Papers by Hasan Mahmud

3 papers
Math Word Problem Solving by Generating Linguistic Variants of Problem Statements (2023.acl-srw)

Copied to clipboard

Challenge: Existing models for solving Math Word Problems depend on shallow heuristics and spurious correlations to derive the solution expressions.
Approach: They propose a framework for MWP solvers based on generation of linguistic variants of problem text.
Outcome: The proposed framework improves the mathematical reasoning and robustness of the proposed model.
BanglaBook: A Large-scale Bangla Dataset for Sentiment Analysis from Book Reviews (2023.findings-acl)

Copied to clipboard

Challenge: Existing literature on Bangla Sentiment Analysis (SA) has limited data and cross-domain adaptability.
Approach: They present a large-scale dataset of Bangla book reviews with 158,065 samples . they employ a range of machine learning models to establish baselines including SVM, LSTM, and Bangla-BERT.
Outcome: The proposed model improves performance over models that rely on manual features.
“When Words Fail, Emojis Prevail”: A Novel Architecture for Generating Sarcastic Sentences With Emoji Using Valence Reversal and Semantic Incongruity (2023.acl-srw)

Copied to clipboard

Challenge: Existing sarcasm generation tasks focus on textual sarcasm, but people often use emojis to express their emotions.
Approach: They propose a novel architecture for sarcasm generation with emojis from a non-sarcastic input sentence in English.
Outcome: The proposed architecture generates sarcastic outputs with emojis from a non-sarcastic input sentence in english.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations