Papers with self-supervised manner

3 papers
Pretraining and Finetuning Language Models on Geospatial Networks for Accurate Address Matching (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing approaches to address matching and building authoritative address catalogues are limited in data quality and require labeling effort to develop accurate models.
Approach: They propose to view addresses as an address graph and curate inputs by placing geospatially linked addresses in the same context.
Outcome: The proposed framework improves address matching and fine-tuning language models.
Language Model Pre-Training with Sparse Latent Typing (2022.emnlp-main)

Copied to clipboard

Challenge: Modern large-scale Pre-trained Language Models focus on text reconstruction, but have not sought to learn latent-level interpretable representations of sentences.
Approach: They propose a new pre-training objective that enables the model to learn latent types . the objective allows the model a self-supervised way to extract sentence-level keywords .
Outcome: The proposed model learns interpretable latent type categories without external knowledge and improves downstream tasks.
Learning Reasoning Patterns for Relational Triple Extraction with Mutual Generation of Text and Graph (2022.findings-acl)

Copied to clipboard

Challenge: Existing methods focused on learning text patterns from explicit mentions but failed to extract the implicitly implied triples.
Approach: They propose to construct a relational graph from a sentence and apply multi-layer graph convolutions to capture the type inference logic of the paths.
Outcome: The proposed framework can find multi-hop reasoning paths and capture type inference logic with the sentence's supplementary relational expressions.

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