no code implementations • 1 Feb 2024 • Jishnu Ray Chowdhury, Cornelia Caragea
In this paper, we study the inductive biases of two major approaches to augmenting Transformers with a recurrent mechanism - (1) the approach of incorporating a depth-wise recurrence similar to Universal Transformers; and (2) the approach of incorporating a chunk-wise temporal recurrence like Temporal Latent Bottleneck.
1 code implementation • 31 May 2023 • Jishnu Ray Chowdhury, Cornelia Caragea
We explore different ways to utilize position-based cross-attention in seq2seq networks to enable length generalization in algorithmic tasks.
1 code implementation • 31 May 2023 • Jishnu Ray Chowdhury, Cornelia Caragea
We propose Beam Tree Recursive Cell (BT-Cell) - a backpropagation-friendly framework to extend Recursive Neural Networks (RvNNs) with beam search for latent structure induction.
1 code implementation • 29 May 2023 • Krishna Garg, Jishnu Ray Chowdhury, Cornelia Caragea
Very few works address the problem of keyphrase generation in low-resource settings, but they still rely on a lot of additional unlabeled data for pretraining and on automatic methods for pseudo-annotations.
no code implementations • 27 Apr 2023 • Tuhin Kundu, Jishnu Ray Chowdhury, Cornelia Caragea
Keyphrase generation aims at generating topical phrases from a given text either by copying from the original text (present keyphrases) or by producing new keyphrases (absent keyphrases) that capture the semantic meaning of the text.
1 code implementation • 9 Mar 2022 • Jishnu Ray Chowdhury, Debanjan Mahata, Cornelia Caragea
Second, we compare different strategies to utilize a pre-trained seq2seq model to generate and select a set of questions related to a given paragraph.
no code implementations • 1 Feb 2022 • Jishnu Ray Chowdhury, Yong Zhuang, Shuyi Wang
Paraphrase generation is a fundamental and long-standing task in natural language processing.
1 code implementation • 13 Dec 2021 • Krishna Garg, Jishnu Ray Chowdhury, Cornelia Caragea
Unlike prior large-scale datasets, FullTextKP includes the full text of the articles along with the title and abstract.
1 code implementation • 2 Dec 2021 • Jishnu Ray Chowdhury, Seoyeon Park, Tuhin Kundu, Cornelia Caragea
Keyphrase generation is the task of generating phrases (keyphrases) that summarize the main topics of a given document.
1 code implementation • 10 Jun 2021 • Jishnu Ray Chowdhury, Cornelia Caragea
We also show that CRvNN performs comparably or better than prior latent structure models on real-world tasks such as sentiment analysis and natural language inference.
1 code implementation • ACL 2020 • Jishnu Ray Chowdhury, Cornelia Caragea, Doina Caragea
Distinguishing informative and actionable messages from a social media platform like Twitter is critical for facilitating disaster management.
1 code implementation • 5 Jan 2020 • Jishnu Ray Chowdhury, Cornelia Caragea, Doina Caragea
Moreover, only a small number of tweets that contain actionable hashtags are useful for disaster response.
no code implementations • 17 Oct 2019 • Jishnu Ray Chowdhury, Cornelia Caragea, Doina Caragea
Previously, joint training of two different layers of a stacked Recurrent Neural Network for keyword discovery and keyphrase extraction had been shown to be effective in extracting keyphrases from general Twitter data.