Neural Temporal Relation Extraction

By Steven Bethard, Timothy Miller, Dmitriy Dligach, Chen Lin, Guergana K. Savova. 2017

96 citations recorded by the source corpus.

We experiment with neural architectures for temporal relation extraction and establish a new state-of-the-art for several scenarios. We find that neural models with only tokens as input outperform state-of-the-art hand-engineered feature-based models, that convolutional neural networks outperform LSTM models, and that encoding relation arguments with XML tags outperforms a traditional position-based encoding.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Nanyun Peng
2. Rujun Han
3. Qiang Ning
4. Dan Roth
5. Matt Gardner
6. Xiang Ren
7. Shuaicheng Zhang
8. Lifu Huang

Citations in the corpus

• Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction (2020, unknown): “Some recent work (Dligach et al., 2017; Leeuwenberg and Moens, 2017; Galvan et al., 2018) apply neural network-based methods to model the temporal relations, but are not capable of incorporating prior knowledge about clinical events and temporal relations as proposed by our framework.”
• Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference (2020, unknown): “2016; Chikka 2016) such as SVMs, MaxEnt and CRFs, and neural network based methods (Lin et al. 2017, 2018; Dligach et al. 2017; Tourille et al. 2017; Lin et al. 2019; Guan et al. 2020; Lin et al. 2020; Galvan-Sosa et al. 2020).”
• Extracting Temporal Event Relation with Syntactic-Guided Temporal Graph Transformer (2021, background): “Recently, deep neural networks (Dligach et al., 2017; Tourille et al., 2017) and large-scale pre-training language models (Han et al., 2019a, 2020; Wang et al., 2020a; Zhou et al., 2020) are further employed and show state-of-the-art performance on temporal relation extraction.”
• Joint Constrained Learning for Event-Event Relation Extraction (2020, methodology): “More recent works attempted to use data-driven methods based on neural relation extraction models (Dligach et al., 2017; Ning et al., 2019; Han et al., 2019a,b) which refrain from feature engineering and offer competent performances.”
• Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks (2017, methodology): “We adopted the same xml-tag marked-up token sequence representation and model setup as (Dligach et al., 2017).”
• TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions (2020, background): “…al., 2012; Cham-bers et al., 2014; Ning et al., 2018a), structured learning (Leeuwenberg and Moens, 2017; Ning et al., 2017), and neural networks (Dligach et al., 2017; Lin et al., 2017; Tourille et al., 2017; Cheng and Miyao, 2017; Meng and Rumshisky, 2018; Leeuwenberg and Moens, 2018; Ning et…”