Search Results for author:
Found 9 papers, 1 papers with code
Graph Expansion in Pruned Recurrent Neural Network Layers Preserve Performance
We prune recurrent networks such as RNNs and LSTMs, maintaining a large spectral gap of the underlying graphs and ensuring their layerwise expansion properties.
Revisiting the Lottery Ticket Hypothesis: A Ramanujan Graph Perspective
Subsequently, with the loss of Ramanujan graph property, accuracy begins to reduce sharply.
On non-surjective word maps on $\mathrm{PSL}_{2}(\mathbb{F}_{q})$
Jambor--Liebeck--O'Brien showed that there exist non-proper-power word maps which are not surjective on $\mathrm{PSL}_{2}(\mathbb{F}_{q})$ for infinitely many $q$.
Group Theory Number Theory 20D05, 16R30
Summarizing User-generated Textual Content: Motivation and Methods for Fairness in Algorithmic Summaries
Specifically, considering that an extractive summarization algorithm selects a subset of the textual units (e. g. microblogs) in the original data for inclusion in the summary, we investigate whether this selection is fair or not.
Sentiment Analysis of Tweets in Three Indian Languages
In this paper, we describe the results of sentiment analysis on tweets in three Indian languages {--} Bengali, Hindi, and Tamil.
A Supervised Authorship Attribution Framework for Bengali Language
Authorship Attribution is a long-standing problem in Natural Language Processing.
A New Bengali Readability Score
In this paper we have proposed methods to analyze the readability of Bengali language texts.
Inter-Rater Agreement Study on Readability Assessment in Bengali
An inter-rater agreement study is performed for readability assessment in Bengali.
