Linguistically Informed Relation Extraction and Neural Architectures for Nested Named Entity Recognition in BioNLP-OST 2019 (2019-10-08T00:00:00.000000Z)

TL;DR

The proposed approach of Named Entities can be generalized to different languages and it’s effectiveness for English and Spanish text is shown, and the system ranked first in the SeeDev-binary Relation Extraction Task.

Abstract

Named Entity Recognition (NER) and Relation Extraction (RE) are essential tools in distilling knowledge from biomedical literature. This paper presents our findings from participating in BioNLP Shared Tasks 2019. We addressed Named Entity Recognition including nested entities extraction, Entity Normalization and Relation Extraction. Our proposed approach of Named Entities can be generalized to different languages and we have shown it’s effectiveness for English and Spanish text. We investigated linguistic features, hybrid loss including ranking and Conditional Random Fields (CRF), multi-task objective and token level ensembling strategy to improve NER. We employed dictionary based fuzzy and semantic search to perform Entity Normalization. Finally, our RE system employed Support Vector Machine (SVM) with linguistic features. Our NER submission (team:MIC-CIS) ranked first in BB-2019 norm+NER task with standard error rate (SER) of 0.7159 and showed competitive performance on PharmaCo NER task with F1-score of 0.8662. Our RE system ranked first in the SeeDev-binary Relation Extraction Task with F1-score of 0.3738.

Authors

Hinrich Schütze

22 papers

Usama Yaseen

1 papers

Pankaj Gupta

1 papers

TL;DR

Abstract

Authors

References36 items

Bacteria Biotope at BioNLP Open Shared Tasks 2019

PharmaCoNER: Pharmacological Substances, Compounds and proteins Named Entity Recognition track

Enriching Pre-trained Language Model with Entity Information for Relation Classification

BioWordVec, improving biomedical word embeddings with subword information and MeSH

Neural Relation Extraction Within and Across Sentence Boundaries

Document Informed Neural Autoregressive Topic Models with Distributional Prior

LISA: Explaining Recurrent Neural Network Judgments via Layer-wIse Semantic Accumulation and Example to Pattern Transformation

Joint Bootstrapping Machines for High Confidence Relation Extraction

A Multi-task Approach for Named Entity Recognition in Social Media Data

Semi-supervised Multitask Learning for Sequence Labeling

Cross-Sentence N-ary Relation Extraction with Graph LSTMs

Table Filling Multi-Task Recurrent Neural Network for Joint Entity and Relation Extraction

LitWay, Discriminative Extraction for Different Bio-Events

Relation Classification via Multi-Level Attention CNNs

Overview of the Regulatory Network of Plant Seed Development (SeeDev) Task at the BioNLP Shared Task 2016.

Enriching Word Vectors with Subword Information

Bi-directional recurrent neural network with ranking loss for spoken language understanding

Neural Architectures for Named Entity Recognition

Overview of the gene regulation network and the bacteria biotope tasks in BioNLP'13 shared task

Classifying Relations by Ranking with Convolutional Neural Networks

PubMed and beyond: a survey of web tools for searching biomedical literature

A unified architecture for natural language processing: deep neural networks with multitask learning

Various criteria in the evaluation of biomedical named entity recognition

Simple Algorithms for Complex Relation Extraction with Applications to Biomedical IE

Biomedical Named Entity Recognition using Conditional Random Fields and Rich Feature Sets

Combining Lexical, Syntactic, and Semantic Features with Maximum Entropy Models for Information Extraction

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

Bagging Predictors

Spacccpos-tagger

Annotation of negation in the IULA Spanish Clinical Record Corpus

VERSE: Event and Relation Extraction in the BioNLP 2016 Shared Task

[ SciELO (Scientific Electronic Library Online) statistical data interpretation].

Interpretação dos dados estatísticos da SciELO (Scientific Eletronic Library Online)

[The Spanish Bibliographic Index of the Health Sciences (IBECS) and Actas Urológicas Españolas].

Índice bibliográfico español en ciencias de la salud (ibecs) y actas urológicas españolas

MEDLINEplus: building and maintaining the National Library of Medicine's consumer health Web service.

Field of Study

Venue Information

Name

Type

URL

Alternate Names