Papers by Satwik Bhattamishra

7 papers
Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data Augmentation (N19-1)

Copied to clipboard

Challenge: Previous work focused on generating semantically similar paraphrases without considering diversity.
Approach: They propose a method to obtain highly diverse paraphrases without compromising on paraphrasing quality by using monotone submodular function maximization.
Outcome: The proposed method is effective on multiple tasks such as intent classification and paraphrase recognition.
MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations (2023.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have a knowledge cutoff and are costly to finetune repeatedly.
Approach: They introduce a language evaluation suite that incorporates diverse tokens and prompt settings to simulate real-world complexity.
Outcome: The proposed evaluation suite incorporates diverse tokens and prompt settings to simulate real-world complexity.
Are NLP Models really able to Solve Simple Math Word Problems? (2021.naacl-main)

Copied to clipboard

Challenge: Existing solvers for math word problems often achieve high performance on benchmark datasets . existing models rely on shallow heuristics to achieve high accuracy .
Approach: They restrict their attention to English MWPs taught in grades four and lower . they propose a challenge dataset to test the accuracy of MWp solvers .
Outcome: The proposed model can solve a large fraction of MWPs even with shallow heuristics . the proposed model is much lower on the challenge dataset SVAMP .
On the Ability and Limitations of Transformers to Recognize Formal Languages (2020.emnlp-main)

Copied to clipboard

Challenge: Existing studies on LSTMs have not revealed their ability to model syntactic properties.
Approach: They propose to build a Transformers model for a subclass of counter languages and find that their learning mechanism strongly correlates with their construction.
Outcome: The proposed model generalizes well on counter languages and its learned mechanism correlates with it.
On the Practical Ability of Recurrent Neural Networks to Recognize Hierarchical Languages (2020.coling-main)

Copied to clipboard

Challenge: recurrent models have been effective in NLP tasks but performance on context-free languages (CFLs) is weak.
Approach: They evaluate the performance of recurrent models on Dyck-n languages . they find that they are expressive enough to recognize Dyck words of arbitrary lengths if their depths are bounded.
Outcome: The proposed models generalize well on Dyck-n languages, while performing poorly on longer test strings.
Revisiting the Compositional Generalization Abilities of Neural Sequence Models (2022.acl-short)

Copied to clipboard

Challenge: Existing studies have suggested that standard seq-to-seq models lack the ability to generalize compositionally.
Approach: They propose to use one-shot primitive generalization as introduced by the popular SCAN benchmark to modify the training distribution in simple and intuitive ways to achieve near-perfect generalization performance.
Outcome: The proposed model achieves near-perfect generalization performance despite a lack of training data .
Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions (2023.acl-long)

Copied to clipboard

Challenge: Recent studies have found that Transformers struggle to model several formal languages when compared to recurrent models.
Approach: They conduct an extensive empirical study on Boolean functions to demonstrate that Transformers are relatively more biased towards functions of low sensitivity . they also show that Transformer's generalize near perfectly even in the presence of noisy labels whereas recurrent models overfit and achieve poor generalization accuracy.
Outcome: The results show that Transformers generalize near perfectly even in noisy Boolean functions whereas recurrent models overfit and achieve poor generalization accuracy.

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