Leading the way in innovation for over 55 years, we build greater futures for businesses across multiple industries and 55 countries.
Our expert, committed team put our shared beliefs into action – every day. Together, we combine innovation and collective knowledge to create the extraordinary.
We share news, insights, analysis and research – tailored to your unique interests – to help you deepen your knowledge and impact.
At TCS, we believe exceptional work begins with hiring, celebrating and nurturing the best people — from all walks of life.
Get access to a catalog of the latest news stories from across TCS. Discover our press releases, reports, and company announcements.
Recent advancement in neural network architectures has provided several opportunities to develop systems to automatically extract and represent information from domain-specific unstructured text sources. The Finsim-2021 shared task, collocated with the FinNLP workshop, offered the challenge to automatically learn effective and precise semantic models of financial domain concepts. Building such semantic representations of domain concepts requires knowledge about the specific domain. Such a thorough knowledge can be obtained through the contextual information available in raw text documents on those domains. In this paper, we proposed a transformer-based BERT architecture that captures such contextual information from a set of domain-specific raw documents and then perform a classification task to segregate domain terms into fixed number of class labels. The proposed model not only considers the contextual BERT embeddings but also incorporates a TF-IDF vectorizer that gives a word-level importance to the model. The performance of the model has been evaluated against several baseline architectures.
Research area: Data and decision sciences
Authors: Tushar Goel, Vipul Chauhan, Ishan Verma, Tirthankar Dasgupta, Lipika Dey
Conference/event: Financial Technology on the Web (FinWeb) Workshop at World Wide Web Conference (WWW) – TheWebConf 2021
Conference date: April 2021
Digital twin tech for sustainable food supply chain
Improving manufacturing process efficiency with unobtrusive sensing
Transforming Lives Through Service Design & Design for Change
AI workload migration to the cloud