基于GCN和门机制的汉语框架排歧方法(Chinese Frame Disambiguation Method Based on GCN and Gate Mechanism)

no code implementations • CCL 2022 • Yanan You, Ru Li, Xuefeng Su, Zhichao Yan, Minshuai Sun, Chao Wang

基于框架语义映射和类型感知的篇章事件抽取(Document-Level Event Extraction Based on Frame Semantic Mapping and Type Awareness)

no code implementations • CCL 2022 • Jiang Lu, Ru Li, Xuefeng Su, Zhichao Yan, Jiaxing Chen

“篇章事件抽取是从给定的文本中识别其事件类型和事件论元。目前篇章事件普遍存在数据稀疏和多值论元耦合的问题。基于此, 本文将汉语框架网(CFN)与中文篇章事件建立映射, 同时引入滑窗机制和触发词释义改善了事件检测的数据稀疏问题;使用基于类型感知标签的多事件分离策略缓解了论元耦合问题。为了提升模型的鲁棒性, 进一步引入对抗训练。本文提出的方法在DuEE-Fin和CCKS2021数据集上实验结果显著优于现有方法。”

Document-level Event Extraction Event Extraction

Handwritten Mathematical Expression Recognition via Attention Aggregation based Bi-directional Mutual Learning

1 code implementation • 7 Dec 2021 • Xiaohang Bian, Bo Qin, Xiaozhe Xin, Jianwu Li, Xuefeng Su, Yanfeng Wang

Handwritten mathematical expression recognition aims to automatically generate LaTeX sequences from given images.

Data Augmentation Decoder +1

A Knowledge-Guided Framework for Frame Identification

no code implementations • ACL 2021 • Xuefeng Su, Ru Li, XiaoLi Li, Jeff Z. Pan, Hu Zhang, Qinghua Chai, Xiaoqi Han

In this paper, we propose a Knowledge-Guided Frame Identification framework (KGFI) that integrates three types frame knowledge, including frame definitions, frame elements and frame-to-frame relations, to learn better frame representation, which guides the KGFI to jointly map target words and frames into the same embedding space and subsequently identify the best frame by calculating the dot-product similarity scores between the target word embedding and all of the frame embeddings.

Semantic Parsing Sentence