Search

Your search keyword '"Chauhan, Anuj"' showing total 798 results
Start Over Author "Chauhan, Anuj"
798 results on '"Chauhan, Anuj"'

2. PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries

Author

Dong, Mingwen, Kumar, Nischal Ashok, Hu, Yiqun, Chauhan, Anuj, Hang, Chung-Wei, Chang, Shuaichen, Pan, Lin, Lan, Wuwei, Zhu, Henghui, Jiang, Jiarong, Ng, Patrick, and Wang, Zhiguo

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

Previous text-to-SQL datasets and systems have primarily focused on user questions with clear intentions that can be answered. However, real user questions can often be ambiguous with multiple interpretations or unanswerable due to a lack of relevant data. In this work, we construct a practical conversational text-to-SQL dataset called PRACTIQ, consisting of ambiguous and unanswerable questions inspired by real-world user questions. We first identified four categories of ambiguous questions and four categories of unanswerable questions by studying existing text-to-SQL datasets. Then, we generate conversations with four turns: the initial user question, an assistant response seeking clarification, the user's clarification, and the assistant's clarified SQL response with the natural language explanation of the execution results. For some ambiguous queries, we also directly generate helpful SQL responses, that consider multiple aspects of ambiguity, instead of requesting user clarification. To benchmark the performance on ambiguous, unanswerable, and answerable questions, we implemented large language model (LLM)-based baselines using various LLMs. Our approach involves two steps: question category classification and clarification SQL prediction. Our experiments reveal that state-of-the-art systems struggle to handle ambiguous and unanswerable questions effectively. We will release our code for data generation and experiments on GitHub.

Published
2024

16. UNITE: A Unified Benchmark for Text-to-SQL Evaluation

Author

Lan, Wuwei, Wang, Zhiguo, Chauhan, Anuj, Zhu, Henghui, Li, Alexander, Guo, Jiang, Zhang, Sheng, Hang, Chung-Wei, Lilien, Joseph, Hu, Yiqun, Pan, Lin, Dong, Mingwen, Wang, Jun, Jiang, Jiarong, Ash, Stephen, Castelli, Vittorio, Ng, Patrick, and Xiang, Bing

Subjects
Computer Science - Computation and Language
Abstract

A practical text-to-SQL system should generalize well on a wide variety of natural language questions, unseen database schemas, and novel SQL query structures. To comprehensively evaluate text-to-SQL systems, we introduce a UNIfied benchmark for Text-to-SQL Evaluation (UNITE). It is composed of publicly available text-to-SQL datasets, containing natural language questions from more than 12 domains, SQL queries from more than 3.9K patterns, and 29K databases. Compared to the widely used Spider benchmark, we introduce $\sim$120K additional examples and a threefold increase in SQL patterns, such as comparative and boolean questions. We conduct a systematic study of six state-of-the-art (SOTA) text-to-SQL parsers on our new benchmark and show that: 1) Codex performs surprisingly well on out-of-domain datasets; 2) specially designed decoding methods (e.g. constrained beam search) can improve performance for both in-domain and out-of-domain settings; 3) explicitly modeling the relationship between questions and schemas further improves the Seq2Seq models. More importantly, our benchmark presents key challenges towards compositional generalization and robustness issues -- which these SOTA models cannot address well. Our code and data processing script are available at https://github.com/awslabs/unified-text2sql-benchmark, Comment: 5 pages

Published
2023

17. A Comparative Review on Bisphenol A Sources, Environmental Levels, Migration, and Health Impacts in India and Global Context

Author

Sugata Datta, Abhishek Chauhan, Anuj Ranjan, Abul Hasan Sardar, Hardeep Singh Tuli, Seema Ramniwas, Moyad Shahwan, Ujjawal Sharma and Tanu Jindal

Subjects
bisphenol a, health concerns, environmental levels, food-contact materials, Environmental effects of industries and plants, TD194-195, Science (General), Q1-390
Abstract

