Indian Institute of Technology Guwahati

About: Indian Institute of Technology Guwahati is a education organization based out in Guwahati, Assam, India. It is known for research contribution in the topics: Catalysis & Computer science. The organization has 6933 authors who have published 17102 publications receiving 257351 citations.

Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention.

Abstract: Relation extraction is the problem of classifying the relationship between two entities in a given sentence. Distant Supervision (DS) is a popular technique for developing relation extractors starting with limited supervision. We note that most of the sentences in the distant supervision relation extraction setting are very long and may benefit from word attention for better sentence representation. Our contributions in this paper are threefold. Firstly, we propose two novel word attention models for distantly- supervised relation extraction: (1) a Bi-directional Gated Recurrent Unit (Bi-GRU) based word attention model (BGWA), (2) an entity-centric attention model (EA), and (3) a combination model which combines multiple complementary models using weighted voting method for improved relation extraction. Secondly, we introduce GDS, a new distant supervision dataset for relation extraction. GDS removes test data noise present in all previous distant- supervision benchmark datasets, making credible automatic evaluation possible. Thirdly, through extensive experiments on multiple real-world datasets, we demonstrate the effectiveness of the proposed methods.

Effect of graphene content on the properties of poly(lactic acid) nanocomposites

Abstract: In the current work, the influence of temperature on the exfoliation of expandable graphite (EG) and its structural properties were investigated in detail. The EG exfoliated at 750 °C was subjected to sonication and further used as reinforcement material in the poly(lactic acid) (PLA) matrix to investigate the influence of “graphene” (GR) on the structural, morphological, thermal, optical, mechanical and oxygen barrier properties of PLA composites. X-ray diffraction results disclose the effect of sonication time on the dispersion ability of GR in the PLA matrix. A high resolution transmission electron microscopy image of GR demonstrates a monolayer structure of GR. Thermo-gravimetric analysis reveals that the Tonset value for the PLA composite with 0.5 wt% GR content increases by 6 °C over neat PLA, when 10% weight loss is taken as a point of comparison. The increase in the thermal stability of PLA composites is also verified by an increase of activation energy (Ea) value evaluated by the Coats–Redfern method. Differential scanning calorimetry analysis confirms that GR acts as a nucleating agent that enhances the melting point of PLA composites over neat PLA. The enhancement of tensile strength (17%) and elongation at break (51%) is obtained for PLA composites over neat PLA.