Physics

Pattern recognition (psychology)

Feature (linguistics)

Span (engineering)

Mathematics

Boundary (topology)

Structural engineering

Politics

Operating system

Optics

Data mining

Encoder

Engineering

Relationship extraction

Library science

Mathematical analysis

Philosophy

Political science

Artificial intelligence

Relation (database)

Set (abstract data type)

Focus (optics)

Programming language

Representation (politics)

Code (set theory)

Subject (documents)

Computer science

Linguistics

Recent entity and relation extraction works focus on investigating how to obtain a better span representation from the pre-trained encoder. However, a major limitation of existing works is that they ignore the interrelation between spans (pairs). In this work, we propose a novel span representation approach, named Packed Levitated Markers (PL-Marker), to consider the interrelation between the spans (pairs) by strategically packing the markers in the encoder. In particular, we propose a neighborhood-oriented packing strategy, which considers the neighbor spans integrally to better model the entity boundary information. Furthermore, for those more complicated span pair classification tasks, we design a subject-oriented packing strategy, which packs each subject and all its objects to model the interrelation between the same-subject span pairs. The experimental results show that, with the enhanced marker feature, our model advances baselines on six NER benchmarks, and obtains a 4.1%-4.3% strict relation F1 improvement with higher speed over previous state-of-the-art models on ACE04 and ACE05. Our code and models are publicly available at https://github.com/thunlp/PL-Marker

Packed Levitated Marker for Entity and Relation Extraction