Huiyuan Lai
YOU?
Author Swipe
View article: Multidimensional Consistency Improves Reasoning in Language Models
Multidimensional Consistency Improves Reasoning in Language Models Open
While Large language models (LLMs) have proved able to address some complex reasoning tasks, we also know that they are highly sensitive to input variation, which can lead to different solution paths and final answers. Answer consistency a…
View article: Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation
Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation Open
View article: Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation
Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation Open
Neural machine translation (NMT) systems amplify lexical biases present in their training data, leading to artificially impoverished language in output translations. These language-level characteristics render automatic translations differ…
View article: ContraMAE: Contrastive alignment masked autoencoder framework for cancer survival prediction
ContraMAE: Contrastive alignment masked autoencoder framework for cancer survival prediction Open
With the rapid advancement in multimodal fusion technology, the integration of pathological images with genomics data has achieved promising results in cancer survival prediction. However, most existing multimodal models are not pre-traine…
View article: Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation
Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation Open
Machine translations are found to be lexically poorer than human translations. The loss of lexical diversity through MT poses an issue in the automatic translation of literature, where it matters not only what is written, but also how it i…
View article: Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models
Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models Open
Automatic methods for generating and gathering linguistic data have proven effective for fine-tuning Language Models (LMs) in languages less resourced than English. Still, while there has been emphasis on data quantity, less attention has …
View article: mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models
mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models Open
Large language models (LLMs) with Chain-of-thought (CoT) have recently emerged as a powerful technique for eliciting reasoning to improve various downstream tasks. As most research mainly focuses on English, with few explorations in a mult…
View article: A Survey on Automatic Generation of Figurative Language: From Rule-based Systems to Large Language Models
A Survey on Automatic Generation of Figurative Language: From Rule-based Systems to Large Language Models Open
Figurative language generation (FLG) is the task of reformulating a given text to include a desired figure of speech, such as a hyperbole, a simile, and several others, while still being faithful to the original context. This is a fundamen…
View article: Neural Text Rewriting: Style Transfer, Figurative Language, and Beyond
Neural Text Rewriting: Style Transfer, Figurative Language, and Beyond Open
Neural networks have yielded great breakthroughs in NLP in recent years, but the vast majority of research has focused on literal language, while modelling text attributes, or style has received less attention. In this thesis, we focus on …
View article: mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models
mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models Open
Large language models (LLMs) with Chain-of-thought (CoT) have recently emerged as a powerful technique for eliciting reasoning to improve various downstream tasks. As most research mainly focuses on English, with few explorations in a mult…
View article: Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models
Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models Open
Automatic methods for generating and gathering linguistic data have proven effective for fine-tuning Language Models (LMs) in languages less resourced than English. Still, while there has been emphasis on data quantity, less attention has …
View article: A text style transfer system for reducing the physician–patient expertise gap: An analysis with automatic and human evaluations
A text style transfer system for reducing the physician–patient expertise gap: An analysis with automatic and human evaluations Open
View article: Responsibility Perspective Transfer for Italian Femicide News
Responsibility Perspective Transfer for Italian Femicide News Open
Different ways of linguistically expressing the same real-world event can lead to different perceptions of what happened. Previous work has shown that different descriptions of gender-based violence (GBV) influence the reader's perception …
View article: Multilingual Multi-Figurative Language Detection
Multilingual Multi-Figurative Language Detection Open
Figures of speech help people express abstract concepts and evoke stronger emotions than literal expressions, thereby making texts more creative and engaging. Due to its pervasive and fundamental character, figurative language understandin…
View article: Pre-Trained Language-Meaning Models for Multilingual Parsing and Generation
Pre-Trained Language-Meaning Models for Multilingual Parsing and Generation Open
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 not fully benefit from PLMs since meaning representations are not explicitly in…
View article: Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP
Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP Open
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 evaluations in NLP more/less reproducible. We present our results and findings, which…
View article: Multidimensional Evaluation for Text Style Transfer Using ChatGPT
Multidimensional Evaluation for Text Style Transfer Using ChatGPT Open
We investigate the potential of ChatGPT as a multidimensional evaluator for the task of \emph{Text Style Transfer}, alongside, and in comparison to, existing automatic metrics as well as human judgements. We focus on a zero-shot setting, i…
View article: Responsibility Perspective Transfer for Italian Femicide News
Responsibility Perspective Transfer for Italian Femicide News Open
Different ways of linguistically expressing the same real-world event can lead to different perceptions of what happened. Previous work has shown that different descriptions of gender-based violence (GBV) influence the reader's perception …
View article: Multilingual Multi-Figurative Language Detection
Multilingual Multi-Figurative Language Detection Open
Figures of speech help people express abstract concepts and evoke stronger emotions than literal expressions, thereby making texts more creative and engaging. Due to its pervasive and fundamental character, figurative language understandin…
View article: Pre-Trained Language-Meaning Models for Multilingual Parsing and Generation
Pre-Trained Language-Meaning Models for Multilingual Parsing and Generation Open
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 not fully benefit from PLMs since meaning representations are not explicitly in…
View article: Multi-Figurative Language Generation
Multi-Figurative Language Generation Open
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 take the first step towards multi-figurative language modelling by providing a …
View article: Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer
Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer Open
Although text style transfer has witnessed rapid development in recent years, there is as yet no established standard for evaluation, which is performed using several automatic metrics, lacking the possibility of always resorting to human …
View article: Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer
Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer Open
We exploit the pre-trained seq2seq model mBART for multilingual text style transfer. Using machine translated data as well as gold aligned English sentences yields state-of-the-art results in the three target languages we consider. Besides…
View article: Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer
Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer Open
We exploit the pre-trained seq2seq model mBART for multilingual text style transfer. Using machine translated data as well as gold aligned English sentences yields state-of-the-art results in the three target languages we consider. Besides…
View article: Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer
Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer Open
Although text style transfer has witnessed rapid development in recent years, there is as yet no established standard for evaluation, which is performed using several automatic metrics, lacking the possibility of always resorting to human …
View article: Generic resources are what you need: Style transfer tasks without task-specific parallel training data
Generic resources are what you need: Style transfer tasks without task-specific parallel training data Open
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 generic resources, and without using any task-specific parallel (source-target) …
View article: Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer
Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer Open
Scarcity of parallel data causes formality style transfer models to have scarce success in preserving content. We show that fine-tuning pre-trained language (GPT-2) and sequence-to-sequence (BART) models boosts content preservation, and th…
View article: On the interaction of automatic evaluation and task framing in headline style transfer
On the interaction of automatic evaluation and task framing in headline style transfer Open
An ongoing debate in the NLG community concerns the best way to evaluate systems, with human evaluation often being considered the most reliable method, compared to corpus-based metrics. However, tasks involving subtle textual differences,…
View article: Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer
Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer Open
Scarcity of parallel data causes formality style transfer models to have scarce success in preserving content. We show that fine-tuning pre-trained language (GPT-2) and sequence-to-sequence (BART) models boosts content preservation, and th…
View article: Generic resources are what you need: Style transfer tasks without task-specific parallel training data
Generic resources are what you need: Style transfer tasks without task-specific parallel training data Open
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 generic resources, and without using any task-specific parallel (source–target) …