Search Results - "Lai, Huiyuan"

Bi-directional attention comparison for semantic sentence matching by Lai, Huiyuan, Tao, Yizheng, Wang, Chunliu, Xu, Lunfan, Tang, Dingyong, Li, Gongliang

“…Semantic sentence matching, also known as calculation of text similarity, is one of the most important problems in natural language processing. Existing deep…”
Get full text

A text style transfer system for reducing the physician–patient expertise gap: An analysis with automatic and human evaluations by Bacco, Luca, Dell’Orletta, Felice, Lai, Huiyuan, Merone, Mario, Nissim, Malvina

“…Physicians and patients often come from different backgrounds and have varying levels of education, which can result in communication difficulties in the…”
Get full text

Preliminary characterization of the thickness of bulk MoS2 layer by the colour by Zeng, Jianhua, Lai, Huiyuan, Tu, Qiu

“…We propose a method to preliminarily determine the thicknesses of bulk MoS2 layers based on their colours. The reflectance spectra of thin-layer and bulk MoS2…”
Get full text

mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models by Lai, Huiyuan, Nissim, Malvina

“…Large language models (LLMs) with Chain-of-thought (CoT) have recently emerged as a powerful technique for eliciting reasoning to improve various downstream…”
Get full text

Multi-Figurative Language Generation by Lai, Huiyuan, Nissim, Malvina

“…Figurative language generation is the task of reformulating a given text in the desired figure of speech while still being faithful to the original context. We…”
Get full text

Multilingual Multi-Figurative Language Detection by Lai, Huiyuan, Toral, Antonio, Nissim, Malvina

“…Figures of speech help people express abstract concepts and evoke stronger emotions than literal expressions, thereby making texts more creative and engaging…”
Get full text

Multidimensional Evaluation for Text Style Transfer Using ChatGPT by Lai, Huiyuan, Toral, Antonio, Nissim, Malvina

“…We investigate the potential of ChatGPT as a multidimensional evaluator for the task of \emph{Text Style Transfer}, alongside, and in comparison to, existing…”
Get full text

Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation by Ploeger, Esther, Lai, Huiyuan, van Noord, Rik, Toral, Antonio

“…Machine translations are found to be lexically poorer than human translations. The loss of lexical diversity through MT poses an issue in the automatic…”
Get full text

Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer by Lai, Huiyuan, Toral, Antonio, Nissim, Malvina

“…We exploit the pre-trained seq2seq model mBART for multilingual text style transfer. Using machine translated data as well as gold aligned English sentences…”
Get full text

Responsibility Perspective Transfer for Italian Femicide News by Minnema, Gosse, Lai, Huiyuan, Muscato, Benedetta, Nissim, Malvina

“…Different ways of linguistically expressing the same real-world event can lead to different perceptions of what happened. Previous work has shown that…”
Get full text

Pre-Trained Language-Meaning Models for Multilingual Parsing and Generation by Wang, Chunliu, Lai, Huiyuan, Nissim, Malvina, Bos, Johan

“…Pre-trained language models (PLMs) have achieved great success in NLP and have recently been used for tasks in computational semantics. However, these tasks do…”
Get full text

Generic resources are what you need: Style transfer tasks without task-specific parallel training data by Lai, Huiyuan, Toral, Antonio, Nissim, Malvina

“…Style transfer aims to rewrite a source text in a different target style while preserving its content. We propose a novel approach to this task that leverages…”
Get full text

Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer by Lai, Huiyuan, Toral, Antonio, Nissim, Malvina

“…Scarcity of parallel data causes formality style transfer models to have scarce success in preserving content. We show that fine-tuning pre-trained language…”
Get full text

Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models by Occhipinti, Daniela, Marchi, Michele, Mondella, Irene, Lai, Huiyuan, Dell'Orletta, Felice, Nissim, Malvina, Guerini, Marco

“…Automatic methods for generating and gathering linguistic data have proven effective for fine-tuning Language Models (LMs) in languages less resourced than…”
Get full text

Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer by Lai, Huiyuan, Mao, Jiali, Toral, Antonio, Nissim, Malvina

“…Although text style transfer has witnessed rapid development in recent years, there is as yet no established standard for evaluation, which is performed using…”
Get full text

On the interaction of automatic evaluation and task framing in headline style transfer by De Mattei, Lorenzo, Cafagna, Michele, Lai, Huiyuan, Dell'Orletta, Felice, Nissim, Malvina, Gatt, Albert

“…An ongoing debate in the NLG community concerns the best way to evaluate systems, with human evaluation often being considered the most reliable method,…”
Get full text

Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP by Belz, Anya, Thomson, Craig, Reiter, Ehud, Abercrombie, Gavin, Alonso-Moral, Jose M, Arvan, Mohammad, Braggaar, Anouck, Cieliebak, Mark, Clark, Elizabeth, van Deemter, Kees, Dinkar, Tanvi, Dušek, Ondřej, Eger, Steffen, Fang, Qixiang, Gao, Mingqi, Gatt, Albert, Gkatzia, Dimitra, González-Corbelle, Javier, Hovy, Dirk, Hürlimann, Manuela, Ito, Takumi, Kelleher, John D, Klubicka, Filip, Krahmer, Emiel, Lai, Huiyuan, van der Lee, Chris, Li, Yiru, Mahamood, Saad, Mieskes, Margot, van Miltenburg, Emiel, Mosteiro, Pablo, Nissim, Malvina, Parde, Natalie, Plátek, Ondřej, Rieser, Verena, Ruan, Jie, Tetreault, Joel, Toral, Antonio, Wan, Xiaojun, Wanner, Leo, Watson, Lewis, Yang, Diyi

“…We report our efforts in identifying a set of previous human evaluations in NLP that would be suitable for a coordinated study examining what makes human…”
Get full text