1 code implementation • 28 Sep 2020 • Artuur Leeuwenberg, Marie-Francine Moens
Temporal information extraction is a challenging but important area of automatic natural language understanding.
Natural Language Understanding Temporal Information Extraction
no code implementations • 13 May 2020 • Artuur Leeuwenberg, Marie-Francine Moens
Time is deeply woven into how people perceive, and communicate about the world.
Natural Language Understanding Temporal Information Extraction
no code implementations • 9 Jan 2020 • Liesbeth Allein, Artuur Leeuwenberg, Marie-Francine Moens
Drawing on previous research conducted on neural context-dependent dt-mistake correction models (Heyman et al. 2018), this study constructs the first neural network model for Dutch demonstrative and relative pronoun resolution that specifically focuses on the correction and part-of-speech prediction of these two pronouns.
1 code implementation • EMNLP 2018 • Artuur Leeuwenberg, Marie-Francine Moens
The current leading paradigm for temporal information extraction from text consists of three phases: (1) recognition of events and temporal expressions, (2) recognition of temporal relations among them, and (3) time-line construction from the temporal relations.
1 code implementation • COLING 2018 • Artuur Leeuwenberg, Marie-Francine Moens
In this work, we extend our classification model's task loss with an unsupervised auxiliary loss on the word-embedding level of the model.
no code implementations • COLING 2018 • Quynh Ngoc Thi Do, Artuur Leeuwenberg, Geert Heyman, Marie-Francine Moens
This paper presents a flexible and open source framework for deep semantic role labeling.
1 code implementation • SEMEVAL 2017 • Artuur Leeuwenberg, Marie-Francine Moens
In this paper, we describe the system of the KULeuven-LIIR submission for Clinical TempEval 2017.
1 code implementation • EACL 2017 • Artuur Leeuwenberg, Marie-Francine Moens
We propose a scalable structured learning model that jointly predicts temporal relations between events and temporal expressions (TLINKS), and the relation between these events and the document creation time (DCTR).