Papers by Xavier Carreras
Interpolated Spectral NGram Language Models (P19-1)
Copied to clipboard
| Challenge: | Spectral methods for learning weighted non-deterministic automata have nice theoretical and algorithmic properties, but they have been challenging to get competitive results on language modeling tasks. |
| Approach: | They propose a method for scaling up spectral learning and use interpolated predictions that are optimized to maximize perplexity. |
| Outcome: | The proposed method matches state-of-the-art ngram models while being very fast to train. |
Local String Transduction as Sequence Labeling (C18-1)
Copied to clipboard
| Challenge: | String transduction and sequence labeling are often treated as separate entities and often give treatment to different problems in NLP. |
| Approach: | They propose to reduce string transduction to sequence labeling by using a finite-state technique that uses string transducing and sequence labelling. |
| Outcome: | The proposed method performs better than seq2seq models and yields state-of-the-art results in several cases. |
Translate First Reorder Later: Leveraging Monotonicity in Semantic Parsing (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing approaches that model alignments between sentences fail at compositional generalization tasks, resulting in a resurgence of such approaches. |
| Approach: | They propose a two-step approach that first translates input sentences monotonically and then reorders them to obtain the correct output. |
| Outcome: | The proposed approach improves compositional generalization over existing models and other approaches that exploit gold alignment annotations. |
Minimizing Annotation Effort via Max-Volume Spectral Sampling (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Spectral sampling strategies that minimize the number of annotations required to train a model are proposed. |
| Approach: | They propose a method that maximizes the amount of information useful for the learning algorithm by minimizing redundancy of samples in the selection. |
| Outcome: | The proposed method maximizes the amount of information useful for the learning algorithm or minimizes redundancy of samples in the selection. |