Papers with contrastive learning objectives
SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for dialog understanding only consider self-augmented dialogs as positive samples and treat all other dialogs like negative ones. |
| Approach: | They propose a tree-structured pre-trained conversation model which learns dialog representations from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised contrastive pre-training. |
| Outcome: | The proposed model can achieve state-of-the-art results on the DialoGLUE benchmark. |
KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering (2022.emnlp-main)
Copied to clipboard
| Challenge: | Extractive Question Answering (EQA) is one of the most essential tasks in Machine Reading Comprehension (MRC). |
| Approach: | They propose a framework that transforms extractive question answering into a non-autoregressive Masked Language Modeling (MLM) generation problem. |
| Outcome: | The proposed framework outperforms state-of-the-art approaches in few-shot learning scenarios by a large margin. |
Factual Dialogue Summarization via Learning from Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing models generate fluent and coherent summaries, but inconsistencies can be found in generated summary. |
| Approach: | They propose to use symbolic knowledge distillation to improve the factual consistency of smaller pretrained models for dialogue summarization. |
| Outcome: | The proposed model outperforms baseline models in BART, PEGASUS, and Flan-T5 in factual consistency and accuracy. |
The Overlooked Role of Graded Relevance Thresholds in Multilingual Dense Retrieval (2026.findings-acl)
Copied to clipboard
| Challenge: | Dense retrieval models are fine-tuned with contrastive learning objectives that require binary relevance judgments. |
| Approach: | They examine how graded relevance scores affect multilingual dense retrieval . they argue that a well-chosen threshold can improve effectiveness and mitigate annotation noise . |
| Outcome: | The optimal threshold varies systematically across languages and tasks, the authors show . a well-chosen threshold can improve effectiveness and mitigate annotation noise . |
Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings (2022.emnlp-main)
Copied to clipboard
| Challenge: | Prior work relies on discrete citation relations to generate contrast samples, but discrete ones enforce a hard cut-off to similarity. |
| Approach: | They propose to use nearest neighbor sampling to learn continuous similarity and to sample hard-to-learn negatives and positives by controlling the sampling margin between them. |
| Outcome: | The proposed method outperforms the state-of-the-art on the SciDocs benchmark and can train (or tune) language models sample-efficiently. |