Ruty Rinott

Show Me Your Evidence - an Automatic Method for Context Dependent Evidence Detection

Engaging in a debate with oneself or others to take decisions is an integral part of our day-today life. A debate on a topic (say, use of performance enhancing drugs) typically proceeds by one party making an assertion/claim (say, PEDs are bad for health) and then providing an evidence to support the claim (say, a 2006 study shows that PEDs have psychiatric side effects). In this work, we propose the task of automatically detecting such evidences from unstructured text that support a given claim. This task has many practical applications in decision support and persuasion enhancement in a wide range of domains. We first introduce an extensive benchmark data set tailored for this task, which allows training statistical models and assessing their performance. Then, we suggest a system architecture based on supervised learning to address the evidence detection task. Finally, promising experimental results are reported.

A Benchmark Dataset for Automatic Detection of Claims and Evidence in the Context of Controversial Topics

We describe a novel and unique argumentative structure dataset. This corpus consists of data extracted fro m hundreds of Wikipedia articles using a meticulously monitored manual annotation process. The result is 2,683 argument elements, collected in the context of 33 controversial topics, organized under a simp le claim-evidence structure. The obtained data are publicly available for academic research.

TR9856: A Multi-word Term Relatedness Benchmark

Measuring word relatedness is an important ingredient of many NLP applications. Several datasets have been developed in order to evaluate such measures. The main drawback of existing datasets is the focus on single words, although natural language contains a large proportion of multiword terms. We propose the new TR9856 dataset which focuses on multi-word terms and is significantly larger than existing datasets. The new dataset includes many real world terms such as acronyms and named entities, and further handles term ambiguity by providing topical context for all term pairs. We report baseline results for common relatedness methods over the new data, and exploit its magnitude to demonstrate that a combination of these methods outperforms each individual method.

Evicase: an evidence-based case structuring approach for personalized healthcare.

The personalized medicine era stresses a growing need to combine evidence-based medicine with case based reasoning in order to improve the care process. To address this need we suggest a framework to generate multi-tiered statistical structures we call Evicases. Evicase integrates established medical evidence together with patient cases from the bedside. It then uses machine learning algorithms to produce statistical results and aggregators, weighted predictions, and appropriate recommendations. Designed as a stand-alone structure, Evicase can be used for a range of decision support applications including guideline adherence monitoring and personalized prognostic predictions.

Utilizing assigned treatments as labels for supervised machine learning in clinical decision support

Clinical Decision Support (CDS) tools are typically designed to assist physicians in clinical decision making at Point Of Care (POC). Existing CDS tools commonly rely on relatively simple rules, deduced from relevant clinical guidelines. However, the increasing pace by which Health Care Organizations (HCOs) adopt Electronic Health Record technologies suggest great potential for CDS tools that directly mine the massive clinical data collected at the HCO. A natural goal for such tools is to exploit Machine Learning (ML) algorithms in order to predict patients outcome. However, the technical challenges involved in constructing such a system in practice are quite involved, where in particular treatments outcome are often not available as part of the HCOs data. Here, we propose a different strategy in which we use the assigned treatments as the labels in the learning process of the supervised ML algorithms. We present two different use-cases in which our approach could be used. First, in order to highlight the clinical features most associated with the assigned treatments; and second, in order to predict the customary treatment for a patient at POC in a statistically data-driven manner. Altogether, our approach represents a novel strategy that is complementary to the classical paradigm of rule-based clinical guidelines adherence. Experimental results over hypertension clinical data demonstrate the validity of our approach.