and Cabiddu, Bott, Jones, and Gambi (2023).…”

Section: Introductionmentioning

confidence: 99%

Computational Modeling of the Segmentation of Sentence Stimuli From an Infant Word‐Finding Study

Swingley,

Algayres

2024

Cognitive Science

View full text Add to dashboard Cite

show abstract

“…Sentence context plays a significant role in sense disambiguation (e.g., Sophia [played in / twisted] a band). Children master word ambiguities in naturalistic conversations (Meylan et al, 2021), which raises a question about which sentence properties facilitate child word disambiguation (Cabiddu et al, 2022b;Hahn, Snedeker, & Rabagliati, 2015;Khanna & Boland, 2010;Rabagliati et al, 2013). Children should access cues at different linguistic levels to successfully disambiguate senses.…”

Section: Child Word Sense Disambiguationmentioning

confidence: 99%

“…Here, we examined the plausibility of these models as distributional learners posited by usage-based approaches of language acquisition (e.g., Ambridge, 2020;Bybee, 2010). We focused on child word sense disambiguation (e.g., Cabiddu, Bott, Jones, & Gambi, 2022b;Rabagliati, Pylkkänen, & Marcus, 2013). That is, how children use sense-specific representations (e.g., band = music band, elastic band).…”

Section: Introductionmentioning

confidence: 99%

“…We examined Transformers using datasets from behavioral studies that tested 4-year-old children's abilities to use bottom-up (word associations) and top-down (sentence global plausibility, verb-event structure) cues to sense disambiguation (Cabiddu et al, 2022b;Rabagliati et al, 2013). We tested a large pool of models (N=45) from 14 different families.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparing Children and Large Language Models in Word Sense Disambiguation: Insights and Challenges

Cabiddu¹,

Nikolaus²,

Fourtassi³

2023

Preprint

View full text Add to dashboard Cite

Understanding how children process ambiguous words is a challenge because sense disambiguation depends on sentence context bottom-up and top-down aspects. Here, we seek in- sight into this phenomenon by investigating how such a com- petence might arise in large distributional learners (Transform- ers) that purport to acquire sense representations from lan- guage input in a largely unsupervised fashion. We investigated how sense disambiguation might be achieved using model rep- resentations derived from naturalistic child-directed speech. We tested a large pool of Transformer models, varying in their pretraining input size/nature as well as the size of their param- eter space. Tested across three behavioral experiments from the developmental literature, we found that these models cap- ture some essential properties of child sense disambiguation, although most still struggle in the more challenging tasks with contrastive cues. We discuss implications for both theories of word learning and for using Transformers to capture child lan- guage processing.

show abstract

CLASSIC Utterance Boundary: A Chunking‐Based Model of Early Naturalistic Word Segmentation

Abstract: Cabiddu (he/him) , a Lewis Bott (he/him), a Gary Jones (he/him), b and Chiara Gambi (she/her) a,c

Cited by 2 publications

References 120 publications

Computational Modeling of the Segmentation of Sentence Stimuli From an Infant Word‐Finding Study

Computational Modeling of the Segmentation of Sentence Stimuli From an Infant Word‐Finding Study

Comparing Children and Large Language Models in Word Sense Disambiguation: Insights and Challenges

Contact Info

Product

Resources

About