No abstract

Distant supervised relation extraction has been widely used to find novel relational facts from text. However, distant supervision inevitably accompanies with the wrong labelling problem, and these noisy data will substantially hurt the performance of relation extraction. To alleviate this issue, we propose a sentence-level attention-based model for relation extraction. In this model, we employ convolutional neural networks to embed the semantics of sentences. Afterwards, we build sentence-level attention over multiple instances, which is expected to dynamically reduce the weights of those noisy instances. Experimental results on real-world datasets show that, our model can make full use of all informative sentences and effectively reduce the influence of wrong labelled instances. Our model achieves significant and consistent improvements on relation extraction as compared with baselines. The source code of this paper can be obtained from https: //github.com/thunlp/NRE.

Neural language representation models such as BERT pre-trained on large-scale corpora can well capture rich semantic patterns from plain text, and be fine-tuned to consistently improve the performance of various NLP tasks. However, the existing pre-trained language models rarely consider incorporating knowledge graphs (KGs), which can provide rich structured knowledge facts for better language understanding. We argue that informative entities in KGs can enhance language representation with external knowledge. In this paper, we utilize both large-scale textual corpora and KGs to train an enhanced language representation model (ERNIE), which can take full advantage of lexical, syntactic, and knowledge information simultaneously. The experimental results have demonstrated that ERNIE achieves significant improvements on various knowledge-driven tasks, and meanwhile is comparable with the state-of-the-art model BERT on other common NLP tasks. The source code and experiment details of this paper can be obtained from https:// github.com/thunlp/ERNIE. * indicates equal contribution † Corresponding author: Z.Liu(liuzy@tsinghua.edu.cn) is_a is_a Song Book a u th o r c o m p o s e r Bob Dylan Chronicles: Volume One Blowin' in the wind Songwriter Writer is_a is_a Bob Dylan wrote

No abstract

Herein, we report a de novo chemical design of supramolecular polymer materials (SPMs-1-3) by condensation polymerization, consisting of (i) soft polymeric chains (polytetramethylene glycol and tetraethylene glycol) and (ii) strong and reversible quadruple H-bonding cross-linkers (from 0 to 30 mol %). The former contributes to the formation of the soft domain of the SPMs, and the latter furnishes the SPMs with desirable mechanical properties, thereby producing soft, stretchable, yet tough elastomers. The resulting SPM-2 was observed to be highly stretchable (up to 17 000% strain), tough (fracture energy ∼30 000 J/m), and self-healing, which are highly desirable properties and are superior to previously reported elastomers and tough hydrogels. Furthermore, a gold, thin film electrode deposited on this SPM substrate retains its conductivity and combines high stretchability (∼400%), fracture/notch insensitivity, self-healing, and good interfacial adhesion with the gold film. Again, these properties are all highly complementary to commonly used polydimethylsiloxane-based thin film metal electrodes. Last, we proceed to demonstrate the practical utility of our fabricated electrode via both in vivo and in vitro measurements of electromyography signals. This fundamental understanding obtained from the investigation of these SPMs will facilitate the progress of intelligent soft materials and flexible electronics.

Multiple entities in a document generally exhibit complex inter-sentence relations, and cannot be well handled by existing relation extraction (RE) methods that typically focus on extracting intra-sentence relations for single entity pairs. In order to accelerate the research on document-level RE, we introduce DocRED, a new dataset constructed from Wikipedia and Wikidata with three features: (1) DocRED annotates both named entities and relations, and is the largest humanannotated dataset for document-level RE from plain text; (2) DocRED requires reading multiple sentences in a document to extract entities and infer their relations by synthesizing all information of the document; (3) along with the human-annotated data, we also offer large-scale distantly supervised data, which enables DocRED to be adopted for both supervised and weakly supervised scenarios. In order to verify the challenges of documentlevel RE, we implement recent state-of-the-art methods for RE and conduct a thorough evaluation of these methods on DocRED. Empirical results show that DocRED is challenging for existing RE methods, which indicates that document-level RE remains an open problem and requires further efforts. Based on the detailed analysis on the experiments, we discuss multiple promising directions for future research. We make DocRED and the code for our baselines publicly available at https: //github.com/thunlp/DocRED. * indicates equal contribution

Representation learning of knowledge bases aims to embed both entities and relations into a low-dimensional space. Most existing methods only consider direct relations in representation learning. We argue that multiple-step relation paths also contain rich inference patterns between entities, and propose a path-based representation learning model. This model considers relation paths as translations between entities for representation learning, and addresses two key challenges: (1) Since not all relation paths are reliable, we design a path-constraint resource allocation algorithm to measure the reliability of relation paths. (2) We represent relation paths via semantic composition of relation embeddings.Experimental results on real-world datasets show that, as compared with baselines, our model achieves significant and consistent improvements on knowledge base completion and relation extraction from text. The source code of this paper can be obtained from https://github.com/mrlyk423/ relation_extraction.

The ability to control chemical and physical structuring at the nanometre scale is important for developing high-performance thermoelectric materials. Progress in this area has been achieved mainly by enhancing phonon scattering and consequently decreasing the thermal conductivity of the lattice through the design of either interface structures at nanometre or mesoscopic length scales or multiscale hierarchical architectures. A nanostructuring approach that enables electron transport as well as phonon transport to be manipulated could potentially lead to further enhancements in thermoelectric performance. Here we show that by embedding nanoparticles of a soft magnetic material in a thermoelectric matrix we achieve dual control of phonon- and electron-transport properties. The properties of the nanoparticles-in particular, their superparamagnetic behaviour (in which the nanoparticles can be magnetized similarly to a paramagnet under an external magnetic field)-lead to three kinds of thermoelectromagnetic effect: charge transfer from the magnetic inclusions to the matrix; multiple scattering of electrons by superparamagnetic fluctuations; and enhanced phonon scattering as a result of both the magnetic fluctuations and the nanostructures themselves. We show that together these effects can effectively manipulate electron and phonon transport at nanometre and mesoscopic length scales and thereby improve the thermoelectric performance of the resulting nanocomposites.