DE eng

Search in the Catalogues and Directories

Hits 1 – 7 of 7

1
Value-aware Approximate Attention ...
BASE
Show details
2
Memory-efficient Transformers via Top-k Attention ...
BASE
Show details
3
Achieving Model Robustness through Discrete Adversarial Training ...
BASE
Show details
4
COVR: A Test-Bed for Visually Grounded Compositional Generalization with Real Images ...
Abstract: Anthology paper link: https://aclanthology.org/2021.emnlp-main.774/ Abstract: While interest in models that generalize at test time to new compositions has risen in recent years, benchmarks in the visually-grounded domain have thus far been restricted to synthetic images. In this work, we propose COVR, a new test-bed for visually-grounded compositional generalization with real images. To create COVR, we use real images annotated with scene graphs, and propose an almost fully automatic procedure for generating question-answer pairs along with a set of context images. COVR focuses on questions that require complex reasoning, including higher-order operations such as quantification and aggregation. Due to the automatic generation process, COVR facilitates the creation of compositional splits, where models at test time need to generalize to new concepts and compositions in a zero- or few-shot setting. We construct compositional splits using COVR and demonstrate a myriad of cases where state-of-the-art ...
Keyword: Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing; Text Generation
URL: https://dx.doi.org/10.48448/ccz0-bc51
https://underline.io/lecture/37494-covr-a-test-bed-for-visually-grounded-compositional-generalization-with-real-images
BASE
Hide details
5
Transformer Feed-Forward Layers Are Key-Value Memories ...
BASE
Show details
6
What's in Your Head? Emergent Behaviour in Multi-Task Transformer Models ...
BASE
Show details
7
Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization ...
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
7
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern