TY - GEN
T1 - Like a baby
T2 - 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019
AU - Ororbia, Alexander G.
AU - Mali, Ankur
AU - Kelly, Matthew A.
AU - Reitter, David
N1 - Publisher Copyright:
© 2019 Association for Computational Linguistics
PY - 2020
Y1 - 2020
N2 - We examine the benefits of visual context in training neural language models to perform next-word prediction. A multi-modal neural architecture is introduced that outperform its equivalent trained on language alone with a 2% decrease in perplexity, even when no visual context is available at test. Fine-tuning the embeddings of a pre-trained state-of-the-art bidirectional language model (BERT) in the language modeling framework yields a 3.5% improvement. The advantage for training with visual context when testing without is robust across different languages (English, German and Spanish) and different models (GRU, LSTM, ?-RNN, as well as those that use BERT embeddings). Thus, language models perform better when they learn like a baby, i.e, in a multi-modal environment. This finding is compatible with the theory of situated cognition: language is inseparable from its physical context.
AB - We examine the benefits of visual context in training neural language models to perform next-word prediction. A multi-modal neural architecture is introduced that outperform its equivalent trained on language alone with a 2% decrease in perplexity, even when no visual context is available at test. Fine-tuning the embeddings of a pre-trained state-of-the-art bidirectional language model (BERT) in the language modeling framework yields a 3.5% improvement. The advantage for training with visual context when testing without is robust across different languages (English, German and Spanish) and different models (GRU, LSTM, ?-RNN, as well as those that use BERT embeddings). Thus, language models perform better when they learn like a baby, i.e, in a multi-modal environment. This finding is compatible with the theory of situated cognition: language is inseparable from its physical context.
UR - http://www.scopus.com/inward/record.url?scp=85084045832&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084045832&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85084045832
T3 - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
SP - 5127
EP - 5136
BT - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
Y2 - 28 July 2019 through 2 August 2019
ER -