Papers by Antonio Toral
Dr. Livingstone, I presume? Polishing of foreign character identification in literary texts (2022.naacl-srw)
Copied to clipboard
| Challenge: | Current state-of-the-art models that use neural networks can help with character identification in agglutinative languages. |
| Approach: | They propose to use a search for the shortest version of the name to identify the baseform of the character's lemma to align different appearances of the same character in the narrative. |
| Outcome: | The proposed method is the easiest, best performing and resource-independent method. |
DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in neural language modeling and multilingual training have prompted widespread adoption of machine translation (MT) technologies across an unprecedented range of world languages. |
| Approach: | They propose to use a dataset to assess the impact of two state-of-the-art NMT systems, Google Translate and the multilingual mBART-50 model, on translation productivity. |
| Outcome: | The proposed model is faster than translation from scratch, but the magnitude of productivity gains varies widely across systems and languages. |
Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer (2022.acl-short)
Copied to clipboard
| Challenge: | Text style transfer is a text generation task where a given sentence must be rewritten changing its style while preserving its meaning. |
| Approach: | They propose a modular approach for multilingual formality transfer using machine translated data and gold aligned English sentences. |
| Outcome: | The proposed approach achieves competitive performance without monolingual task-specific parallel data and can be applied to other style transfer tasks as well as to other languages. |
Quality Beyond A Glance: Revealing Large Quality Differences Between Web-Crawled Parallel Corpora (2025.coling-main)
Copied to clipboard
| Challenge: | Parallel corpora play a vital role in advanced multilingual natural language processing tasks, notably in machine translation (MT). |
| Approach: | They manually and automatically evaluated four well-known publicly available parallel corpora across eleven language pairs. |
| Outcome: | The results show that the four well-known parallel corpora have a substantial amount of noisy sentence pairs, while CCMatrix and CCAligned have low quality sentences. |
Character-level Representations Improve DRS-based Semantic Parsing Even in the Age of BERT (2020.emnlp-main)
Copied to clipboard
| Challenge: | a new method of analysis based on semantic tags demonstrates that character-level representations improve performance across a subset of selected semantic phenomena. |
| Approach: | They combine character-level and contextual language model representations to improve performance on Discourse Representation Structure parsing. |
| Outcome: | The proposed model improves performance on a subset of selected semantic phenomena. |
Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer (2021.acl-short)
Copied to clipboard
| Challenge: | Formality style transfer models have limited success in preserving content due to the scarcity of parallel data. |
| Approach: | They propose to fine-tune pre-trained language and sequence-to-sequence models with rewards that target style and content to enhance content preservation. |
| Outcome: | The proposed models can be fine-tuned with rewards that target style and content, and achieve good performance even with limited amounts of parallel data. |
Generic resources are what you need: Style transfer tasks without task-specific parallel training data (2021.emnlp-main)
Copied to clipboard
| Challenge: | Text style transfer is a task aimed at converting a text of one style into another while preserving its content. |
| Approach: | They propose a multi-step procedure which builds on a generic pre-trained sequence-to-sequence model and an iterative back-translation approach to train two models in a transfer direction. |
| Outcome: | The proposed method outperforms existing unsupervised approaches on the two most popular style transfer tasks: formality transfer and polarity swap. |
Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation (2025.acl-long)
Copied to clipboard
| Challenge: | Neural machine translation systems amplify lexical biases, rendering outputs artificially impoverished . Attempts to increase naturalness in NMT can fall short in terms of content preservation . |
| Approach: | They propose a method that rewards both naturalness and content preservation . they use multiple perspectives to produce more natural translations . |
| Outcome: | The proposed method produces translations that are lexically richer and exhibit more properties of human-written language without loss in translation accuracy. |
Multilingual Multi-Figurative Language Detection (2023.findings-acl)
Copied to clipboard
| Challenge: | Figures of speech help people express abstract concepts and emotions, but it's understudied in a multilingual setting and when considering more than one figure of speech at the same time. |
| Approach: | They propose a framework for sentence-level figurative language detection based on template-based prompt learning and use it to unify multiple detection tasks that are interrelated across multiple figures of speech and languages. |
| Outcome: | The proposed framework outperforms baselines and may serve as blueprint for the joint modelling of other interrelated tasks. |
From Shortcuts to Balance: Attribution Analysis of Speech-Text Feature Utilization in Distinguishing Original from Machine-Translated Texts (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent work demonstrated strong performance in distinguishing machine-translated text from human-authored or human-transcribed content using pretrained language models. |
| Approach: | They find that bimodal integration reduces reliance on NEs while moderating overemphasis attribution patterns in speech features. |
| Outcome: | The proposed models show that they are more balanced while relying less on NEs. |
Do Language Models Care about Text Quality? Evaluating Web-Crawled Corpora across 11 Languages (2024.lrec-main)
Copied to clipboard
Rik van Noord, Taja Kuzman, Peter Rupnik, Nikola Ljubešić, Miquel Esplà-Gomis, Gema Ramírez-Sánchez, Antonio Toral
| Challenge: | Large, curated, web-crawled corpora play a vital role in training language models . however, relatively little attention has been given to the quality of these corporata . |
| Approach: | They compare four of the currently most relevant large, web-crawled corpora across eleven lower-resourced European languages to evaluate their quality. |
| Outcome: | The CC100 corpus achieves the highest scores on the tests in 11 lower-resourced European languages. |
Subword-Delimited Downsampling for Better Character-Level Translation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Subword-level models are expensive in terms of time and computation, but character-level model with downsampling component can be used for machine translation. |
| Approach: | They propose a character-level downsampling method which is informed by subwords to improve model performance. |
| Outcome: | The proposed method outperforms existing methods and shows that it can be done without sacrificing quality. |