Zobrazeno 1 - 10
of 66
pro vyhledávání: '"Ghosh, Debanjan"'
Autor:
Ghosh, Debanjan, Chan, Sophia
We present \llinstruct: An 8B instruction-tuned model that is designed to generate content for English Language Proficiency Assessments (ELPA) and related applications. Our work involves creating a new dataset of 70K instructions and explanations in
Externí odkaz:
http://arxiv.org/abs/2410.09314
Autor:
Stowe, Kevin, Longwill, Benny, Francis, Alyssa, Aoyama, Tatsuya, Ghosh, Debanjan, Somasundaran, Swapna
Natural language generation tools are powerful and effective for generating content. However, language models are known to display bias and fairness issues, making them impractical to deploy for many use cases. We here focus on how fairness issues im
Externí odkaz:
http://arxiv.org/abs/2404.15104
Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to further improv
Externí odkaz:
http://arxiv.org/abs/2305.02239
Autor:
Ghosh, Debanjan
The focus of this thesis is on building models by utilizing process information: from data, from our knowledge of physics, or both. The closer the model approximates reality, the better is the expected performance in forecasting, soft-sensing, proces
Externí odkaz:
http://hdl.handle.net/11375/27710
This work aims to employ natural language generation (NLG) to rapidly generate items for English language learning applications: this requires both language models capable of generating fluent, high-quality English, and to control the output of the g
Externí odkaz:
http://arxiv.org/abs/2211.15731
We describe the AGReE system, which takes user-submitted passages as input and automatically generates grammar practice exercises that can be completed while reading. Multiple-choice practice items are generated for a variety of different grammar con
Externí odkaz:
http://arxiv.org/abs/2210.16302
Figurative language understanding has been recently framed as a recognizing textual entailment (RTE) task (a.k.a. natural language inference, or NLI). However, similar to classical RTE/NLI datasets, the current benchmarks suffer from spurious correla
Externí odkaz:
http://arxiv.org/abs/2205.12404
We propose a type-controlled framework for inquisitive question generation. We annotate an inquisitive question dataset with question types, train question type classifiers, and finetune models for type-controlled question generation. Empirical resul
Externí odkaz:
http://arxiv.org/abs/2205.08056
We introduce a collection of recognizing textual entailment (RTE) datasets focused on figurative language. We leverage five existing datasets annotated for a variety of figurative language -- simile, metaphor, and irony -- and frame them into over 12
Externí odkaz:
http://arxiv.org/abs/2106.01195
Autor:
Alhindi, Tariq, Ghosh, Debanjan
Argument mining is often addressed by a pipeline method where segmentation of text into argumentative units is conducted first and proceeded by an argument component identification task. In this research, we apply a token-level classification to iden
Externí odkaz:
http://arxiv.org/abs/2103.04518