An official website of the United States government
Childhood is marked by the rapid accumulation of knowledge and the prolific production of drawings. We conducted a systematic study of how children create and recognize line drawings of visual concepts. We recruited 2-10-year-olds to draw 48 categories via a kiosk at a children’s museum, resulting in >37K drawings. We analyze changes in the category-diagnostic information in these drawings using vision algorithms and annotations of object parts. We find developmental gains in children’s inclusion of category-diagnostic information that are not reducible to variation in visuomotor control or effort. Moreover, even unrecognizable drawings contain information about the animacy and size of the category children tried to draw. Using guessing games at the same kiosk, we find that children improve across childhood at recognizing each other’s line drawings. This work leverages vision algorithms to characterize developmental changes in children’s drawings and suggests that these changes reflect refinements in children’s internal representations.
more »
« less
What 50 Million Drawings Can Tell Us About Shared Meaning
A foundational assumption of linguistic communication is that conversants have similar underlying concepts (Brennan & Clark, 1996; Wierzbicka, 2012). On this view, the ability of one person to understand another when she says “the tree” depends on the word activating the same concept in both people. One approach to verifying this assumption is to rely on definitions, but this reasoning is circular— how can we be sure the words in our definitions are the same? Here, we investigate the assumption of shared linguistic concepts by studying concepts represented in the visual modality—drawings—and examining predictors of their variability. Specifically, we ask whether people who are geographically closer and inhabit a similar linguistic environment produce more similar drawings.
more »
« less
- Award ID(s):
- 1734260
- PAR ID:
- 10074364
- Date Published:
- Journal Name:
- Proceedings of the 12th International Conference on the Evolution of Language (Evolang12)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
How do children’s representations of object categories change as they grow older? As they learn about the world around them, they also express what they know in the drawings they make. Here, we examine drawings as a window into how children represent familiar object categories, and how this changes across childhood. We asked children (age 3-10 years) to draw familiar object categories on an iPad. First, we analyzed their semantic content, finding large and consistent gains in how well children could produce drawings that are recognizable to adults. Second, we quantified their perceptual similarity to adult drawings using a pre-trained deep convolutional neural network, allowing us to visualize the representational layout of object categories across age groups using a common feature basis. We found that the organization of object categories in older children’s drawings were more similar to that of adults than younger children’s drawings. This correspondence was strong in the final layers of the neural network, showing that older children’s drawings tend to capture the perceptual features critical for adult recognition. We hypothesize that this improvement reflects increasing convergence between children’s representations of object categories and that of adults; future work will examine how these age-related changes relate to children’s developing perceptual and motor capacities. Broadly, these findings point to drawing as a rich source of insight into how children represent object concepts.more » « less
-
The success of a design is not determined solely by its technical aspects. A design must work for the people who will be using it and in the context in which it will be used. Human-centered design approaches suggest strategies to remind engineering designers of the people impacted by their design decisions. While many of these strategies can be used within and across multiple design phases, during the act of sketching concepts during concept generation, there are few explicit strategies for centering people. We investigate possible impact from a simple intervention during a concept generation task through a between-subjects experiment. Working alone is a single design session, half of a group of mechanical engineering students were asked to explicitly “represent people” within their conceptual sketches. Afterwards, all students reviewed each of their concepts to answer, “Who is this idea for? Who do you imagine would use it?” Those who received the intervention requiring representation of people within concept sketches produced significantly longer reflections with greater depth compared to the control group. Adding drawings of people to sketches resulted in more consideration of the social and physical context of use and of the user's personal preferences and values. Depicting people in generated concepts substantially reduced claims a design is "for everyone,” suggesting explicit representation of potential users produced more thoughtful consideration of diversity among potential users.more » « less
-
Abstract BackgroundBiomedical ontologies are representations of biomedical knowledge that provide terms with precisely defined meanings. They play a vital role in facilitating biomedical research in a cross-disciplinary manner. Quality issues of biomedical ontologies will hinder their effective usage. One such quality issue is missing concepts. In this study, we introduce a logical definition-based approach to identify potential missing concepts in SNOMED CT. A unique contribution of our approach is that it is capable of obtaining both logical definitions and fully specified names for potential missing concepts. MethodThe logical definitions of unrelated pairs of fully defined concepts in non-lattice subgraphs that indicate quality issues are intersected to generate the logical definitions of potential missing concepts. A text summarization model (called PEGASUS) is fine-tuned to predict the fully specified names of the potential missing concepts from their generated logical definitions. Furthermore, the identified potential missing concepts are validated using external resources including the Unified Medical Language System (UMLS), biomedical literature in PubMed, and a newer version of SNOMED CT. ResultsFrom the March 2021 US Edition of SNOMED CT, we obtained a total of 30,313 unique logical definitions for potential missing concepts through the intersecting process. We fine-tuned a PEGASUS summarization model with 289,169 training instances and tested it on 36,146 instances. The model achieved 72.83 of ROUGE-1, 51.06 of ROUGE-2, and 71.76 of ROUGE-L on the test dataset. The model correctly predicted 11,549 out of 36,146 fully specified names in the test dataset. Applying the fine-tuned model on the 30,313 unique logical definitions, 23,031 total potential missing concepts were identified. Out of these, a total of 2,312 (10.04%) were automatically validated by either of the three resources. ConclusionsThe results showed that our logical definition-based approach for identification of potential missing concepts in SNOMED CT is encouraging. Nevertheless, there is still room for improving the performance of naming concepts based on logical definitions.more » « less
-
To what extent do people attribute meanings to “nonsense” words? How general is such attribution of meaning? We used a set of words lacking conventional meanings to elicit drawings of made‐up creatures. Separate groups of participants rated the nonsense words and the drawings on several semantic dimensions, and selected what name best corresponded to each creature. Despite lacking conventional meanings, “nonsense” words elicited a high level of consistency in the produced drawings. Meaning attributions made to nonsense words corresponded with meaning attributions made by separate people to drawings that were inspired by the name. Naïve participants were able to recover the name that inspired the drawing with greater‐than‐chance accuracy. These results suggest that people make liberal and consistent use of non‐arbitrary relationships between forms and meanings.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.12775/3991-1.059
