Naslov
Iterative Recursive Attention Model for Interpretable Sequence Classification

Autori
Tutek, Martin ; Šnajder, Jan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP / Linzen, Tal ; Chrupała, Grzegorz ; Alishahi, Afra - Brisel : Association for Computational Linguistics (ACL), 2018, 249-257

Skup
EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

Mjesto i datum
Bruxelles, Belgija, 01.11.2018

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Obrada prirodnog jezika ; Duboko učenje ; interpretabilnost
(Natural language processing ; Deep learning ; interpretability)

Sažetak
Natural language processing has greatly benefited from the introduction of the attention mechanism. However, standard attention models are of limited interpretability for tasks that involve a series of inference steps. We describe an iterative recursive attention model, which constructs incremental representations of input data through reusing results of previously computed queries. We train our model on sentiment classification datasets and demonstrate its capacity to identify and combine different aspects of the input in an easily interpretable manner, while obtaining performance close to the state of the art

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA