Towards Recognition of Textual Entailment in the Biomedical Domain

The medical literature suffers from disagreements among authors discussing the same topic or treatment. With thousands of articles published daily, there is a need to detect inconsistent and often contradictory findings. Natural language inference (NLI) gained a lot of interest in the past years, however, domain-specific NLI systems are yet to be examined in depth. In this paper, we conduct several experiments on sentence pairs extracted from PubMed abstracts, to infer whether they express entailment, contradiction or neutral meanings. The main focus of this research is to recognize textual entailment in published evidence-based medicine findings. We explore popular NLI models and sentence embeddings, adapted to the biomedical domain. We further investigate improving the inference detection abilities of the models by incorporating traditional machine learning (ML) features with deep learning (DL) architecture. The proposed model serves in capturing biomedical language’s representations by combining lexical, contextual and compositional semantics.

[1]  J. Ioannidis.  Why Most Published Research Findings Are False , 2005, PLoS medicine.

[2]  Marco R. Spruit,et al.  Automated Contradiction Detection in Biomedical Literature , 2018, MLDM.

[3]  Stergios Chatzikyriakidis,et al.  Testing the Generalization Power of Neural Network Models across NLI Benchmarks , 2018, BlackboxNLP@ACL.

[4]  John A. Stankovic,et al.  Preclude2 : Personalized conflict detection in heterogeneous health applications , 2017, Pervasive Mob. Comput..

[5]  Jianhua Li,et al.  Analysis of Polarity Information in Medical Text , 2005, AMIA.

[6]  Nan Hua,et al.  Universal Sentence Encoder for English , 2018, EMNLP.

[7]  Holger Schwenk,et al.  Supervised Learning of Universal Sentence Representations from Natural Language Inference Data , 2017, EMNLP.

[8]  John P A Ioannidis,et al.  Reversals of established medical practices: evidence to abandon ship. , 2012, JAMA.

[9]  Omer Levy,et al.  Annotation Artifacts in Natural Language Inference Data , 2018, NAACL.

[10]  Dejing Dou,et al.  Discovering Inconsistencies in PubMed Abstracts through Ontology-Based Information Extraction , 2017, BCB.

[11]  Wlodek Zadrozny,et al.  A Sheaf Model of Contradictions and Disagreements. Preliminary Report and Discussion , 2018, ArXiv.

[12]  W. Bruce Croft,et al.  On the Benefit of Incorporating External Features in a Neural Architecture for Answer Sentence Selection , 2017, SIGIR.

[13]  Farzaneh Sarafraz,et al.  Finding conflicting statements in the biomedical literature , 2012 .

[14]  Abdulaziz Alamri,et al.  The Detection of Contradictory Claims in Biomedical Abstracts , 2016 .