Bisphenol A (BPA) is a widely utilized chemical found in numerous everyday products, including plastic containers, food packaging, and thermal paper. Research has linked BPA exposure to a range of health concerns, encompassing developmental and reproductive issues, cancer, and obesity. Given India's status as one of the world's largest producers and consumers of plastic goods, understanding the potential risks associated with BPA exposure and its health impacts on the Indian population is of paramount importance. This paper conducts a comparative analysis of BPA sources, environmental levels, migration, and health impacts in India in comparison to other countries. By examining data from various nations, we aim to discern overarching trends and patterns in BPA exposure and its associated health effects. This analysis serves as a foundation for the development of policies and regulations designed to safeguard public health. While the Indian government has taken some regulatory steps, such as banning the production, import, and sale of BPA-containing polycarbonate baby bottles, there is a notable absence of specific regulations or bans on BPA in other food-contact materials (FCMs). Studies conducted in India have detected BPA in various food items, underscoring the potential risk of BPA exposure through food consumption. This emphasizes the urgent need for effective monitoring and control of BPA migration in FCMs within India. In conclusion, this comparative review underscores the imperative for ongoing research and rigorous monitoring of BPA exposure and its health impacts in India, as well as in other nations. Safeguarding the health of the general public necessitates a comprehensive understanding of BPA's prevalence, sources, and consequences. By implementing and refining regulations, such as extending bans on BPA in additional FCMs, policymakers can work towards mitigating the risks associated with BPA exposure and ensuring the safety of populations worldwide.

Published
2024
Full Text
View/download PDF

19. Importance of Synthesizing High-quality Data for Text-to-SQL Parsing

Author

Zhao, Yiyun, Jiang, Jiarong, Hu, Yiqun, Lan, Wuwei, Zhu, Henry, Chauhan, Anuj, Li, Alexander, Pan, Lin, Wang, Jun, Hang, Chung-Wei, Zhang, Sheng, Dong, Marvin, Lilien, Joe, Ng, Patrick, Wang, Zhiguo, Castelli, Vittorio, and Xiang, Bing

Subjects
Computer Science - Computation and Language
Abstract

Recently, there has been increasing interest in synthesizing data to improve downstream text-to-SQL tasks. In this paper, we first examined the existing synthesized datasets and discovered that state-of-the-art text-to-SQL algorithms did not further improve on popular benchmarks when trained with augmented synthetic data. We observed two shortcomings: illogical synthetic SQL queries from independent column sampling and arbitrary table joins. To address these issues, we propose a novel synthesis framework that incorporates key relationships from schema, imposes strong typing, and conducts schema-distance-weighted column sampling. We also adopt an intermediate representation (IR) for the SQL-to-text task to further improve the quality of the generated natural language questions. When existing powerful semantic parsers are pre-finetuned on our high-quality synthesized data, our experiments show that these models have significant accuracy boosts on popular benchmarks, including new state-of-the-art performance on Spider.

Published
2022

20. Contributors

Author

Ahamad, Faheem, primary, Allahkarami, Ebrahim, additional, Allahkarami, Esmaeil, additional, Aneja, Riya, additional, Aparajita, Pragnyashree, additional, Bandyopadhyay, Anwesha, additional, Bano, Ambreen, additional, Bhutiani, Rakesh, additional, Bulgariu, Laura, additional, Chandniha, Surendra Kumar, additional, Chauhan, Anuj, additional, Choudhury, Shubhalaxmi, additional, Das, Subhankar, additional, Dhiman, Soniya, additional, Duguna, Selamu, additional, Ghosh, Amit Kumar, additional, Ghosh, Asim K., additional, Gupta, Himanshu, additional, Hota, Garudadhwaj, additional, Islam, Sk Saruk, additional, Kalyani, Manjula Ishwara, additional, Kant, Krishan, additional, Karmakar, Suchetana, additional, Khosla, Babita, additional, Kohli, Himanshu P., additional, Kothari, Richa, additional, Kumar, Vikas, additional, Kumar, Sanjay, additional, Laura, Jitender Singh, additional, M V, Thara, additional, Maddheshiya, Rahul, additional, Mahadwad, Omprakash K., additional, Mahato, Sumana, additional, Maitra, S.S., additional, Midya, Sujoy, additional, Murugesan, Sibiraj, additional, Nainwal, Y.C., additional, Nambi, Indumathi M., additional, Nasr, Mahmoud, additional, Padhiari, Sandip, additional, Patel, Dipaknashi, additional, R, Sasikaladevi, additional, Raval, Akash R., additional, Sahoo, Ugrabadi, additional, Sahu, Deep Mala, additional, Saini, Karan, additional, Saini, Vipin Kumar, additional, Saxena, Gaurav, additional, Sen, Nupur, additional, Sharma, Pooja, additional, Singh, Bhupender, additional, Singh, Surendra Pratap, additional,  , Surbhi, additional, Tanwer, Naresh, additional, Tong, Yen Wah, additional, Tyagi, Inderjeet, additional, Tyagi, Kaomud, additional, Usman, Sani Sharif, additional, Vaidyanathan, Rama, additional, Verma, Akanksha, additional, Wani, Atif Khurshid, additional, and Yadav,  , Rahul, additional

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results