Events

EMNLP w/ Juha, Maciej & Julien

LOUHI 2020: The 11th International Workshop on Health Text Mining and Information Analysis.

20 November | 09:30 | Register here →

Simple Hierarchical Multi-Task Neural End-To-End Entity Linking for Biomedical Text

Recognising and linking entities is a crucial first step to many tasks in biomedical text analysis, such as relation extraction and target identification. Traditionally, biomedical entity linking methods rely heavily on heuristic rules and predefined, often domain-specific features. The features try to capture the properties of entities and complex multi-step architectures to detect, and subsequently link entity mentions. We propose a significant simplification to the biomedical entity linking setup that does not rely on any heuristic methods. The system performs all the steps of the entity linking task jointly in either single or two stages. We explore the use of hierarchical multi-task learning, using mention recognition and entity typing tasks as auxiliary tasks. We show that hierarchical multi-task models consistently outperform single-task models when trained tasks are homogeneous. We evaluate the performance of our models on the biomedical entity linking benchmarks using MedMentions and BC5CDR datasets. We achieve state-of-theart results on the challenging MedMentions dataset, and comparable results on BC5CDR.


Maciej Wiatrak
Machine Learning Engineer

Maciej is a Machine Learning Engineer at BenevolentAI, where he focuses on Natural Language Processing (NLP) and its applications in drug discovery. In the past he has worked in research labs at University College London and University of Edinburgh on topics such as multi-agent reinforcement learning and generative adversarial networks. Recently, he has become interested in geometric deep learning and utilising different manifolds for effective representation learning.

Juha Iso-Sipila
Senior Lead AI Scientist

Juha has MSc (1996) and PhD (2008) degrees in Computer Science from Tampere University of Technology. After graduation he worked for Nokia in Finland and in China, developing speech recognition, text-to-speech synthesis and predictive text input technologies for Nokia. In 2013 Juha relocated to London to work as Head of Research at SwiftKey. During this time SwiftKey launched a neural network based mobile predictive text input system. Juha has been at BenevolentAI from 2017. His main interests are in Deep Learning for biomedical NLP and distributed computing using Apache Spark.


SustaiNLP 2020

20 November | Time TBC | Register here →

Learning Informative Representations of Biomedical Relations with Latent Variable Models

Extracting biomedical relations from large cor-pora of scientific documents is a challengingnatural language processing task.  Existing ap-proaches  usually  focus  on  identifying  a  rela-tion either in a single sentence (mention-level)or across an entire corpus (pair-level). In bothcases, recent methods have achieved strong re-sults by learning a point estimate to representthe relation;  this is then used as the input toa relation classifier.  However, the relation ex-pressed  in  text  between  a  pair of  biomedicalentities is often more complex than can be cap-tured by a point estimate.  To address this is-sue, we propose a latent variable model withan arbitrarily flexible distribution to representthe relation between an entity pair.  Addition-ally, our model provides a unified architecturefor both mention-level and pair-level relationextraction.    We  demonstrate  that  our  modelachieves results competitive with strong base-lines for both tasks while having fewer param-eters and being significantly faster to train. Wemake our code publicly available.

You can find the paper published here, and the code can be accessed on GitHub here.

The lead author of this paper was Harshil Shah, our Machine Learning Intern.

Julien Fauqueur
Lead AI Scientist

Julien Fauqueur is a Lead AI Scientist at BenevolentAI. He has developed natural language processing methods for biomedical information extraction and, since this year, he has been the AI Lead for the Chemistry group. He holds a PhD in computer science from INRIA in France. While a research associate at the University of Cambridge, then as a senior researcher in industry, he developed new methods and products using computer vision and machine learning. He co-authored around 30 academic publications and 5 patents.

More Posts

You Might Also Like

Blog
Transforming drug discovery with AI: how we’re building and nurturing the best talent for the job
At BenevolentAI, we are on a mission to bring life-changing medicines to patients, and we are looking for collaborative, mission-driven people to join our tech, drug discovery and business operations teams in London, Cambridge and New York.
Oct 17, 2021
News
BenevolentAI identifies novel target for ulcerative colitis and advances candidate to IND/CTA-enabling studies
BenevolentAI’s AI-Drug Discovery platform uncovered a novel target not previously linked to ulcerative colitis and advanced candidate to preclinical studies.
Oct 14, 2021
Blog
Measuring bias: moving towards more inclusive health research outcomes #stateofai
Having shared our open-source Diversity Analysis Tool last year, we were tasked to investigate and demonstrate the lack of diversity in biomedical data as part of the State of AI Report 2021.
Oct 12, 2021
Blog
Expert-augmented computational drug discovery for rare diseases
Combining scientific expertise, computational tools and our AI-enhanced biomedical knowledge graph to successfully uncover a new drug combination for treating a rare brain cancer in children.
Sep 28, 2021
News
BenevolentAI appoints Dr John Orloff to its Board of Directors
Biopharmaceutical veteran Dr John Orloff joins the BenevolentAI Board as a Non-Executive Director as it scales the development of its leading AI-derived drug pipeline.
Sep 9, 2021
Blog
AI in Drug Discovery
This blog seeks to demystify the application of artificial intelligence (AI) and machine learning (ML) in drug discovery by exploring some of the challenges, opportunities and progress that has been achieved in the field so far.
Jul 13, 2021