Skip to main content
Premium Trial:

Request an Annual Quote

Website Serves as Home for Biological Natural Language Processing

Premium

Interest in natural language processing is steadily increasing in the bioinformatics community. Following on the attention devoted to the topic at the recent Pacific Symposium for Biocomputing, Northeastern University’s Bob Futrelle has launched a website devoted to the subject of extracting information from biological literature.

The site (www.bionlp.org) is meant to serve as the focal point for research in the field. Futrelle said it is designed to take account of the fact that, despite its growth, natural language technology is still a very new area for most biologists.

"The people at [PSB] working in this area in January all felt that the time was right to build some organizational structure into the world-wide efforts. Given my many years of experience in both NLP and biology, I felt that I could really contribute by building a site and setting up a mailing list,”Futrelle said.

Futrelle said that one of the greatest difficulties biological NLP faces is the dearth of people trained in both areas. However, factors such as the availability of Medline and other electronic biology text are spurring the growth of the field.

While the challenges of building systems that allow full natural language querying of text are formidable, Futrelle said that because biology text is generally focused and concise, "the NLP systems that are devised for biology text are not going to have to understand all the nuances of literature such as fiction, poetry, legal writing, and other broad and complex fields.”Current biological NLP approaches, however, are only able to extract information from abstracts. Full-text searching capability is still a long-term goal, according to Futrelle.

In addition to hosting the bionlp.org site and setting up a mailing list on the topic, Futrelle intends to continue his own research in the field. He is in the process of submitting an NSF proposal to further his research on a new system architecture that he said would be more advanced than current approaches to computational linguistics.

Futrelle said he is considering hosting a workshop on natural language processing at the Intelligent Systems for Molecular Biology conference this July in Copenhagen.

— BT

Filed under

The Scan

Shape of Them All

According to BBC News, researchers have developed a protein structure database that includes much of the human proteome.

For Flu and More

The Wall Street Journal reports that several vaccine developers are working on mRNA-based vaccines for influenza.

To Boost Women

China's Ministry of Science and Technology aims to boost the number of female researchers through a new policy, reports the South China Morning Post.

Science Papers Describe Approach to Predict Chemotherapeutic Response, Role of Transcriptional Noise

In Science this week: neural network to predict chemotherapeutic response in cancer patients, and more.