Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Whereas people learn many different types of knowledge from diverse experiences over many years, most current machine learning systems acquire just a single function or data model from just a single data set. We propose a never-ending... more
Whereas people learn many different types of knowledge from diverse experiences over many years, most current machine learning systems acquire just a single function or data model from just a single data set. We propose a never-ending learning paradigm for machine learning, to better reflect the more ambitious and encompassing type of learning performed by humans. As a case study, we describe the Never-Ending Language Learner (NELL), which achieves some of the desired properties of a never-ending learner, and we discuss lessons learned. NELL has been learning to read the web 24 hours/day since January 2010, and so far has acquired a knowledge base with over 80 million confidence-weighted beliefs (e.g., servedWith(tea, biscuits)). NELL has also learned millions of features and parameters that enable it to read these beliefs from the web. Additionally, it has learned to reason over these beliefs to infer new beliefs, and is able to extend its ontology by synthesizing new relational pr...
Research Interests:
The choice of surfactant is vital for tailoring the zeta potential of silica which in turn improves the electro-osmotic performance.
Research Interests:
To what extent do language models (LMs) build “mental models” of a scene when answering situated questions (e.g., questions about a specific ethical dilemma)? While cognitive science has shown that mental models play a fundamental role in... more
To what extent do language models (LMs) build “mental models” of a scene when answering situated questions (e.g., questions about a specific ethical dilemma)? While cognitive science has shown that mental models play a fundamental role in human problemsolving, it is unclear whether the high questionanswering performance of existing LMs is backed by similar model building and if not, whether that can explain their wellknown catastrophic failures. We observed that Macaw, an existing T5-based LM, when probed provides somewhat useful but inadequate mental models for situational questions (estimated accuracy=43%, usefulness=21%, consistency=42%). We propose DREAM, a model that takes a situational question as input to produce a mental model elaborating the situation, without any additional task specific training data for mental models. It inherits its social commonsense through distant supervision from existing NLP resources. Our analysis shows that DREAM can produce significantly better ...
Research Interests:
The mineral deposits in the Kachchh region of Gujarat contain bauxite of all different grades, with a huge amount of low-grade bauxite. The low-grade bauxite from Kachchh is characterized in detail using different physicochemical... more
The mineral deposits in the Kachchh region of Gujarat contain bauxite of all different grades, with a huge amount of low-grade bauxite. The low-grade bauxite from Kachchh is characterized in detail using different physicochemical techniques like X-ray diffraction (XRD), wavelength dispersive X-ray fluorescence (WD-XRF), field emission scanning electron microscopy (FESEM) with energy-dispersive X-ray (EDX) detector, nitrogen adsorption/desorption isotherm at 77 K, and inductive coupled plasma-mass spectrophotometer (ICP-MS). The different mineral phases present in the low-grade bauxite were identified from the X-ray diffraction studies. The different elements present in the mineral were identified and quantified using WD-XRF and EDX measurements. The quantification of rare-earth elements particularly scandium is carried out by ICP-MS analysis. The digestion method has been optimized for the complete mineral digestion and precise measurement of scandium. The low-grade Kachchh bauxite is explored for the possible extraction of alumina and scandium. The ICP-MS analysis shows the presence of approximately 80 ppm of scandium in the low-grade bauxite. The low-grade bauxite has approximately 39% alumina, which is predominantly gibbsite in nature. The alkali digestion conditions were optimized for the maximum dissolution and extraction of gibbsite.
