Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences
- Daniel Khashabi, Snigdha Chaturvedi, Michael Roth, Shyam Upadhyay, D. Roth
- Computer ScienceNorth American Chapter of the Association for…
- 1 June 2018
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%.
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.
Interaction of influenza virus haemagglutinin with sphingolipid–cholesterol membrane domains via its transmembrane domain
It is demonstrated that raft association is an intrinsic property encoded in the protein, and the data suggest that the binding to specific membrane domains can be encoded in transmembrane proteins and that this information will be used for polarized sorting and signal transduction processes.
LSDSem 2017 Shared Task: The Story Cloze Test
- N. Mostafazadeh, Michael Roth, Annie Louis, Nathanael Chambers, James F. Allen
- Computer ScienceLSDSem@EACL
- 3 April 2017
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, and…
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.
MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge
- Simon Ostermann, Ashutosh Modi, Michael Roth, Stefan Thater, Manfred Pinkal
- Computer ScienceInternational Conference on Language Resources…
- 14 March 2018
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.
SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge
- Simon Ostermann, Michael Roth, Ashutosh Modi, Stefan Thater, Manfred Pinkal
- Computer ScienceInternational Workshop on Semantic Evaluation
- 1 June 2018
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%.
Automatic induction of FrameNet lexical units
- M. Pennacchiotti, D. D. Cao, Roberto Basili, D. Croce, Michael Roth
- Computer ScienceConference on Empirical Methods in Natural…
- 25 October 2008
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.
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.
Tumors Promote Altered Maturation and Early Apoptosis of Monocyte-Derived Dendritic Cells1
It is found that CD14+ cells responded to tumor culture supernatant (TSN) by increasing expression of APC surface markers, up-regulating nuclear translocation of RelB, and developing allostimulatory activity, which may represent another mechanism by which tumors evade immune detection.