RECORD
Representation Learning of Image Schema
Human-Computer Interaction · Submitted 17 Jul 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim With the image schemas representable as vectors, it also becomes possible to have a notion that some image schemas are closer or more similar to each other than to the others because the distance between the vectors is a proxy of the dissimilarity between the corresponding image schemas.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Image schema is a recurrent pattern of reasoning where one entity is mapped into another. Image schema is similar to conceptual metaphor and is also related to metaphoric gesture. Our main goal is to generate metaphoric gestures for an Embodied Conversational Agent. We propose a technique to learn the vector representation of image schemas. As far as we are aware of, this is the first work which addresses that problem. Our technique uses Ravenet et al's algorithm which we use to compute the image schemas from the text input and also BERT and SenseBERT which we use as the base word embedding technique to calculate the final vector representation of the image schema. Our representation learning technique works by clustering: word embedding vectors which belong to the same image schema should be relatively closer to each other, and thus form a cluster. With the image schemas representable as vectors, it also becomes possible to have a notion that some image schemas are closer or more similar to each other than to the others because the distance between the vectors is a proxy of the dissimilarity between the corresponding image schemas. Therefore, after obtaining the vector representation of the image schemas, we calculate the distances between those vectors. Based on these, we create visualizations to illustrate the relative distances between the different image schemas.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Image schema is a recurrent pattern of reasoning where one entity is mapped into another. | background 1.00 | 0.05 | 0.03 | asserted 1.00 |
| s1 | Image schema is similar to conceptual metaphor and is also related to metaphoric gesture. | background 1.00 | 0.07 | 0.02 | asserted 1.00 |
| s2 | Our main goal is to generate metaphoric gestures for an Embodied Conversational Agent. | contribution 0.75 | 0.39 | 0.05 | asserted 0.97 |
| s3 | We propose a technique to learn the vector representation of image schemas. | contribution 0.97 | 0.85 | 0.08 | asserted 0.99 |
| s4 | As far as we are aware of, this is the first work which addresses that problem. | gap 0.81 | 0.32 | 0.04 | asserted 0.95 |
| s5 | Our technique uses Ravenet et al's algorithm which we use to compute the image schemas from the text input and also BERT and SenseBERT which we use as the base word embedding technique to calculate the final vector representation of the image schema. | method 1.00 | 0.70 | 0.03 | asserted 1.00 |
| s6 | Our representation learning technique works by clustering: word embedding vectors which belong to the same image schema should be relatively closer to each other, and thus form a cluster. | method 1.00 | 0.56 | 0.08 | asserted 0.97 |
| s7 | With the image schemas representable as vectors, it also becomes possible to have a notion that some image schemas are closer or more similar to each other than to the others because the distance between the vectors is a proxy of the dissimilarity between the corresponding image schemas. | interpretation 0.82 | 0.40 | 0.13 | hedged possibility 0.60 |
| s8 | Therefore, after obtaining the vector representation of the image schemas, we calculate the distances between those vectors. | method 0.98 | 0.94 | 0.04 | asserted 1.00 |
| s9 | Based on these, we create visualizations to illustrate the relative distances between the different image schemas. | method 0.52 | 0.94 | 0.09 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Image schema is a recurrent pattern of reasoning where one entity is mapped into another. Image schema is similar to conceptual metaphor and is also related to metaphoric gesture. Our main goal is to generate metaphoric gestures for an Embodied Conversational Agent. We propose a technique to learn the vector representation of image schemas. As far as we are aware of, this is the first work which addresses that problem. Our technique uses Ravenet et al's algorithm which we use to compute the image schemas from the text input and also BERT and SenseBERT which we use as the base word embedding technique to calculate the final vector representation of the image schema. Our representation learning technique works by clustering: word embedding vectors which belong to the same image schema should be relatively closer to each other, and thus form a cluster. With the image schemas representable as vectors, it also becomes possible to have a notion that some image schemas are closer or more similar to each other than to the others because the distance between the vectors is a proxy of the dissimilarity between the corresponding image schemas. Therefore, after obtaining the vector representation of the image schemas, we calculate the distances between those vectors. Based on these, we create visualizations to illustrate the relative distances between the different image schemas.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 2 sentences without a confident label
Uses the method or tool of 1 paper
-
We also display the UMAP visualizations [ref] of three cases, namely EMPTY image schema in BERT and euclidean distance (Figure [ref]), RIGHT image schema in SenseBERT and cosine dissimilarity (Figure [ref]), and NEAR image schema in SenseBERT and euclidean distance (Figure [ref]).
UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction · Experiment · 1.00
Cites as background 1 paper
-
For example, when BERT [ref] is being proposed, it is tested on natural language understanding tasks, questions answering tasks, and sentence continuation tasks.
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding · Word Embedding · 0.87
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.