AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Disambiguating Spatial Prepositions Using Deep Convolutional Networks

Kaveh Hassani, Won-Sook Lee

AAAI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use pre-trained universal embeddings instead of corpus-trained embeddings (ablation)all models · PDEP spatial prepositionsaccuracy and F1: 4.85% accuracy, 5.39% F1Improved
use hybrid features instead of other feature sets (ablation)all classifiers · PDEP spatial prepositionsaccuracy and F1Improved
combine linguistic features with universal embeddings (ablation)classifiers · PDEP spatial prepositionsaccuracy and F1Improved
increase context window size beyond 5 (ablation)DNN · PDEP spatial prepositionsF1-scoreHurt
use window size 3 instead of 5 (ablation)DNN · PDEP spatial prepositionsF1-scoreHurt
reduce word vector dimensionality from 300 with PCA to about 100 (ablation)DNN · PDEP spatial prepositionsF1-scoreImproved
use GloVe instead of Word2Vec pre-trained embeddings with classic classifiers (ablation)classic classifiers · PDEP spatial prepositionsaccuracyImproved
use Word2Vec instead of GloVe embeddings with DNN (ablation)DNN · PDEP spatial prepositionsF1-scoreImproved
use deep learning models instead of classic classifiers (ablation)classifiers · PDEP spatial prepositionsaccuracy and F1Improved
use ensemble classifiers instead of other classic classifiers (ablation)classic classifiers · PDEP spatial prepositionsaccuracy and F1Improved
hybrid features with CNN versus Kordjamshidi et al. 2011Hybrid + CNN · PDEP spatial prepositionsaccuracy: 94.21% accuracy, +7.06%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy