Papers with self-supervised task

5 papers
Self-Supervised Knowledge Triplet Learning for Zero-Shot Question Answering (2020.emnlp-main)

Copied to clipboard

Challenge: Current supervised Question Answering methods rely on expensive data annotations and can introduce unintended annotator bias.
Approach: They propose a self-supervised task over knowledge graphs that can be supervised by a data annotation tool.
Outcome: The proposed task performs better than pre-trained language models on a large dataset.
Towards Unified Prompt Tuning for Few-shot Text Classification (2022.findings-emnlp)

Copied to clipboard

Challenge: Prompt-based fine-tuning has boosted performance of Pre-trained Language Models (PLMs) on few-shot text classification, but PLMs are unfamiliar with prompt-style expressions during pre-training, which limits the few- shot learning performance on downstream tasks.
Approach: They propose a framework for prompt-based fine-tuning that captures prompting semantics from non-target NLP datasets and propose 'Prompt-Options-Verbalizer' for joint prompt learning across different NLP tasks.
Outcome: Experiments show that the proposed framework outperforms state-of-the-art prompt-based fine-tuning frameworks on few-shot text classification tasks.
Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting (2021.emnlp-main)

Copied to clipboard

Challenge: Existing text infilling objectives for pretrained language models require self-supervision by masking out tokens or spans in text.
Approach: They propose to extend text infilling to a self-supervised sequence-to-sequence (Seq2Sequen) task.
Outcome: The proposed task improves the model's performance on various natural language generation tasks.
Weakly-supervised Text Classification Based on Keyword Graph (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for text classification ignore keyword correlation, thus ignoring it . existing methods treat keywords independently, thus not exploiting correlation between them .
Approach: They propose a framework to explore keyword-keyword correlation on keyword graph by GNN . they use a self-supervised task to pretrain annotators and fine-tune them .
Outcome: The proposed method outperforms existing methods on long- and short-text datasets.
MEVTR: A Multilingual Model Enhanced with Visual Text Representations (2024.lrec-main)

Copied to clipboard

Challenge: Existing models that generate multilingual text representations perform poorly on low-resource languages due to lack of representation space and model capacity.
Approach: They propose a multilingual model enhanced with visual text representations which complements textual representations and extends multilingual representation space with visual representations.
Outcome: The proposed model outperforms state-of-the-art models on zero-shot cross-lingual transfer tasks without the target language adapter.

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