• Publications
  • Influence
Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences
The dataset is the first to study multi-sentence inference at scale, with an open-ended set of question types that requires reasoning skills, and finds human solvers to achieve an F1-score of 88.1%. Expand
Targeting QseC Signaling and Virulence for Antibiotic Development
Using a high-throughput screen, a small molecule is identified that inhibits the binding of signals to QseC, preventing its autophosphorylation and consequently inhibitingQseC-mediated activation of virulence gene expression, markedly inhibits the virulence of several pathogens in vitro and in vivo in animals. Expand
Neural Semantic Role Labeling with Dependency Path Embeddings
A novel model for semantic role labeling that makes use of neural sequence modeling techniques and treats complex syntactic structures and related phenomena, such as nested subordinations and nominal predicates, as subsequences of lexicalized dependency paths and learns suitable embedding representations. Expand
SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge
This report summarizes the results of the SemEval 2018 task on machine comprehension using commonsense knowledge, where the best performing system achieves an accuracy of 83.95%, outperforming the baselines by a large margin, but still far from the human upper bound, which was found to be at 98%. Expand
MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge
A large dataset of narrative texts and questions about these texts, intended to be used in a machine comprehension task that requires reasoning using commonsense knowledge, and shows that the mode of data collection via crowdsourcing results in a substantial amount of inference questions. Expand
LSDSem 2017 Shared Task: The Story Cloze Test
The LSDSem’17 shared task is the Story Cloze Test, a new evaluation for story understanding and script learning. This test provides a system with a four-sentence story and two possible endings, andExpand
Automatic induction of FrameNet lexical units
This paper investigates the applicability of distributional and WordNet-based models on the task of lexical unit induction, i.e. the expansion of FrameNet with new lexical units, and shows good level of accuracy and coverage, especially when combined. Expand
Composition of Word Representations Improves Semantic Role Labelling
While straight-forward word representations of predicates and arguments improve performance, it is shown that further gains are achieved by composing representations that model the interaction between predicate and argument, and capture full argument spans. Expand
Minimal PU.1 reduction induces a preleukemic state and promotes development of acute myeloid leukemia
It is demonstrated that minimal reduction of a key lineage-specific transcription factor, which commonly occurs in human disease, is sufficient to initiate cancer development, and it provides mechanistic insight into the formation and progression of preleukemic stem cells in AML. Expand
Context-aware Frame-Semantic Role Labeling
This paper presents a semantic role labeling system that takes into account sentence and discourse context and introduces several new features which are motivated based on linguistic insights and experimentally demonstrate that they lead to significant improvements over the current state-of-the-art in FrameNet-based semantic role labeled. Expand