Papers by Thiago Castro Ferreira
Referring to what you know and do not know: Making Referring Expression Generation Models Generalize To Unseen Entities (2020.coling-main)
Copied to clipboard
| Challenge: | Data-to-text Natural Language Generation (NLG) is a computational process of generating natural language from non-linguistic data. |
| Approach: | They propose two extensions to a state-of-the-art encoder-decoder REG model that generates referring expressions to unseen entities. |
| Outcome: | The proposed model generates more meaningful referring expressions to unseen entities than the original system and related work. |
Surface Realization Shared Task 2019 (MSR19): The Team 6 Approach (D19-63)
Copied to clipboard
| Challenge: | This paper describes the approach developed by the Tilburg University team for the shallow track of the Multilingual Surface Realization Shared Task 2019 (SR'19). |
| Approach: | They propose a method for the shallow track of the Multilingual Surface Realization Shared Task 2019 using a rule-based and a statistical machine translation (SMT) model. |
| Outcome: | The proposed approach can generate texts in 11 languages, compared with the submission of the same approach for the same task in 2018 which only covered 6 languages. |
A Persona-Based Corpus in the Diabetes Self-Care Domain - Applying a Human-Centered Approach to a Low-Resource Context (2024.lrec-main)
Copied to clipboard
| Challenge: | Human-centered design (HCD) is a new approach to natural language processing that uses personas, user profiles and other tools to build corpus. |
| Approach: | They propose to use personas to model interpersonal interaction in a healthcare domain to follow an HCD approach. |
| Outcome: | The proposed model improves the quality of human-centered design in a healthcare domain and overcomes the lack of in-depth human-centricity in the field. |
Neural data-to-text generation: A comparison between pipeline and end-to-end architectures (D19-1)
Copied to clipboard
| Challenge: | Traditionally, data-to-text applications have been designed using a modular pipeline architecture, in which the non-linguistic input data is converted into natural language through several intermediate transformations. |
| Approach: | They propose to use Gated-Recurrent Units and Transformer to implement neural pipelines for data-to-text generation. |
| Outcome: | The proposed models generalize better to unseen inputs and have better performance than the existing pipeline architectures. |
Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines (2025.acl-demo)
Copied to clipboard
| Challenge: | a single AI model is often insufficient for complex tasks, requiring integration of multiple models into pipelines . a conversational agent can build pipelines composed of diverse AI models based on user requirements . |
| Approach: | They propose a conversational agent that constructs AI model pipelines based on user requirements. |
| Outcome: | The proposed agent can build AI model pipelines from human-curated and synthetic data. |
Generating Questions from Wikidata Triples (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for question generation from knowledge bases rely on extensive pre- and post-processing of the input triple. |
| Approach: | They revisit KBQG using pre training, a new (triple, question) dataset and taking question type into account and provide a more extended KBqg dataset. |
| Outcome: | The proposed approach outperforms existing methods in a standard and in 'zero-shot' setting. |
Building The First English-Brazilian Portuguese Corpus for Automatic Post-Editing (2020.coling-main)
Copied to clipboard
| Challenge: | Existing corpus for automatic post-editing of English and Brazilian Portuguese is limited. |
| Approach: | They introduce a corpus for Automatic Post-Editing of English and Brazilian Portuguese. |
| Outcome: | The proposed corpus improves on the English and Brazilian Portuguese languages. |
NeuralREG: An end-to-end approach to referring expression generation (P18-1)
Copied to clipboard
| Challenge: | Referring Expression Generation models typically rely on features such as salience and grammatical function to make decisions about form and content. |
| Approach: | They propose a new approach that makes decisions about form and content in one go . they use a delexicalized version of the WebNLG corpus to test the approach . |
| Outcome: | The proposed approach significantly improves over two strong baselines. |
MTLens: Machine Translation Output Debugging (2022.lrec-1)
Copied to clipboard
Shreyas Sharma, Kareem Darwish, Lucas Pavanelli, Thiago Castro Ferreira, Mohamed Al-Badrashiny, Kamer Ali Yuksel, Hassan Sawaf
| Challenge: | a demo demonstrates a system for quantitatively evaluating MT systems in isolation or multiple MT models collectively . performance of machine translation systems varies significantly with inputs of diverging features, such as genres, genres and surface properties. |
| Approach: | They propose a benchmarking interface that quantitatively evaluates MT systems in isolation or collectively . the interface can be extended to include additional filters such as lexical, morphological, and syntactic features. |
| Outcome: | The proposed system quantitatively evaluates MT systems on multiple domains and evaluation metrics. |