paper-with-me

홈 › Papers

Learning word-referent mappings and concepts from raw inputs

2020-03-12 · Wai Keen Vong, Brenden M. Lake

How do children learn correspondences between the language and the world from noisy, ambiguous, naturalistic input? One hypothesis is via cross-situational learning: tracking words and their possible referents across multiple situations allows learners to disambiguate correct word-referent mappings (Yu & Smith, 2007). However, previous models of cross-situational word learning operate on highly simplified representations, side-stepping two important aspects of the actual learning problem. First, how can word-referent mappings be learned from raw inputs such as images? Second, how can these learned mappings generalize to novel instances of a known word? In this paper, we present a neural network model trained from scratch via self-supervision that takes in raw images and words as inputs, and show that it can learn word-referent mappings from fully ambiguous scenes and utterances through cross-situational learning. In addition, the model generalizes to novel word instances, locates referents of words in a scene, and shows a preference for mutual exclusivity.

📄 PDF Abstract BibTeX arXiv:2003.05573

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

From Speed to Car and Back: An Exploratory Study about Associations between Abstract Nouns and Images

2022-09-01 · CLASP 2022 9 · Ludovica Cerini, Eliana Di Palma, Alessandro Lenci

Abstract concepts, notwithstanding their lack of physical referents in real world, are grounded in sensorimotor experience. In fact, images depicting concrete entities may be associated to abstract concepts, both via dir…

Wow! What a Useful Extension! Introducing Non-Referential Concepts to Wordnet

2016-05-01 · LREC 2016 5 · Luis Morgado Da Costa, Francis Bond

In this paper we present the ongoing efforts to expand the depth and breath of the Open Multilingual Wordnet coverage by introducing two new classes of non-referential concepts to wordnet hierarchies: interjections and n…

Do Blind Spots Matter for Word-Referent Mapping? A Computational Study with Infant Egocentric Video

2025-11-13 · Zekai Shi, Zhixi Cai, Kalin Stefanov arxiv

Typically, children start to learn their first words between 6 and 9 months, linking spoken utterances to their visual referents. Without prior knowledge, a word encountered for the first time can be interpreted in count…

Contrastive Learning

Competition in Cross-situational Word Learning: A Computational Study

2020-12-06 · Aida Nematzadeh, Zahra Shekarchi, Thomas L. Griffiths, Suzanne Stevenson

Children learn word meanings by tapping into the commonalities across different situations in which words are used and overcome the high level of uncertainty involved in early word learning experiences. We propose a mode…

Continual Visual and Verbal Learning Through a Child's Egocentric Input

2026-06-03 · Xiaoyang Jiang, Yanlai Yang, Kenneth A. Norman, Brenden Lake 외 arxiv

Children learn the meanings of words from a continuous, temporally structured stream of egocentric experience. Recent work shows that neural networks can also learn word-referent mappings from a child's egocentric video …

Representation Learning