Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to non-federal websites. Their policies may differ from this site.
It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation ClassifiersWe propose an explainable approach for relation extraction that mitigates the tension between generalization and explainability by jointly training for the two goals. Our approach uses a multi-task learning architecture, which jointly trains a classifier for relation extraction, and a sequence model that labels words in the context of the relation that explain the decisions of the relation classifier. We also convert the model outputs to rules to bring global explanations to this approach. This sequence model is trained using a hybrid strategy: supervised, when supervision from pre-existing patterns is available, and semi-supervised otherwise. In the latter situation, we treat the sequence model’s labels as latent variables, and learn the best assignment that maximizes the performance of the relation classifier. We evaluate the proposed approach on the two datasets and show that the sequence model provides labels that serve as accurate explanations for the relation classifier’s decisions, and, importantly, that the joint training generally improves the performance of the relation classifier. We also evaluate the performance of the generated rules and show that the new rules are great add-on to the manual rules and bring the rule-based system much closer to the neural models.Free, publicly-accessible full text available April 1, 2023
Three fused-ring electron acceptors ( SIDIC , DIDIC and TIDIC ) were designed and synthesized using single bond, vinylene and acetylene units linked indaceno[3,2- b ]dithiophene dimers as electron-rich cores and 3-(1,1-dicyanomethylene)-5,6-difluoro-1-indanone as electron-deficient termini. These molecules exhibit strong absorption from 550 to 900 nm with large attenuation coefficients of 1.8–2.0 × 10 5 M −1 cm −1 and high electron mobilities of 2.2–4.9 × 10 −3 cm 2 V −1 s −1 . In combination with wide-bandgap polymer FTAZ as a donor, organic solar cells exhibit efficiencies of 9.3–13.1%. Effects of the linking units on optical, electronic, morphologic, and photovoltaic properties were revealed. Relative to SIDIC , vinylene-bridged DIDIC shows red-shifted absorption, while acetylene-bridged TIDIC shows blue-shifted absorption. Compared with SIDIC and DIDIC , TIDIC has a lower HOMO, higher electron mobility, and higher device efficiency.