From POS tagging to dependency parsing for biomedical event extraction (2018-08-11T00:00:00.000000Z)

TL;DR

A detailed empirical study comparing traditional feature-based and neural network-based models for POS tagging and dependency parsing in the biomedical context is presented, and the influence of parser selection for a biomedical event extraction downstream task is investigated.

Abstract

Given the importance of relation or event extraction from biomedical research publications to support knowledge capture and synthesis, and the strong dependency of approaches to this information extraction task on syntactic information, it is valuable to understand which approaches to syntactic processing of biomedical text have the highest performance. We perform an empirical study comparing state-of-the-art traditional feature-based and neural network-based models for two core natural language processing tasks of part-of-speech (POS) tagging and dependency parsing on two benchmark biomedical corpora, GENIA and CRAFT. To the best of our knowledge, there is no recent work making such comparisons in the biomedical context; specifically no detailed analysis of neural models on this data is available. Experimental results show that in general, the neural models outperform the feature-based models on two benchmark biomedical corpora GENIA and CRAFT. We also perform a task-oriented evaluation to investigate the influences of these models in a downstream application on biomedical event extraction, and show that better intrinsic parsing performance does not always imply better extrinsic event extraction performance. We have presented a detailed empirical study comparing traditional feature-based and neural network-based models for POS tagging and dependency parsing in the biomedical context, and also investigated the influence of parser selection for a biomedical event extraction downstream task. We make the retrained models available at https://github.com/datquocnguyen/BioPosDep.

Authors

Karin M. Verspoor

4 papers

Dat Quoc Nguyen

12 papers

TL;DR

Abstract

Authors

References60 items

Are general practitioners getting the information they need from hospitals and specialists to provide quality cancer care for Indigenous Australians?

CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

An Improved Neural Network Model for Joint POS Tagging and Dependency Parsing

Paris and Stanford at EPE 2017: Downstream Evaluation of Graph-based Dependency Representations

Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging

Deep learning with word embeddings improves biomedical named entity recognition

A Novel Neural Network Model for Joint POS Tagging and Graph-based Dependency Parsing

Cross-Sentence N-ary Relation Extraction with Graph LSTMs

Deep Biaffine Attention for Neural Dependency Parsing

How to Train good Word Embeddings for Biomedical NLP

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Dynamic Feature Induction: The Last Gist to the State-of-the-Art

Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss

Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations

End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

Neural Architectures for Named Entity Recognition

Incorporating Nesterov Momentum into Adam

Bidirectional LSTM-CRF Models for Sequence Tagging

It Depends: Dependency Parser Comparison Using A Web-based Evaluation Tool

Distributed Representations of Words and Phrases and their Compositionality

Efficient Higher-Order CRFs for Morphological Tagging

Extracting Biomedical Events and Modifications Using Subgraph Matching with Noisy Training Data

Transition-based Dependency Parsing with Selectional Branching

Overview of BioNLP Shared Task 2013

A corpus of full-text journal articles is a robust evaluation tool for revealing differences in performance of biomedical natural language processing tools

A corpus of full-text journal articles is a robust evaluation tool for revealing differences in performance of biomedical natural language processing tools

BioLemmatizer: a lemmatization tool for morphological processing of biomedical text

Supervised Sequence Labelling with Recurrent Neural Networks

Getting the Most out of Transition-based Dependency Parsing

The structural and content aspects of abstracts versus bodies of full text journal articles are different

Evaluating Dependency Representations for Event Extraction

Lemmatization and Lexicalized Statistical Parsing of Morphologically-Rich Languages: the Case of French

Proceedings of the NAACL HLT 2010 First Workshop on Statistical Parsing of Morphologically-Rich Languages

Overview of BioNLP’09 Shared Task on Event Extraction

Extracting Complex Biological Events with Rich Graph-Based Feature Sets

The Stanford Typed Dependencies Representation

The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies

Self-Training for Biomedical Parsing

Simple Semi-supervised Dependency Parsing

Manual curation is not sufficient for annotation of genomic databases

Characterizing the Errors of Data-Driven Dependency Parsing Models

Developing a Robust Part-of-Speech Tagger for Biomedical Text

Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking

Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network

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

Long Short-Term Memory

Bidirectional recurrent neural networks

Building a Large Annotated Corpus of English: The Penn Treebank

Class-Based n-gram Models of Natural Language

Proceedings of the Workshop on Cross-Framework and Cross-Domain Parser Evaluation; 2008

The Biomedical Event Extraction Downstream Application

Stanford’s Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task

Shared Task on Extrinsic Parser Evaluation

A Fast and Accurate Dependency Parser using Neural Networks

Guidelines for the CLEAR Style Constituent to Dependency Conversion

Any Domain Parsing: Automatic Domain Adaptation for Natural Language Parsing

Workshop Companion Volume for Shared Task

Syntax Annotation for the GENIA Corpus

The 2017 Shared Task on Extrinsic Parser Evaluation Towards a Reusable Community Infrastructure

File Description: Accepted version

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names