Papers by Tarun Tater
AbsVis – Benchmarking How Humans and Vision-Language Models “See” Abstract Concepts in Images (2025.emnlp-main)
Copied to clipboard
| Challenge: | Abstract concepts like mercy and peace lack clear visual grounding, and therefore challenge humans and models to provide suitable image representations. |
| Approach: | They propose a dataset of 675 images annotated with 14,175 concept–explanation attributions from humans and two Vision-Language Models where each concept is accompanied by a textual explanation. |
| Outcome: | The proposed dataset compares human and VLM attributions in terms of diversity, abstractness, and alignment, and shows that overlapping concepts are most preferred. |
Unveiling the mystery of visual attributes of concrete and abstract concepts: Variability, nearest neighbors, and challenging categories (2024.emnlp-main)
Copied to clipboard
| Challenge: | a recent study examines the visual representation of concrete concepts using images from Bing and YFCC. |
| Approach: | They examine the variability in visual representations by using images of concrete and abstract concepts from Bing and YFCC. |
| Outcome: | The proposed model can distinguish between concrete and abstract concepts using basic visual features, the authors show . their model outperforms other models in the nearest neighbor analysis, but it is more complex and requires more visual features . |
Concreteness vs. Abstractness: A Selectional Preference Perspective (2022.aacl-srw)
Copied to clipboard
| Challenge: | Using a collection of 5,438 nouns and 1,275 verbs, we exploit selectional preferences as a salient characteristic in classifying abstract vs. concrete words. |
| Approach: | They propose to use selectional preferences as a criterion to distinguish between concrete and abstract concepts and words. |
| Outcome: | The proposed method achieves an f1-score of 0.84 for nouns and 0.71 for verbs in classification and Spearman’s correlation of 0.86 for nonoms and 0.59% for verb. |
A Modular Architecture for Unsupervised Sarcasm Generation (D19-1)
Copied to clipboard
| Challenge: | Existing systems for sarcasm generation are elusive due to the fact that both selection of contents and training of sarcasm are based on the same data. |
| Approach: | They propose a framework that takes a literal negative opinion as input and translates it into a sarcastic version. |
| Outcome: | The proposed system outperforms baselines built using known unsupervised statistical and neural machine translation and style transfer techniques. |