8 citations · 9 across the 5 of their papers we have counts for
5 papers
Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data
Parth Patwa, Simone Filice, Zhiyu Chen +3
Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks. In-Context Learning (ICL) typically achieves better…
Evaluation Metrics of Language Generation Models for Synthetic Traffic Generation Tasks
Simone Filice, Jason Ingyu Choi, Giuseppe Castellucci +2
Many Natural Language Generation (NLG) tasks aim to generate a single output text given an input prompt. Other settings require the generation of multiple texts, e.g., for Syntheti…
Faithful Low-Resource Data-to-Text Generation through Cycle Training
Zhuoer Wang, Marcus Collins, Nikhita Vedula +3
Methods to generate text from structured data have advanced significantly in recent years, primarily due to fine-tuning of pre-trained language models on large datasets. However, s…
Preventing Catastrophic Forgetting in Continual Learning of New Natural Language Tasks
Sudipta Kar, Giuseppe Castellucci, Simone Filice +2
Multi-Task Learning (MTL) is widely-accepted in Natural Language Processing as a standard technique for learning multiple related tasks in one model. Training an MTL model requires…
Global Thread-Level Inference for Comment Classification in Community Question Answering
Shafiq Joty, Alberto Barrón-Cedeño, Giovanni Da San Martino +4
Community question answering, a recent evolution of question answering in the Web context, allows a user to quickly consult the opinion of a number of people on a particular topic,…