• Publications
  • Influence
Summarizing Source Code using a Neural Attention Model
This paper presents the first completely datadriven approach for generating high level summaries of source code, which uses Long Short Term Memory (LSTM) networks with attention to produce sentences that describe C# code snippets and SQL queries.
Neural AMR: Sequence-to-Sequence Models for Parsing and Generation
This work presents a novel training procedure that can lift the limitation of the relatively limited amount of labeled data and the non-sequential nature of the AMR graphs, and presents strong evidence that sequence-based AMR models are robust against ordering variations of graph-to-sequence conversions.
Learning a Neural Semantic Parser from User Feedback
We present an approach to rapidly and easily build natural language interfaces to databases for new domains, whose performance improves over time based on user feedback, and requires minimal
Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval
This work proposes a simple and efficient multi-hop dense retrieval approach for answering complex open-domain questions, which achieves state-of-the-art performance on twoMulti-hop datasets, HotpotQA and multi-evidence FEVER, and can be applied to any unstructured text corpus.
Mapping Language to Code in Programmatic Context
This work introduces CONCODE, a new large dataset with over 100,000 examples consisting of Java classes from online code repositories, and develops a new encoder-decoder architecture that models the interaction between the method documentation and the class environment.
Learning to Map Context-Dependent Sentences to Executable Formal Queries
We propose a context-dependent model to map utterances within an interaction to executable formal queries. To incorporate interaction history, the model maintains an interaction-level encoder that
Efficient One-Pass End-to-End Entity Linking for Questions
ELQ is presented, a fast end-to-end entity linking model for questions, which uses a biencoder to jointly perform mention detection and linking in one pass, and significantly improves the downstream QA performance of GraphRetriever.
Pharmacovigilance Using Clinical Notes
It is argued that analyzing large volumes of free‐text clinical notes enables drug safety surveillance using a yet untapped data source and can be used for hypothesis generation and for rapid analysis of suspected adverse event risk.
Proton Pump Inhibitor Usage and the Risk of Myocardial Infarction in the General Population
The association of PPI exposure with risk for MI in the general population supports the pre-clinical findings that PPIs may adversely impact vascular function, and provides an example of how a combination of experimental and data-mining approaches can be applied to prioritize drug safety signals for further investigation.
Mining clinical text for signals of adverse drug-drug interactions
It is feasible to identify DDI signals and estimate the rate of adverse events among patients on drug combinations, directly from clinical text, and this could have utility in prioritizing drug interaction surveillance as well as in clinical decision support.