MALeViC: Modeling Adjectives Leveraging Visual Contexts
Description
This work aims at modeling how the meaning of gradable adjectives of size (‘big’, ‘small’) can be learned from visually-grounded contexts. Inspired by cognitive and linguistic evidence showing that the use of these expressions relies on setting a threshold that is dependent on a specific context, we investigate the ability of multi-modal models in assessing whether an object is ‘big’ or ‘small’ in a given visual scene. In contrast with the standard computational approach that simplistically treats gradable adjectives as ‘fixed’ attributes, we pose the problem as relational: to be successful, a model has to consider the full visual context.
Models and visual features used in:
- Pezzelle, S., Fernandez, R. (2019). Is the Red Square Big? MALeViC: Modeling Adjectives Leveraging Visual Contexts. Proceedings of EMNLP-IJCNLP 2019.
- Pezzelle, S., Fernandez, R. (2019). Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size. Proceedings of LANTERN 2019 co-located with EMNLP-IJCNLP 2019.
Files
Files
(43.7 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:1e39842498346fcf1ae4b026d80d10ea
|
5.3 GB | Download |
|
md5:06eee191e87ea42e0b86bc69b47a140c
|
5.9 GB | Download |
|
md5:77a957d02e97024cc39cc0101ddfc93c
|
1.3 GB | Download |
|
md5:d263b14f4adfaa748f865526837f34c9
|
6.6 GB | Download |
|
md5:0cdec36ae080571297898a41ce99abf2
|
6.7 GB | Download |
|
md5:7aba28ee854b4a57645d2189a2c83fc7
|
4.0 GB | Download |
|
md5:d0b820fe4f9a8ea83c5bf5aed6fafd4f
|
662.8 MB | Download |
|
md5:fa6ef758665a914558ae1bbac1a73cad
|
6.6 GB | Download |
|
md5:24cbea517545b78aec6916178deb4642
|
6.6 GB | Download |
Additional details
Related works
- Is documented by
- Preprint: https://arxiv.org/pdf/1908.10285.pdf (URL)