4 papers
Multimodal Multihop Source Retrieval for Web Question Answering
Navya Yarrabelly, Saloni Mittal
This work deals with the challenge of learning and reasoning over multi-modal multi-hop question answering (QA). We propose a graph reasoning network based on the semantic structur…
Multilingual Open QA on the MIA Shared Task
Navya Yarrabelly, Saloni Mittal, Ketan Todi +1
Cross-lingual information retrieval (CLIR) ~\cite{shi2021cross, asai2021one, jiang2020cross} for example, can find relevant text in any language such as English(high resource) or T…
Mitigating Gender Bias in Contextual Word Embeddings
Navya Yarrabelly, Vinay Damodaran, Feng-Guang Su
Word embeddings have been shown to produce remarkable results in tackling a vast majority of NLP related tasks. Unfortunately, word embeddings also capture the stereotypical biases…
Rich-Item Recommendations for Rich-Users: Exploiting Dynamic and Static Side Information
Amar Budhiraja, Gaurush Hiranandani, Darshak Chhatbar +5
In this paper, we study the problem of recommendation system where the users and items to be recommended are rich data structures with multiple entity types and with multiple sourc…