Research Interests:
Research Interests:
Panchpatmali Bauxite deposit is the one amongst a series of bauxite deposits which were discovered in the east coast region of India in early 1960s to put India in the 5th position in the world's Bauxite map with a total bauxite... more
Panchpatmali Bauxite deposit is the one amongst a series of bauxite deposits which were discovered in the east coast region of India in early 1960s to put India in the 5th position in the world's Bauxite map with a total bauxite reserve over 02(two) billion tonnes and current annual production is about 4.8 million tonnes per annum which is now under expansion to 6.3 Milion tonne. Consi-dering its vast deposit containing over 300 million tonnes reserve, Panchpatmali bauxite deposit under name and style of NALCO Ltd., was picked up
Research Interests:
Procedural texts often describe processes (e.g., photosynthesis and cooking) that happen over entities (e.g., light, food). In this paper, we introduce an algorithm for procedural reading comprehension by translating the text into a... more
Procedural texts often describe processes (e.g., photosynthesis and cooking) that happen over entities (e.g., light, food). In this paper, we introduce an algorithm for procedural reading comprehension by translating the text into a general formalism that represents processes as a sequence of transitions over entity attributes (e.g., location, temperature). Leveraging pre-trained language models, our model obtains entity-aware and attribute-aware representations of the text by joint prediction of entity attributes and their transitions. Our model dynamically obtains contextual encodings of the procedural text exploiting information that is encoded about previous and current states to predict the transition of a certain attribute which can be identified as a span of text or from a pre-defined set of classes. Moreover, our model achieves state of the art results on two procedural reading comprehension datasets, namely ProPara and npn-cooking
Research Interests:
Artificial intelligence has achieved remarkable mastery over games such as Chess, Go, and poker, and even Jeopardy!, but the rich variety of standardized exams has remained a landmark challenge. Even as recently as 2016, the best... more
Artificial intelligence has achieved remarkable mastery over games such as Chess, Go, and poker, and even Jeopardy!, but the rich variety of standardized exams has remained a landmark challenge. Even as recently as 2016, the best artificial intelligence system could only achieve 59.3 percent on an eighth‐grade science exam (Schoenick et al. 2017). This article reports success on the Grade 8 New York Regents Science Exam, where, for the first time, a system scores more than ninety percent on the exam's non‐diagram, multiple‐choice questions. In addition, our Aristo system, building upon the success of recent language models, exceeded eighty‐three percent on the corresponding Grade 12 Science Exam's non‐diagram, multiple‐choice questions. The results, on unseen test questions, are robust across different test years and different variations of this kind of test. They demonstrate that modern natural language processing methods can result in mastery on this task. While not a full...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Whereas people learn many different types of knowledge from diverse experiences over many years, and become better learners over time, most current machine learning systems are much more narrow, learning just a single function or data... more
Whereas people learn many different types of knowledge from diverse experiences over many years, and become better learners over time, most current machine learning systems are much more narrow, learning just a single function or data model based on statistical analysis of a single data set. We suggest that people learn better than computers precisely because of this difference, and we suggest a key direction for machine learning research is to develop software architectures that enable intelligent agents to also learn many types of knowledge, continuously over many years, and to become better learners over time. In this paper we define more precisely this never-ending learning paradigm for machine learning, and we present one case study: the Never-Ending Language Learner (NELL), which achieves a number of the desired properties of a never-ending learner. NELL has been learning to read the Web 24hrs/day since January 2010, and so far has acquired a knowledge base with 120mn diverse,...
Research Interests:
Our goal is to construct a domain-targeted, high precision knowledge base (KB), containing general (subject,predicate,object) statements about the world, in support of a downstream question-answering (QA) application. Despite recent... more
Our goal is to construct a domain-targeted, high precision knowledge base (KB), containing general (subject,predicate,object) statements about the world, in support of a downstream question-answering (QA) application. Despite recent advances in information extraction (IE) techniques, no suitable resource for our task already exists; existing resources are either too noisy, too named-entity centric, or too incomplete, and typically have not been constructed with a clear scope or purpose. To address these, we have created a domain-targeted, high precision knowledge extraction pipeline, leveraging Open IE, crowdsourcing, and a novel canonical schema learning algorithm (called CASI), that produces high precision knowledge targeted to a particular domain - in our case, elementary science. To measure the KB’s coverage of the target domain’s knowledge (its “comprehensiveness” with respect to science) we measure recall with respect to an independent corpus of domain text, and show that our ...
Research Interests:
Research Interests:
Use of plant based drugs and chemicals for curing the various ailments specific to women is as old as human civilization. Plants and plant-based medicaments are the basis of many of the modern pharmaceuticals we used today for our various... more
Use of plant based drugs and chemicals for curing the various ailments specific to women is as old as human civilization. Plants and plant-based medicaments are the basis of many of the modern pharmaceuticals we used today for our various ailments. Nearly 80% of the world populations rely on the traditional medicines for primary health care, most of which involve the use of plant extracts. Many traditional herbal remedies have also been utilized as aids in various gynecological problems arise in females. The present paper gave an overview on the uses of medicinal plants for the treatment of gynecological problems and it was concluded that they are effective alternative to allopath medicine.