Zobrazeno 1 - 10
of 76
pro vyhledávání: '"Saxena, Apoorv"'
Accurately attributing answer text to its source document is crucial for developing a reliable question-answering system. However, attribution for long documents remains largely unexplored. Post-hoc attribution systems are designed to map answer text
Externí odkaz:
http://arxiv.org/abs/2409.17073
Generating presentation slides from a long document with multimodal elements such as text and images is an important task. This is time consuming and needs domain expertise if done manually. Existing approaches for generating a rich presentation from
Externí odkaz:
http://arxiv.org/abs/2406.06556
Autor:
Phukan, Anirudh, Somasundaram, Shwetha, Saxena, Apoorv, Goswami, Koustava, Srinivasan, Balaji Vasan
With the enhancement in the field of generative artificial intelligence (AI), contextual question answering has become extremely relevant. Attributing model generations to the input source document is essential to ensure trustworthiness and reliabili
Externí odkaz:
http://arxiv.org/abs/2405.17980
Autor:
Shekhar, Shivanshu, Dubey, Tanishq, Mukherjee, Koyel, Saxena, Apoorv, Tyagi, Atharv, Kotla, Nishanth
Generative AI and LLMs in particular are heavily used nowadays for various document processing tasks such as question answering and summarization. However, different LLMs come with different capabilities for different tasks as well as with different
Externí odkaz:
http://arxiv.org/abs/2402.01742
Social media advertisements are key for brand marketing, aiming to attract consumers with captivating captions and pictures or logos. While previous research has focused on generating captions for general images, incorporating brand personalities int
Externí odkaz:
http://arxiv.org/abs/2401.01637
We address the task of evidence retrieval for long document question answering, which involves locating relevant paragraphs within a document to answer a question. We aim to assess the applicability of large language models (LLMs) in the task of zero
Externí odkaz:
http://arxiv.org/abs/2311.13565
Autor:
Agarwal, Aishwarya, Karanam, Srikrishna, Joseph, K J, Saxena, Apoorv, Goswami, Koustava, Srinivasan, Balaji Vasan
While recent developments in text-to-image generative models have led to a suite of high-performing methods capable of producing creative imagery from free-form text, there are several limitations. By analyzing the cross-attention representations of
Externí odkaz:
http://arxiv.org/abs/2306.14544
We propose KGT5-context, a simple sequence-to-sequence model for link prediction (LP) in knowledge graphs (KG). Our work expands on KGT5, a recent LP model that exploits textual features of the KG, has small model size, and is scalable. To reach good
Externí odkaz:
http://arxiv.org/abs/2305.13059
TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs
Autor:
Sharma, Aditya, Saxena, Apoorv, Gupta, Chitrank, Kazemi, Seyed Mehran, Talukdar, Partha, Chakrabarti, Soumen
Publikováno v:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023) pages 2049 to 2060
Recent years have witnessed much interest in temporal reasoning over knowledge graphs (KG) for complex question answering (QA), but there remains a substantial gap in human capabilities. We explore how to generalize relational graph convolutional net
Externí odkaz:
http://arxiv.org/abs/2210.06281
Knowledge graph embedding (KGE) models represent each entity and relation of a knowledge graph (KG) with low-dimensional embedding vectors. These methods have recently been applied to KG link prediction and question answering over incomplete KGs (KGQ
Externí odkaz:
http://arxiv.org/abs/2203.10321