Papers › NTUA-SLP at SemEval-2018 Task 2: Predicting Emojis using RNNs with Context-aware Attention

NTUA-SLP at SemEval-2018 Task 2: Predicting Emojis using RNNs with Context-aware Attention

18 Apr 2018SEMEVAL 2018 6arXiv:1804.06657archive 2025-07-28

Christos Baziotis, Nikos Athanasiou, Georgios Paraskevopoulos, Nikolaos Ellinas, Athanasia Kolovou, Alexandros Potamianos

In this paper we present a deep-learning model that competed at SemEval-2018 Task 2 "Multilingual Emoji Prediction". We participated in subtask A, in which we are called to predict the most likely associated emoji in English tweets. The proposed architecture relies on a Long Short-Term Memory network, augmented with an attention mechanism, that conditions the weight of each word, on a "context vector" which is taken as the aggregation of a tweet's meaning. Moreover, we initialize the embedding layer of our model, with word2vec word embeddings, pretrained on a dataset of 550 million English tweets. Finally, our model does not rely on hand-crafted features or lexicons and is trained end-to-end with back-propagation. We ranked 2nd out of 48 teams.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

alexandra-chron/ntua-slp-semeval2018 mentioned on GitHubpytorch report
cbaziotis/ntua-slp-semeval2018 mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Task 2Word Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections