Wholly sustainable graft copolymers derived from cellulose, lignin, and hemicellulose for high-performance elastomers, adhesives, and UV-blocking materials.

Sustainable elastomers derived from renewable biobased resources with excellent mechanical properties and varied functions are highly pursued to substitute traditional petroleum-based polymers yet challenging due to their limited macroscopic performance. In this work, we designed a series of wholly biobased cellulose-graft-poly(vanillin acrylate-co-tetrahydrofurfuryl acrylate) (Cell-g-P(VA-co-THFA) copolymer elastomers with cellulose as the rigid backbone, sustainable VA derived from lignin and soft THFA derived from hemicellulose as the hard and soft segments in the rubbery side chains. Moreover, the grafted side chains can be cross-linked to introduce an additional dynamic network structure via Schiff-base chemistry between the aldehyde and amino groups. The mechanical properties of Cell-g-P(VA-co-THFA) copolymer elastomers, including tensile strength, extensibility, elasticity, and toughness can be facilely manipulated by the VA/THFA feed ratio, cellulose content, and cross-linking density. These Cell-g-P(VA-co-THFA) copolymer elastomers are thermally stable and possess outstanding adhesion behavior and prominent UV-shielding performance. Besides dramatically enhanced mechanical properties, the cross-linked Cell-g-P(VA-co-THFA) counterparts exhibit remarkable shape memory behavior. This work provides a robust and convenient strategy for developing strong and versatile sustainable elastomers with different application demands by integrating different biomass feedstocks via elaborate molecular design.

Fully biobased sustainable elastomers derived from chitin, lignin, and plant oil via grafting strategy and Schiff-base chemistry.

With the dramatically increased environmental problems, the rational design of sustainable polymers from renewable feedstocks opens new avenues to reduce the huge pollution impact. The major challenge for sustainable polymers is the decreased mechanical performance compared to that of petroleum-based materials. In this work, fully biobased sustainable elastomers were developed by integrating renewable chitin, lignin, and plant oil into one macromolecule, in which chitin was chosen as the rigid backbone, while a lignin-derived monomer vanillin acrylate (VA) and a plant oil-based monomer lauryl acrylate (LA) were selected as the hard and soft segments for the grafted side chains. A series of Chitin-graft-poly(vanillin acrylate-co-lauryl acrylate) (Chitin-g-P(VA-co-LA)) copolymers with varied feed ratios and chitin contents were synthesized by using reversible addition-fragmentation chain transfer (RAFT) polymerization as an effective grafting strategy. In addition, a dynamic cross-linked network was incorporated via Schiff-base reaction to improve the macroscopic behavior of such kind of chitin graft elastomers. These sustainable elastomers are mechanically strong and show excellent reprocessablity, as well as outstanding UV-blocking property. This strategy is versatile and can inspire the further development of fully biobased sustainable materials from natural resources.

Adversarial Knowledge Distillation Based Biomedical Factoid Question Answering.

Biomedical factoid question answering is an essential application for biomedical information sharing. Recently, neural network based approaches have shown remarkable performance for this task. However, due to the scarcity of annotated data which requires intensive knowledge of expertise, training a robust model on limited-scale biomedical datasets remains a challenge. Previous works solve this problem by introducing useful knowledge. It is found that the interaction between question and answer (QA-interaction) is also a kind of knowledge which could help extract answer accurately. This research develops a knowledge distillation framework for biomedical factoid question answering, in which a teacher model as the knowledge source of QA-interaction is designed to enhance the student model. In addition, to further alleviate the problem of limited-scale dataset, a novel adversarial knowledge distillation technique is proposed to robustly distill the knowledge from teacher model to student model by constructing perturbed examples as additional training data. By forcing the student model to mimic the predicted distributions of teacher model on both original examples and perturbed examples, the knowledge of QA-interaction can be learned by student model. We evaluate the proposed framework on the widely used BioASQ datasets, and experimental results have shown the proposed method's promising potential.

Improving Biomedical ReQA With Consistent NLI-Transfer and Post-Whitening.

Retrieval Question Answering (ReQA) is an essential mechanism of information sharing which aims to find the answer to a posed question from large-scale candidates. Currently, the most efficient solution is Dual-Encoder which has shown great potential in the general domain, while it still lacks research on biomedical ReQA. Obtaining a robust Dual-Encoder from biomedical datasets is challenging, as scarce annotated data are not enough to sufficiently train the model which results in over-fitting problems. In this work, we first build ReQA BioASQ datasets for retrieving answers to biomedical questions, which can facilitate the corresponding research. On that basis, we propose a framework to solve the over-fitting issue for robust biomedical answer retrieval. Under the proposed framework, we first pre-train Dual-Encoder on natural language inference (NLI) task before the training on biomedical ReQA, where we appropriately change the pre-training objective of NLI to improve the consistency between NLI and biomedical ReQA, which significantly improve the transferability. Moreover, to eliminate the feature redundancies of Dual-Encoder, consistent post-whitening is proposed to conduct decorrelation on the training and trained sentence embeddings. With extensive experiments, the proposed framework achieves promising results and exhibits significant improvement compared with various competitive methods.

Named Entity Aware Transfer Learning for Biomedical Factoid Question Answering.

Biomedical factoid question answering is an important task in biomedical question answering applications. It has attracted much attention because of its reliability. In question answering systems, better representation of words is of great importance, and proper word embedding can significantly improve the performance of the system. With the success of pretrained models in general natural language processing tasks, pretrained models have been widely used in biomedical areas, and many pretrained model-based approaches have been proven effective in biomedical question-answering tasks. In addition to proper word embedding, name entities also provide important information for biomedical question answering. Inspired by the concept of transfer learning, in this study, we developed a mechanism to fine-tune BioBERT with a named entity dataset to improve the question answering performance. Furthermore, we applied BiLSTM to encode the question text to obtain sentence-level information. To better combine the question level and token level information, we use bagging to further improve the overall performance. The proposed framework was evaluated on BioASQ 6b and 7b datasets, and the results have shown that our proposed framework can outperform all baselines.