Data Augmentation for Hypernymy Detection (2021.eacl-main)

Copied to clipboard

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations