DocRED: A Large-Scale Document-Level Relation Extraction Dataset
- Yuan Yao, Deming Ye, Maosong Sun
- Computer ScienceAnnual Meeting of the Association for…
- 14 June 2019
Empirical results show that DocRED is challenging for existing RE methods, which indicates that document-level RE remains an open problem and requires further efforts.
Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
- Deli Chen, Yankai Lin, Wei Li, Peng Li, Jie Zhou, Xu Sun
- Computer ScienceAAAI Conference on Artificial Intelligence
- 7 September 2019
Two methods to alleviate the over-smoothing issue of GNNs are proposed: MADReg which adds a MADGap-based regularizer to the training objective; AdaEdge which optimizes the graph topology based on the model predictions.
FewRel 2.0: Towards More Challenging Few-Shot Relation Classification
- Tianyu Gao, Xu Han, Jie Zhou
- Computer ScienceConference on Empirical Methods in Natural…
- 1 October 2019
It is found that the state-of-the-art few-shot relation classification models struggle on these two aspects, and that the commonly-used techniques for domain adaptation and NOTA detection still cannot handle the two challenges well.
A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer
Unsupervised text style transfer aims to transfer the underlying style of text but keep its main content unchanged without parallel data. Most existing methods typically follow two steps: first…
NumNet: Machine Reading Comprehension with Numerical Reasoning
- Qiu Ran, Yankai Lin, Peng Li, Jie Zhou, Zhiyuan Liu
- Computer ScienceConference on Empirical Methods in Natural…
- 15 October 2019
A numerical MRC model named as NumNet is proposed, which utilizes a numerically-aware graph neural network to consider the comparing information and performs numerical reasoning over numbers in the question and passage, outperforming all existing machine reading comprehension models by considering the numerical relations among numbers.
Clustering to Find Exemplar Terms for Keyphrase Extraction
- Zhiyuan Liu, Peng Li, Yabin Zheng, Maosong Sun
- Computer ScienceConference on Empirical Methods in Natural…
- 6 August 2009
This work proposes an unsupervised method for keyphrase extraction that outperforms sate-of-the-art graph-based ranking methods (TextRank) by 9.5% in F1-measure and guarantees the document to be semantically covered by these exemplar terms.
Hierarchical Relation Extraction with Coarse-to-Fine Grained Attention
- Xu Han, Pengfei Yu, Zhiyuan Liu, Maosong Sun, Peng Li
- Computer ScienceConference on Empirical Methods in Natural…
- 2018
The multiple layers of the hierarchical attention scheme provide coarse-to-fine granularity to better identify valid instances, which is especially effective for extracting those long-tail relations.
Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation
- Jie Zhou, Ying Cao, Xuguang Wang, Peng Li, W. Xu
- Computer ScienceInternational Conference on Topology, Algebra and…
- 14 June 2016
This work introduces a new type of linear connections, named fast-forward connections, based on deep Long Short-Term Memory (LSTM) networks, and an interleaved bi-directional architecture for stacking the LSTM layers, and achieves state-of-the-art performance and outperforms the best conventional model by 0.7 BLEU points.
Adversarial Training for Weakly Supervised Event Detection
- Xiaozhi Wang, Xu Han, Zhiyuan Liu, Maosong Sun, Peng Li
- Computer ScienceNorth American Chapter of the Association for…
- 1 June 2019
The experiments show that the candidate selection and adversarial training can cooperate together to obtain more diverse and accurate training data for ED, and significantly outperform the state-of-the-art methods in various weakly supervised scenarios.
HMEAE: Hierarchical Modular Event Argument Extraction
- Xiaozhi Wang, Ziqi Wang, Xiang Ren
- Computer ScienceConference on Empirical Methods in Natural…
- 1 November 2019
A Hierarchical Modular Event Argument Extraction model is proposed, to provide effective inductive bias from the concept hierarchy of event argument roles and significantly outperform the state-of-the-art baselines.
...
...