| Challenge: | Existing methods for supervised inference have limited quality training data. |
| Approach: | They propose two techniques which generate new training examples from existing ones . they combine linguistic principles of hypernym transitivity and intersective modifier-noun composition . |
| Outcome: | The proposed techniques generate new training examples from existing datasets. |
Similar Papers
A Survey of Data Augmentation Approaches for NLP (2021.findings-acl)
Copied to clipboard
Steven Y. Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, Eduard Hovy
| Challenge: | Data augmentation is a field of research that has been underexplored due to the discrete nature of language data. |
| Approach: | They present a comprehensive survey of data augmentation for NLP by summarizing the literature in a structured manner. |
| Outcome: | The proposed methods are used for popular NLP applications and tasks and highlight current challenges and directions for future research. |
Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection (N18-1)
Copied to clipboard
| Challenge: | Existing unsupervised methods for learning hypernyms from unlabeled text are not scaled to large vocabularies or yield unacceptably poor accuracy. |
| Approach: | They propose an unsupervised method of hypernym discovery using word contexts . they use word2vec to embed word context distributions without supervision . |
| Outcome: | The proposed method provides double the precision and highest average performance on 11 datasets. |
BiRRE: Learning Bidirectional Residual Relation Embeddings for Supervised Hypernymy Detection (2020.acl-main)
Copied to clipboard
| Challenge: | supervised hypernymy detection has been studied under various frameworks . supervised classifiers are more likely to suffer from "lexical memorization" |
| Approach: | They propose a representation learning framework called Bidirectional Residual Relation Embeddings to model the possibility of a term being mapped to another in the embedding space by hypernymy relations. |
| Outcome: | The proposed model outperforms baselines over evaluation frameworks. |
MixEdit: Revisiting Data Augmentation and Beyond for Grammatical Error Correction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Various data augmentation strategies have been proposed to improve GEC models . high-quality parallel data for GEC is not as widely available . |
| Approach: | They propose a data augmentation approach that strategically augments real data by generating pseudo data. |
| Outcome: | The proposed approach significantly improves GEC models on English and Chinese datasets. |
Undersampling Improves Hypernymy Prototypicality Learning (L18-1)
Copied to clipboard
| Challenge: | supervised hypernymy detection suffers from overfitting hypernies in training data. |
| Approach: | They propose a method that can alleviate the problem of overfitting hypernyms in training data by using distributional representations for unknown word pairs. |
| Outcome: | The proposed method alleviates the problem of overfitting hypernyms in training data and improves distributional prototypicality learning for unknown word pairs. |
Hypernymy Detection for Low-Resource Languages via Meta Learning (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies focus on monolingual hypernymy detection on high-resource languages, but few investigate low-resourced scenarios. |
| Approach: | They propose to combine high-resource languages to solve low-resourced hypernymy detection problem . they extensively compare three joint training paradigms and propose meta learning . |
| Outcome: | The proposed method significantly improves performance of extremely low-resource languages by preventing over-fitting on small datasets. |
When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | a taxonomy is a semantic hierarchy of words or concepts organized w.r.t. their hypernymy relationships. |
| Approach: | They propose a framework for hypernymy detection using large textual corpora . they quantify the non-negligible existence of specific sparsity cases . |
| Outcome: | The proposed framework quantifies the non-negligible existence of specific sparsity cases on several benchmark datasets. |
Lexical Entailment with Hierarchy Representations by Deep Metric Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing lexical entailment studies cannot be applied to words that are not included in the training dataset. |
| Approach: | They propose a method that learns a mapping from word embeddings to hierarchical embedds to predict hypernymy relations among words. |
| Outcome: | The proposed method achieves state-of-the-art performance and robustness for unknown words. |
GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing work adopts data augmentation techniques to generate pseudo-annotated sentences . existing methods neither preserve semantic consistency of original sentences nor preserve syntax structure of sentences when expressing relations using seq2seq models, resulting in less diverse augmentations. |
| Approach: | They propose a dedicated augmentation technique for relational texts, named GDA, which uses two complementary modules to preserve both semantic consistency and syntax structures. |
| Outcome: | The proposed technique can bring 2.0% F1 improvements in three datasets under low-resource setting. |
HyperBox: A Supervised Approach for Hypernym Discovery using Box Embeddings (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for hypernym detection rely on word distribution. |
| Approach: | They propose a model to learn box embeddings for hypernym discovery by using a dataset . they compare the performance of their model on medical and music domains . |
| Outcome: | The proposed model outperforms existing methods on most evaluation metrics on medical and music domains. |