Akash Kumar Mohankumar
YOU?
Author Swipe
Conceptual Framework for Panoramic Progress: Nep 2020 Open
Education is the process where every individual learns the things according their ability and interest because every kid has their panoramic own unique quality like strength, humanality, inner talent and ability. For this unique quality we…
View article: Improving Retrieval in Sponsored Search by Leveraging Query Context Signals
Improving Retrieval in Sponsored Search by Leveraging Query Context Signals Open
Accurately retrieving relevant bid keywords for user queries is critical in Sponsored Search but remains challenging, particularly for short, ambiguous queries. Existing dense and generative retrieval models often fail to capture nuanced u…
Scaling the Vocabulary of Non-autoregressive Models for Efficient Generative Retrieval Open
Generative Retrieval introduces a new approach to Information Retrieval by reframing it as a constrained generation task, leveraging recent advancements in Autoregressive (AR) language models. However, AR-based Generative Retrieval methods…
AIR QUALITY MODELING FOR RITHALA METRO TO MADHUBAN CHOWK, DELHI USING CALINE4 Open
Traffic emissions remain the predominant source of urban air pollution.Despite the introduction of new technologies to regulate pollution levels, the increasing number of vehicles, especially in congested urban areas, continues to cause hi…
Unified Generative & Dense Retrieval for Query Rewriting in Sponsored Search Open
Sponsored search is a key revenue source for search engines, where advertisers bid on keywords to target users or search queries of interest. However, finding relevant keywords for a given query is challenging due to the large and dynamic …
Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons Open
Recent studies have shown the advantages of evaluating NLG systems using pairwise comparisons as opposed to direct assessment. Given $k$ systems, a naive approach for identifying the top-ranked system would be to uniformly obtain pairwise …
A Survey of Evaluation Metrics Used for NLG Systems Open
In the last few years, a large number of automatic evaluation metrics have been proposed for evaluating Natural Language Generation (NLG) systems. The rapid development and adoption of such automatic evaluation metrics in a relatively shor…
Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons Open
Recent studies have shown the advantages of evaluating NLG systems using pairwise comparisons as opposed to direct assessment. Given k systems, a naive approach for identifying the top-ranked system would be to uniformly obtain pairwise co…
Diversity driven Query Rewriting in Search Advertising Open
Retrieving keywords (bidwords) with the same intent as query, referred to as close variant keywords, is of prime importance for effective targeted search advertising. For head and torso search queries, sponsored search engines use a huge r…
Improving Dialog Evaluation with a Multi-reference Adversarial Dataset and Large Scale Pretraining Open
There is an increasing focus on model-based dialog evaluation metrics such as ADEM, RUBER, and the more recent BERT-based metrics. These models aim to assign a high score to all relevant responses and a low score to all irrelevant response…
Towards Transparent and Explainable Attention Models Open
Recent studies on interpretability of attention distributions have led to notions of faithful and plausible explanations for a model's predictions. Attention distributions can be considered a faithful explanation if a higher attention weig…
Let's Ask Again: Refine Network for Automatic Question Generation Open
In this work, we focus on the task of Automatic Question Generation (AQG) where given a passage and an answer the task is to generate the corresponding question. It is desired that the generated question should be (i) grammatically correct…
Let’s Ask Again: Refine Network for Automatic Question Generation Open
Preksha Nema, Akash Kumar Mohankumar, Mitesh M. Khapra, Balaji Vasan Srinivasan, Balaraman Ravindran. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natu…