A Recurrent Neural Model With Attention For The Recognition Of Chinese Implicit Discourse Relations
ASecurity**arXiv ID:** 1704.08092 **Authors:** Samuel Rönnqvist, Niko Schenk, Christian Chiarcos **Published:** 2017-04-26T13:10:12Z **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 vis...
- 3 stars
- 0 votes
- 0 copies
- 4 views
- Added September 11, 2026
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill a-recurrent-neural-model-with-attention-for-the-recognition-of-chinese-implicit-discourse-relations --agent claude-codeAre you the author of A Recurrent Neural Model With Attention For The Recognition Of Chinese Implicit Discourse Relations?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-a-recurrent-neural-model-with-attention-for-the-re)# A Recurrent Neural Model with Attention for the Recognition of Chinese Implicit Discourse Relations
**arXiv ID:** 1704.08092
**Authors:** Samuel Rönnqvist, Niko Schenk, Christian Chiarcos
**Published:** 2017-04-26T13:10:12Z
**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.
## Skill Description
This skill is generated from the arXiv paper: A Recurrent Neural Model with Attention for the Recognition of Chinese Implicit Discourse Relations (1704.08092).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:1704.08092](http://arxiv.org/abs/1704.08092v1)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.