Question answering forums are rapidly growing in size with no effective automated ability to refer to and reuse answers already available for previous posted questions. In this paper, we develop a methodology for finding semantically related questions. The task is difficult since 1) key pieces of information are often buried in extraneous details in the question body and 2) available annotations on similar questions are scarce and fragmented. We design a recurrent and convolutional model (gated convolution) to effectively map questions to their semantic representations. The models are pre-trained within an encoder-decoder framework (from body to title) on the basis of the entire raw corpus, and fine-tuned discriminatively from limited annotations. Our evaluation demonstrates that our model yields substantial gains over a standard IR baseline and various neural network architectures (including CNNs, LSTMs and GRUs).
Benefits derived from the conduct of Big Room are well established. At present, the lean practitioners have been focusing on tapping the potential of this technique by systematizing the processes associated with implementation of Big Room. But there has been no quantifiable metrics to measure the same. In this context, this paper reports a study undertaken to develop and implement Big Room Effectiveness Index (BREI) that assesses effectiveness of Big Room. This research study adopted action research approach in the context of an Indian real estate developer. A core group within this developer was formed to steer the initiative of BREI. Based on literature review and interactions within core group, 10 measures for assessing effectiveness of Big Room were identified, which are grouped under four categories: collaboration, look-ahead planning, knowledge building and tools used, and continuous improvement. The framework was codified with some flexibility to provide inputs like parameter weightages and rating of these parameters. The developed BREI was implemented in an ongoing real estate project. The BREI was plotted on a monthly basis and it provided valuable input to participants involved in the Big Room meetings and suggested areas of improvements.
The term Key Opinion Leader in marketing is not new. Key Opinion Leaders (KOLs) commonly known as thought leaders who play a crucial role in the life science industry. We through this project intend to implement the concept of identifying key opinion leaders using weighted Social Network Analysis (SNA). We intend to use European PubMed Central dataset for creating a weighted social Network of authors who have healthcare and medicine related publications and apply different centrality measures on it. In order to collect the data, we will be using one of the web scraping methods and predefined libraries like scrapy. After fetching and processing the data we intend to form a network of authors using python’s NetworkX library. This network will then be subjected to various centrality measures which in turn will give prominent opinion leaders as the output.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.