A Recurrent Neural Model with Attention for the Recognition of Chinese Implicit Discourse Relations

April 26, 2017 · Entered Twilight · 🏛 Annual Meeting of the Association for Computational Linguistics

"Last commit was 8.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: FarrokhAttentionLayer.py, README.md, acl_poster.pdf, class_dist.py, classify.py, model7301.keras.gz, model7301.map.gz, resources.py, train.py, zh-gw300_intersect.w2v.gz

Authors Samuel Rönnqvist, Niko Schenk, Christian Chiarcos arXiv ID 1704.08092 Category cs.CL: Computation & Language Cross-listed cs.AI, cs.LG, cs.NE Citations 31 Venue Annual Meeting of the Association for Computational Linguistics Repository https://github.com/sronnqvist/discourse-ablstm ⭐ 33 Last Checked 1 month ago

Abstract

We introduce an attention-based Bi-LSTM for Chinese implicit discourse relations and demonstrate that modeling argument pairs as a joint sequence can outperform word order-agnostic approaches. Our model benefits from a partial sampling scheme and is conceptually simple, yet achieves state-of-the-art performance on the Chinese Discourse Treebank. We also visualize its attention activity to illustrate the model's ability to selectively focus on the relevant parts of an input sequence.