PubMed, a repository and search engine for biomedical literature, now indexes >1 million articles each year. This exceeds the processing capacity of human domain experts, limiting our ability to truly understand many diseases. We present Reach, a system for automated, large-scale machine reading of biomedical papers that can extract mechanistic descriptions of biological processes with relatively high precision at high throughput. We demonstrate that combining the extracted pathway fragments with existing biological data analysis algorithms that rely on curated models helps identify and explain a large number of previously unidentified mutually exclusive altered signaling pathways in seven different cancer types. This work shows that combining human-curated ‘big mechanisms’ with extracted ‘big data’ can lead to a causal, predictive understanding of cellular processes and unlock important downstream applications.

We describe the design, development, and API of ODIN (Open Domain INformer), a domainindependent, rule-based event extraction (EE) framework. The proposed EE approach is: simple (most events are captured with simple lexico-syntactic patterns), powerful (the language can capture complex constructs, such as events taking other events as arguments, and regular expressions over syntactic graphs), robust (to recover from syntactic parsing errors, syntactic patterns can be freely mixed with surface, token-based patterns), and fast (the runtime environment processes 110 sentences/second in a real-world domain with a grammar of over 200 rules). We used this framework to develop a grammar for the biochemical domain, which approached human performance. Our EE framework is accompanied by a web-based user interface for the rapid development of event grammars and visualization of matches. The ODIN framework and the domain-specific grammars are available as open-source code.

We describe the design, development, and API for two discourse parsers for Rhetorical Structure Theory. The two parsers use the same underlying framework, but one uses features that rely on dependency syntax, produced by a fast shift-reduce parser, whereas the other uses a richer feature space, including both constituent-and dependency-syntax and coreference information, produced by the Stanford CoreNLP toolkit. Both parsers obtain state-of-the-art performance, and use a very simple API consisting of, minimally, two lines of Scala code. We accompany this code with a visualization library that runs the two parsers in parallel, and displays the two generated discourse trees side by side, which provides an intuitive way of comparing the two parsers.

We propose a lightly-supervised approach for information extraction, in particular named entity classification, which combines the benefits of traditional bootstrapping, i.e., use of limited annotations and interpretability of extraction patterns, with the robust learning approaches proposed in representation learning. Our algorithm iteratively learns custom embeddings for both the multi-word entities to be extracted and the patterns that match them from a few example entities per category. We demonstrate that this representation-based approach outperforms three other state-of-theart bootstrapping approaches on two datasets: CoNLL-2003 and OntoNotes. Additionally, using these embeddings, our approach outputs a globally-interpretable model consisting of a decision list, by ranking patterns based on their proximity to the average entity embedding in a given class. We show that this interpretable model performs close to our complete bootstrapping model, proving that representation learning can be used to produce interpretable models with small loss in performance. This decision list can be edited by human experts to mitigate some of that loss and in some cases outperform the original model.

For many applications of question answering (QA), being able to explain why a given model chose an answer is critical. However, the lack of labeled data for answer justifications makes learning this difficult and expensive. Here we propose an approach that uses answer ranking as distant supervision for learning how to select informative justifications, where justifications serve as inferential connections between the question and the correct answer while often containing little lexical overlap with either. We propose a neural network architecture for QA that reranks answer justifications as an intermediate (and human-interpretable) step in answer selection. Our approach is informed by a set of features designed to combine both learned representations and explicit features to capture the connection between questions, answers, and answer justifications. We show that with this end-to-end approach we are able to significantly improve upon a strong IR baseline in both justification ranking (+9% rated highly relevant) and answer selection (+6% P@1).