Implicit Entity Recognition in Clinical Documents

Abstract

With the increasing automation of health care information processing, it has become crucial to extract meaningful information from textual notes in electronic medical records. One of the key challenges is to extract and normalize entity mentions. State-of-the-art approaches have focused on the recognition of entities that are explicitly mentioned in a sentence. However, clinical documents often contain phrases that indicate the entities but do not contain their names. We term those implicit entity mentions and introduce the problem of implicit entity recognition (IER) in clinical documents. We propose a solution to IER that leverages entity definitions from a knowledge base to create entity models, projects sentences to the entity models and identifies implicit entity mentions by evaluating semantic similarity between sentences and entity models. The evaluation with 857 sentences selected for 8 different entities shows that our algorithm outperforms the most closely related unsupervised solution. The similarity value calculated by our algorithm proved to be an effective feature in a supervised learning setting, helping it to improve over the baselines, and achieving F1 scores of .81 and .73 for different classes of implicit mentions. Our gold standard annotations are made available to encourage further research in the area of IER.

No One is Perfect: Analysing the Performance of Question Answering Components over the DBpedia Knowledge Graph

“…for which the class label university is expected to be mapped to dbo:University through an exact match. In such cases, OKBQA DM CLS 25 has the baseline F-score 0.72 compared to the state-of-the-art F-score 0.52 for the CL task [33]. However, when class mentions are implicit, the baseline F-score drops to 0.45, but OKBQA DM CLS is still the best component.…”

Knowledge will propel machine understanding of content

“…2. The text to be recognized is complex (i.e., beyond simple entity -person/location/organization), requiring novel techniques for dealing with complex/compound entities [27], implicit entities [25,26], and subjectivity (emotions, intention) [13,38]. 3.…”

“…We have developed knowledge-driven solutions that decode the implicit entity mentions in clinical narratives [25] and tweets [26]. We exploit the publicly available knowledge bases (only the portions that matches with the domain of interest) in order to access the required domain knowledge to decode implicitly mentioned entities.…”

Implicit Entity Linking in Tweets

“…Our previous work on implicit entity linking has dealt with clinical entities in electronic medical records [15]. The main challenge in the medical setting resides in the heterogeneous usage of language by individuals mentioning entities implicitly including their negated mentions.…”