Papers by Rik van Noord
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. |
A Taxonomy for In-depth Evaluation of Normalization for User Generated Content (L18-1)
Copied to clipboard
| Challenge: | Existing taxonomies for lexical normalization are not suitable for the task of normalization since the categories are substantially different. |
| Approach: | They propose a taxonomy of error categories for lexical normalization . they annotate a recent normalization dataset and read a near-perfect agreement . |
| Outcome: | The proposed taxonomy is based on a recent normalization dataset and it performs well. |
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. |
Transparent Semantic Parsing with Universal Dependencies Using Graph Transformations (2022.coling-1)
Copied to clipboard
| Challenge: | Existing semantic parsers are based on deep learning, but rule-based approaches offer advantages . a drawback of neural semantic parses is that their output lacks explainability . |
| Approach: | They propose a method that maps a syntactic dependency tree to a formal meaning representation using a series of graph transformations. |
| Outcome: | The proposed method outperforms neural parsers in English, German, Italian and Dutch. |
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. |
Evaluating Scoped Meaning Representations (L18-1)
Copied to clipboard
| Challenge: | Semantic parsing offers many opportunities to improve natural language understanding . current research on open-domain semantic parsers focuses on supervised learning methods . |
| Approach: | They propose a semantically annotated parallel corpus for English, German, Italian, and Dutch . they use a matching tool to evaluate scoped meaning representations to match clauses . |
| Outcome: | The proposed method captures the semantics of negation, modals, quantification, and presupposition triggers . it compares scoped meaning representations to gold standard parsers and finds improvements . |
Input Representations for Parsing Discourse Representation Structures: Comparing English with Chinese (2021.acl-short)
Copied to clipboard
| Challenge: | Neural semantic parsers have obtained acceptable results in parsing DRSs . previous studies have focused on parse of DRS in English, but have focused only on a few languages . |
| Approach: | They propose to use character sequences as input to map meaning representations to string format. |
| Outcome: | The proposed models learn the meaning of a series of semantic phenomena by taking sentences as input and outputting the corresponding DRSs, without the aid of any extra linguistic information. |