paper-with-me

Papers

C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrieval

2022-04-25 · Eugene Yang, Suraj Nair, Ramraj Chandradevan, Rebecca Iglesias-Flores, Douglas W. Oard

Pretrained language models have improved effectiveness on numerous tasks, including ad-hoc retrieval. Recent work has shown that continuing to pretrain a language model with auxiliary objectives before fine-tuning on the retrieval task can further improve retrieval effectiveness. Unlike monolingual retrieval, designing an appropriate auxiliary task for cross-language mappings is challenging. To address this challenge, we use comparable Wikipedia articles in different languages to further pretrain off-the-shelf multilingual pretrained models before fine-tuning on the retrieval task. We show that our approach yields improvements in retrieval effectiveness.

📄 PDF Abstract BibTeX arXiv:2204.11989

Code (0)

등록된 구현이 없습니다.

Tasks

ArticlesLanguage ModelingLanguage ModellingRetrieval

Similar Papers 제목 키워드 기반

OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining

2023-11-15 · Yihong Liu, Peiqin Lin, Mingyang Wang, Hinrich Schütze

Instead of pretraining multilingual language models from scratch, a more efficient method is to adapt existing pretrained language models (PLMs) to new languages via vocabulary extension and continued pretraining. Howeve…

Language ModellingMultilingual Word EmbeddingsWord Embeddings

CLIPin: A Non-contrastive Plug-in to CLIP for Multimodal Semantic Alignment

2025-08-08 · Shengzhu Yang, Jiawei Du, Shuai Lu, Weihang Zhang 외 arxiv

Large-scale natural image-text datasets, especially those automatically collected from the web, often suffer from loose semantic alignment due to weak supervision, while medical datasets tend to have high cross-modal cor…

Contrastive Learning

Weak Supervision for Real World Graphs

2025-06-03 · Pratheeksha Nair, Reihaneh Rabbany

Node classification in real world graphs often suffers from label scarcity and noise, especially in high stakes domains like human trafficking detection and misinformation monitoring. While direct supervision is limited,…

Contrastive LearningMisinformationNode ClassificationRepresentation Learning

Difference-Masking: Choosing What to Mask in Continued Pretraining

2023-05-23 · Alex Wilf, Syeda Nahida Akter, Leena Mathur, Paul Pu Liang 외

The self-supervised objective of masking-and-predicting has led to promising performance gains on a variety of downstream tasks. However, while most approaches randomly mask tokens, there is strong intuition that decidin…

Self-Supervised Learning

Improving Large-Scale Weakly Supervised ASR by Filtering and Selection

2026-06-27 · Kohei Matsuura, Masato Mimura arxiv

Leveraging large-scale weakly supervised datasets is crucial to train robust end-to-end automatic speech recognition (ASR) models. However, such datasets often contain noisy labels and lack domain specificity, limiting t…

Speech Recognition