| Challenge: | a new system for text-to-speech synthesis uses rule-based homograph disambiguation . a simple application of machine learning produces significant improvements in homograph ambiguity . |
| Approach: | They propose a rule-based homograph disambiguation system for text-to-speech synthesis at Google . they compare it to a new system which performs disambiguations using classifiers trained on labeled data . |
| Outcome: | The proposed system is more accurate than hand-written rules or machine learning alone. |
Similar Papers
Disambiguating Homographs and Homophones Simultaneously: A Regrouping Method for Japanese (2024.lrec-main)
Copied to clipboard
| Challenge: | Using a method that re-groups surface forms into clusters representing synonyms, we examine how accurate such disambiguation can be. |
| Approach: | They propose to regroup homographs and homophones into clusters and use them to disambiguate them. |
| Outcome: | The proposed method is applied post-hoc to trained word embeddings in Japanese. |
Handling Homographs in Neural Machine Translation (N18-1)
Copied to clipboard
| Challenge: | Existing methods for MT have problems with translating homographs, as it is difficult to select the correct translation based on the context. |
| Approach: | They propose to model the context of the input word with context-aware word embeddings that help to differentiate the word sense before feeding it into the encoder. |
| Outcome: | The proposed models improve translation accuracy and BLEU score on three language pairs. |
Unsupervised Cross-Lingual Representation Learning (P19-4)
Copied to clipboard
| Challenge: | a comprehensive survey of cutting-edge weakly-supervised and unsupervised cross-lingual word representations is presented . |
| Approach: | This tutorial provides a comprehensive survey of recent work on weakly-supervised and unsupervised cross-lingual word representations. |
| Outcome: | This tutorial provides a comprehensive survey of cutting-edge weakly-supervised and unsupervised word representations. |
Fusing Label Embedding into BERT: An Efficient Improvement for Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to improve text classification performance of pre-trained models have been used to improve their performance. |
| Approach: | They propose a method for improving BERT's performance by using a label embedding technique while keeping almost the same computational cost. |
| Outcome: | The proposed method improves BERT's performance on six text classification benchmark datasets while keeping almost the same computational cost. |
Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13) (D19-53)
Copied to clipboard
| Challenge: | TextGraphs is a workshop on graph-based methods for natural language processing . the workshop is being organized in conjunction with the 9th International Joint Conference on Natural Language Processing . |
| Approach: | TextGraphs is the 13th edition of the Workshop on Graph-Based Methods for Natural Language Processing . the workshop promotes synergy between GT and natural language processing . |
| Outcome: | the 2013 edition of TextGraphs is being held in conjunction with the 9th International Joint Conference on Natural Language Processing in Hong Kong. |
Heterogeneous Graph Transformer for Graph-to-Sequence Learning (2020.acl-main)
Copied to clipboard
| Challenge: | Recent studies ignore the indirect relations between distance nodes, or treat indirect relations and direct relations in the same way. |
| Approach: | They propose a graph-to-sequence (Graph2Seq) encoder which models graph structure to model different relations in individual subgraphs of the original graph. |
| Outcome: | The proposed model outperforms the state-of-the-art on all four benchmarks of AMR-to-text generation and syntax-based neural machine translation. |
Evaluate AMR Graph Similarity via Self-supervised Learning (2023.acl-long)
Copied to clipboard
| Challenge: | Current AMR metrics do not consider the entire structure of AMR graphs . |
| Approach: | They propose to learn automatic AMR graph similarity evaluation metric by encoding AMR to a pre-trained language model and using GNN adapters to capture structural information of AMR diagrams. |
| Outcome: | The proposed metric significantly improves the correlations with human semantic scores and remains robust under diverse challenges. |
Connecting the Dots: What Graph-Based Text Representations Work Best for Text Classification using Graph Neural Networks? (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Graph Neural Networks have been used for text classification, but only in domains with limited data characteristics. |
| Approach: | They compare graph representation methods for text classification using different architectures and setups. |
| Outcome: | The proposed graph representation methods outperform other models in document comprehension tasks. |
A Novel Challenge Set for Hebrew Morphological Disambiguation and Diacritics Restoration (2020.findings-emnlp)
Copied to clipboard
| Challenge: | morphological parsers face a formidable challenge with unbalanced ambiguities in homographs . case of unbalanciated ambiguity is difficult to disambiguate, especially in cases of unbalancing . a new dataset improves the overall average F1 score for Hebrew homograph . |
| Approach: | They propose a challenge set for Hebrew homographs with substantial attestation of each analysis of 21 Hebrew homographies. |
| Outcome: | The proposed set improves the average F1 score for Hebrew homographs by 0.67 . the annotated datasets are made publicly available for further research. |
Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification (2021.eacl-main)
Copied to clipboard
| Challenge: | Semi-supervised learning and multilingual pretraining have been shown to be effective for task-specific labelled data shortages. |
| Approach: | They propose to combine semi-supervised deep generative models and multi-lingual pretraining to form a pipeline for document classification task. |
| Outcome: | The proposed method outperforms state-of-the-art models in low-resource settings across several languages and outperformed existing models in English. |