Papers by Tim Van de Cruys
DiscSense: Automated Semantic Analysis of Discourse Markers (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing models for predicting discourse markers have been used to study link between markers and semantic relations . |
| Approach: | They use a model trained to predict discourse markers between sentence pairs to predict plausible markers between sentences with a known semantic relation. |
| Outcome: | The proposed method predicts markers between sentence pairs with a known semantic relation . the resulting dataset, named DiscSense, is publicly available . |
How Relevant Are Selectional Preferences for Transformer-based Language Models? (2020.coling-main)
Copied to clipboard
| Challenge: | Selectional preference is defined as the tendency of a predicate to favor particular arguments within a certain linguistic context and reject others that result in conflicting or implausible meanings. |
| Approach: | They examine the probability that Bert assigns a dependent word given the presence of a head word in a sentence to determine whether selectional preference exists. |
| Outcome: | The proposed model is based on the SP-10K corpus of selectional preference and the ukWaC corpus. |
“Chère maison” or “maison chère”? Transformer-based prediction of adjective placement in French (2023.findings-eacl)
Copied to clipboard
| Challenge: | Prior work has shown that transformer-based language models are insensitive to permutated word order, but this is not the case with pretraining. |
| Approach: | They conduct experiments to assess whether transformer-based language models are able to learn the adjective position in noun phrases in French. |
| Outcome: | The proposed model is weaker with complex structures and fixed expressions, but favors context and global syntactic roles. |
A Pragmatics-Centered Evaluation Framework for Natural Language Understanding (2022.lrec-1)
Copied to clipboard
| Challenge: | a number of studies have suggested that models induce universal text representations . current benchmarks focus on semantic phenomena, so pragmatics needs to be the focus . |
| Approach: | They propose a benchmark that unites 11 pragmatics-focused evaluation datasets for English. |
| Outcome: | The proposed benchmark shows that natural language inference does not result in genuinely universal representations. |
Automatic Poetry Generation from Prosaic Text (2020.acl-main)
Copied to clipboard
| Challenge: | In recent years, successful approaches have emerged to accurately model various aspects of natural language. |
| Approach: | They propose to combine neural networks with a poetry generation system that only uses standard text as input . they use standard text to model syntactic well-formedness and topical coherence . |
| Outcome: | The proposed framework is applied to the generation of poems in English and French . it uses standard, non-poetic text and its output is constrained to confer a poetic character . |