Papers by Jugal Kalita
Genre Identification and the Compositional Effect of Genre in Literature (C18-1)
Copied to clipboard
| Challenge: | Literature is artistic and conveys complex themes over the course of very long narratives. |
| Approach: | They propose a method which can work with large literary corpus of texts . they propose 'gutenberg' dataset to perform Genre Identification . |
| Outcome: | The proposed methods improve results in a literature-based task with 200,000 words of literature . the Gutenberg dataset is used to model literary classifications with a high level of fidelity . |
Abstractive Text Summarization Using the BRIO Training Paradigm (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing abstractive summarization models rely heavily on reference summaries and lack control over their performance. |
| Approach: | They propose a BRIO paradigm to reduce the dependence on reference summaries by fine-tuning pre-trained language models and training them with the paradigm. |
| Outcome: | The proposed paradigm outperforms existing models on Vietnamese and CNNDM datasets while maintaining the main content of the original text. |
The Less the Merrier? Investigating Language Representation in Multilingual Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Multilingual models can be used to integrate multiple languages into one model and use cross-language transfer learning to improve performance for different NLP tasks. |
| Approach: | They propose to include languages in popular multilingual models and to use cross-language transfer learning to improve performance for different NLP tasks. |
| Outcome: | The proposed models perform better on downstream tasks for seen and unseen languages than community-centered models for low-resource languages. |
Linear Relational Decoding of Morphology in Language Models (2025.naacl-srw)
Copied to clipboard
| Challenge: | Recent work has shown that affine transformations on subject representations can faithfully approximate model outputs for certain subject-object relations. |
| Approach: | They propose to use affine transformations to adapt the Bigger Analogy Test Set to test faithfulness of morphological relations. |
| Outcome: | The proposed method achieves 90% faithfulness on morphological relations, with similar findings across languages and models. |
Training-free Neural Architecture Search for RNNs and Transformers (2023.acl-long)
Copied to clipboard
| Challenge: | Neural architecture search (NAS) has allowed for the automatic creation of new and effective neural network architectures. |
| Approach: | They develop a new NAS metric that predicts the trained performance of an RNN architecture and significantly outperforms existing NAS metrics. |
| Outcome: | The proposed metric outperforms existing training-free metrics on the NAS-Bench-NLP benchmark. |
Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method (2024.eacl-short)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) generate nonfacts and deviate from desired criteria for text generation. |
| Approach: | They propose a controlled text generation algorithm that enforces adherence toward specific rhetorical relations in an LLM sentence-completion context by a parser-driven decoding scheme. |
| Outcome: | The proposed method generates sentences that satisfy desired rhetorical relations in an LLM. |