Litcius/Paper detail

Porous Lattice Transformer Encoder for Chinese NER

Mengge Xue, Bowen Yu, Tingwen Liu, Yue Zhang, Erli Meng, Bin Wang

202077 citationsDOIOpen Access PDF

Abstract

Incorporating lexicons into character-level Chinese NER by lattices is proven effective to exploit rich word boundary information. Previous work has extended RNNs to consume lattice inputs and achieved great success. However, due to the DAG structure and the inherently unidirectional sequential nature, this method precludes batched computation and sufficient semantic interaction. In this paper, we propose PLTE, an extension of transformer encoder that is tailored for Chinese NER, which models all the characters and matched lexical words in parallel with batch processing. PLTE augments self-attention with positional relation representations to incorporate lattice structure. It also introduces a porous mechanism to augment localness modeling and maintain the strength of capturing the rich long-term dependencies. Experimental results show that PLTE performs up to 11.4 times faster than state-of-the-art methods while realizing better performance. We also demonstrate that using BERT representations further substantially boosts the performance and brings out the best in PLTE.

Topics & Concepts

EncoderComputer scienceTransformerComputationNatural language processingArtificial intelligenceExtension (predicate logic)Chinese charactersNamed-entity recognitionLattice (music)Theoretical computer scienceAlgorithmProgramming languageEngineeringSystems engineeringElectrical engineeringAcousticsPhysicsVoltageOperating systemTask (project management)Topic ModelingNatural Language Processing TechniquesSpeech Recognition and Synthesis
Porous Lattice Transformer Encoder for Chinese NER | Litcius