Geodesy

Dependency graph

Quantum mechanics

Algorithm

Benchmark (surveying)

Chromatography

Theoretical computer science

Economics

Data mining

Computer science

Geology

Oceanography

Physics

Extraction (chemistry)

Binary tree

Task (project management)

Graph

Pattern recognition (psychology)

Mathematics

Politics

Management

Geography

Political science

SemEval

Mathematical analysis

Artificial intelligence

Representation (politics)

Tree (set theory)

Combinatorics

Chemistry

Dependency (UML)

Term (time)

Machine learning

Baseline (sea)

Tree structure

IEEE/ACM Transactions on Audio Speech and Language Processing

Aspect term extraction is one of the important subtasks in aspect-based sentiment analysis. Previous studies have shown that using dependency tree structure representation is promising for this task. However, most dependency tree structures involve only one directional propagation on the dependency tree. In this paper, we first propose a novel bidirectional dependency tree network to extract dependency structure features from the given sentences. The key idea is to explicitly incorporate both representations gained separately from the bottom-up and top-down propagation on the given dependency syntactic tree. An end-to-end framework is then developed to integrate the embedded representations and BiLSTM plus CRF to learn both tree-structured and sequential features to solve the aspect term extraction problem. Experimental results demonstrate that the proposed model outperforms state-of-the-art baseline models on four benchmark SemEval datasets.

Improving Aspect Term Extraction With Bidirectional Dependency Tree Representation