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

## TL;DR

This paper presents an attention-based Bi-LSTM model for recognizing Chinese implicit discourse relations, outperforming previous methods by modeling argument pairs as joint sequences and visualizing attention to interpret focus areas.

## Contribution

The paper introduces a novel attention-based Bi-LSTM approach that models argument pairs as joint sequences, achieving state-of-the-art results on Chinese discourse relation recognition.

## Key findings

- Outperforms previous models on Chinese Discourse Treebank
- Effectively models argument pairs as joint sequences
- Provides interpretability through attention visualization

## 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.