Zobrazeno 1 - 10
of 113
pro vyhledávání: '"Bhattacharya, Indrajit"'
Real-world KBQA applications require models that are (1) robust -- e.g., can differentiate between answerable and unanswerable questions, and (2) low-resource -- do not require large training data. Towards this goal, we propose the novel task of few-
Externí odkaz:
http://arxiv.org/abs/2406.14313
An essential requirement for a real-world Knowledge Base Question Answering (KBQA) system is the ability to detect the answerability of questions when generating logical forms. However, state-of-the-art KBQA models assume all questions to be answerab
Externí odkaz:
http://arxiv.org/abs/2403.10849
Autor:
Patidar, Mayur, Sawhney, Riya, Singh, Avinash, Chatterjee, Biswajit, Mausam, Bhattacharya, Indrajit
Existing Knowledge Base Question Answering (KBQA) architectures are hungry for annotated data, which make them costly and time-consuming to deploy. We introduce the problem of few-shot transfer learning for KBQA, where the target domain offers only a
Externí odkaz:
http://arxiv.org/abs/2311.08894
Pre-trained Generative models such as BART, T5, etc. have gained prominence as a preferred method for text generation in various natural language processing tasks, including abstractive long-form question answering (QA) and summarization. However, th
Externí odkaz:
http://arxiv.org/abs/2311.02961
Two distinct approaches have been proposed for relational triple extraction - pipeline and joint. Joint models, which capture interactions across triples, are the more recent development, and have been shown to outperform pipeline models for sentence
Externí odkaz:
http://arxiv.org/abs/2310.00696
Extracting relational triples from text is a crucial task for constructing knowledge bases. Recent advancements in joint entity and relation extraction models have demonstrated remarkable F1 scores ($\ge 90\%$) in accurately extracting relational tri
Externí odkaz:
http://arxiv.org/abs/2302.09887
Autor:
Patidar, Mayur, Faldu, Prayushi, Singh, Avinash, Vig, Lovekesh, Bhattacharya, Indrajit, Mausam
When answering natural language questions over knowledge bases, missing facts, incomplete schema and limited scope naturally lead to many questions being unanswerable. While answerability has been explored in other QA settings, it has not been studie
Externí odkaz:
http://arxiv.org/abs/2212.10189
Publikováno v:
Published in: 2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)
The number of robots deployed in our daily surroundings is ever-increasing. Even in the industrial set-up, the use of coworker robots is increasing rapidly. These cohabitant robots perform various tasks as instructed by co-located human beings. Thus,
Externí odkaz:
http://arxiv.org/abs/2008.10074
Autor:
Pramanick, Pradip, Sarkar, Chayan, P, Balamuralidhar, Kattepur, Ajay, Bhattacharya, Indrajit, Pal, Arpan
Publikováno v:
Published in: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
A robot as a coworker or a cohabitant is becoming mainstream day-by-day with the development of low-cost sophisticated hardware. However, an accompanying software stack that can aid the usability of the robotic hardware remains the bottleneck of the
Externí odkaz:
http://arxiv.org/abs/2008.10073
Social media conversations unfold based on complex interactions between users, topics and time. While recent models have been proposed to capture network strengths between users, users' topical preferences and temporal patterns between posting and re
Externí odkaz:
http://arxiv.org/abs/1809.04487