Papers by Alexandre Salle
Multilingual and Code-Switched Sentence Ordering (2024.starsem-1)
Copied to clipboard
| Challenge: | Prior research has focused on English language structures and multilingual contexts . however, there are several shortcomings with specialized sentence ordering models and advanced Large Language Models like GPT-4. |
| Approach: | They propose a multilingual sentence order task that extends SO to diverse narratives across 12 languages and code-switched texts. |
| Outcome: | The proposed task extends SO to diverse narratives across 12 languages, including challenging code-switched texts. |
Restricted Recurrent Neural Tensor Networks: Exploiting Word Frequency and Compositionality (P18-2)
Copied to clipboard
| Challenge: | Recurrent neural tensor networks (RNNs) increase capacity by augmenting the size of the hidden layer, with significant increase in computational cost. |
| Approach: | They propose restricted recurrent neural tensor networks (r-RNTNs) which reserve distinct hidden layer weights for frequent vocabulary words while sharing a single set of weights . |
| Outcome: | The proposed model outperforms unrestricted RNTNs using only a small fraction of the parameters of unrestrained RNNNs. |