NaCTeM

Two papers from NaCTeM accepted at EMNLP 2019

2019-08-15

We are delighted to announce that two papers with authors from NaCTeM have been accepted at EMNLP 2019, which will be held in Hong Kong from 3 - 7 November 2019.

The details of the papers are as follows:


Title: Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs

Authors: Fenia Christopoulou, Makoto Miwa and Sophia Ananiadou

Abstract:
Document-level relation extraction is a complex human process that requires logical inference to extract relationships between named entities in text. Existing approaches use graph-based neural models with words as nodes and edges as relations between them, to encode relations across sentences. These models are node-based, i.e., they form pair representations based solely on the two target node representations. However, entity relations can be better expressed through unique edge representations formed as paths between nodes. We thus propose an edge-oriented graph neural model for document-level relation extraction. The model utilises different types of nodes and edges to create a document-level graph. An inference mechanism on the graph edges enables to learn intra- and inter-sentence relations using multi-instance learning internally. Experiments on two document-level biomedical datasets for chemical-disease and gene-disease associations show the usefulness of the proposed edge-oriented approach.


Title: A Search-based Neural Model for Biomedical Nested and Overlapping Event Detection

Authors: Kurt Junshean Espinosa, Makoto Miwa and Sophia Ananiadou

Abstract:
We tackle the nested and overlapping event detection task and propose a novel search-based neural network (SBNN) structured prediction model that treats the task as a search problem on a relation graph of trigger-argument structures. Unlike existing structured prediction tasks such as dependency parsing, the task targets to detect DAG structures, which constitute events, from the relation graph. We define actions to construct events and use all the beams in a beam search to detect all event structures that may be overlapping and nested. The search process constructs events in a bottom-up manner while modelling the global properties for nested and overlapping structures simultaneously using neural networks. We show that the model achieves performance comparable to the state-of-the-art model Turku Event Extraction System (TEES) on the BioNLP Cancer Genetics (CG) Shared Task 2013 without the use of any syntactic and hand-engineered features. Further analyses on the development set show that our model is flexible and more computationally efficient while yielding higher F1-score performance.

Previous itemNext item
Back to news summary page