Zobrazeno 1 - 10
of 195
pro vyhledávání: '"Chakrabarti, Soumen"'
Autor:
Saha, Amrita, Ansari, Ghulam Ahmed, Laddha, Abhishek, Sankaranarayanan, Karthik, Chakrabarti, Soumen
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 7, Pp 185-200 (2019)
Recent years have seen increasingly complex question-answering on knowledge bases (KBQA) involving logical, quantitative, and comparative reasoning over KB subgraphs. Neural Program Induction (NPI) is a pragmatic approach toward modularizing the reas
Externí odkaz:
https://doaj.org/article/3a9591e65064424ea1ed096376db075d
Large Language Models (LLMs) exhibit impressive zero/few-shot inference and generation quality for high-resource languages (HRLs). A few of them have been trained on low-resource languages (LRLs) and give decent performance. Owing to the prohibitive
Externí odkaz:
http://arxiv.org/abs/2403.05434
Autor:
Mittal, Anshul, Mohan, Shikhar, Saini, Deepak, Prabhu, Suchith C., jiao, Jain, Agarwal, Sumeet, Chakrabarti, Soumen, Kar, Purushottam, Varma, Manik
Deep extreme classification (XC) aims to train an encoder architecture and an accompanying classifier architecture to tag a data point with the most relevant subset of labels from a very large universe of labels. XC applications in ranking, recommend
Externí odkaz:
http://arxiv.org/abs/2402.18434
Despite superior reasoning prowess demonstrated by Large Language Models (LLMs) with Chain-of-Thought (CoT) prompting, a lack of understanding prevails around the internal mechanisms of the models that facilitate CoT generation. This work investigate
Externí odkaz:
http://arxiv.org/abs/2402.18312
Autor:
Dutta, Subhabrata, Singh, Joykirat, Pandey, Ishan, Manchanda, Sunny, Chakrabarti, Soumen, Chakraborty, Tanmoy
Large Language Models (LLM) exhibit zero-shot mathematical reasoning capacity as a behavior emergent with scale, commonly manifesting as chain-of-thoughts (CoT) reasoning. However, multiple empirical findings suggest that this prowess is exclusive to
Externí odkaz:
http://arxiv.org/abs/2312.05571
End-to-end conversational recommendation systems (CRS) generate responses by leveraging both dialog history and a knowledge base (KB). A CRS mainly faces three key challenges: (1) at each turn, it must decide if recommending a KB entity is appropriat
Externí odkaz:
http://arxiv.org/abs/2311.08511
Existing Text-to-SQL generators require the entire schema to be encoded with the user text. This is expensive or impractical for large databases with tens of thousands of columns. Standard dense retrieval techniques are inadequate for schema subsetti
Externí odkaz:
http://arxiv.org/abs/2311.01173
Autor:
Juneja, Gurusha, Dutta, Subhabrata, Chakrabarti, Soumen, Manchanda, Sunny, Chakraborty, Tanmoy
Large Language Models (LLMs) prompted to generate chain-of-thought (CoT) exhibit impressive reasoning capabilities. Recent attempts at prompt decomposition toward solving complex, multi-step reasoning problems depend on the ability of the LLM to simu
Externí odkaz:
http://arxiv.org/abs/2310.18338
Inference-time adaptation methods for semantic parsing are useful for leveraging examples from newly-observed domains without repeated fine-tuning. Existing approaches typically bias the decoder by simply concatenating input-output example pairs (cas
Externí odkaz:
http://arxiv.org/abs/2301.04110
Automated completion of open knowledge bases (Open KBs), which are constructed from triples of the form (subject phrase, relation phrase, object phrase), obtained via open information extraction (Open IE) system, are useful for discovering novel fact
Externí odkaz:
http://arxiv.org/abs/2211.06959