Named Entity Recognition for Social Media Texts with Semantic Augmentation

EMNLP 2020  ·  Yuyang Nie, Yuanhe Tian, Xiang Wan, Yan Song, Bo Dai ·

Existing approaches for named entity recognition suffer from data sparsity problems when conducted on short and informal texts, especially user-generated social media content. Semantic augmentation is a potential way to alleviate this problem. Given that rich semantic information is implicitly preserved in pre-trained word embeddings, they are potential ideal resources for semantic augmentation. In this paper, we propose a neural-based approach to NER for social media texts where both local (from running text) and augmented semantics are taken into account. In particular, we obtain the augmented semantic information from a large-scale corpus, and propose an attentive semantic augmentation module and a gate module to encode and aggregate such information, respectively. Extensive experiments are performed on three benchmark datasets collected from English and Chinese social media platforms, where the results demonstrate the superiority of our approach to previous studies across all three datasets.

PDF Abstract EMNLP 2020 PDF EMNLP 2020 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Chinese Named Entity Recognition Weibo NER SA-NER F1 69.8 # 5
Named Entity Recognition (NER) WNUT 2016 SA-NER F1 55.01 # 4
Named Entity Recognition (NER) WNUT 2017 SA-NER F1 50.36 # 13

Methods


No methods listed for this paper. Add relevant methods here