Papers with negative sampling methods

3 papers
Improving Cross-Domain Chinese Word Segmentation with Word Embeddings (N19-1)

Copied to clipboard

Challenge: Existing approaches to Chinese word segmentation (CWS) are character-based and word-based . character-driven approaches use conditional random field models to label sequences, with complex hand-crafted discrete features.
Approach: They propose a semi-supervised word-based approach to improve cross-domain Chinese word segmentation given a baseline segmenter.
Outcome: The proposed model outperforms state-of-the-art approaches on five datasets covering domains in novels, medicine, and patent.
Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency (D18-1)

Copied to clipboard

Challenge: Conditional models are frequently encountered in practice, but there has not been a rigorous theoretical analysis of NCE in this setting.
Approach: They propose to use a ranking-based and ranking-only method for conditional models to estimate parameter estimates.
Outcome: The proposed method avoids calculation of partition function or derivatives at each training step . it is closely related to negative sampling methods, now widely used in NLP .
Learning Dense Representations of Phrases at Scale (2021.acl-long)

Copied to clipboard

Challenge: Existing phrase retrieval models rely on sparse representations and still underperform retriever-reader approaches.
Approach: They propose a method to learn phrase representations from reading comprehension tasks using negative sampling methods.
Outcome: The proposed model improves over previous models by 15%-25% absolute accuracy and matches the performance of state-of-the-art retrieval models.

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