paper-with-me

Papers

LinkBERT: Pretraining Language Models with Document Links

2022-03-29 · ACL 2022 5 · Michihiro Yasunaga, Jure Leskovec, Percy Liang

Language model (LM) pretraining can learn various knowledge from text corpora, helping downstream tasks. However, existing methods such as BERT model a single document, and do not capture dependencies or knowledge that span across documents. In this work, we propose LinkBERT, an LM pretraining method that leverages links between documents, e.g., hyperlinks. Given a text corpus, we view it as a graph of documents and create LM inputs by placing linked documents in the same context. We then pretrain the LM with two joint self-supervised objectives: masked language modeling and our new proposal, document relation prediction. We show that LinkBERT outperforms BERT on various downstream tasks across two domains: the general domain (pretrained on Wikipedia with hyperlinks) and biomedical domain (pretrained on PubMed with citation links). LinkBERT is especially effective for multi-hop reasoning and few-shot QA (+5% absolute improvement on HotpotQA and TriviaQA), and our biomedical LinkBERT sets new states of the art on various BioNLP tasks (+7% on BioASQ and USMLE). We release our pretrained models, LinkBERT and BioLinkBERT, as well as code and data at https://github.com/michiyasunaga/LinkBERT.

📄 PDF Abstract BibTeX arXiv:2203.15827

Code (1)

michiyasunaga/LinkBERT 공식 구현 pytorch

Tasks

Document ClassificationLanguage ModelingLanguage ModellingMasked Language ModelingMedical Relation ExtractionNamed Entity Recognition (NER)PICOQuestion AnsweringRelation ExtractionRelation PredictionSemantic SimilaritySentence SimilarityText ClassificationTriviaQA

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

WRAP++: Web discoveRy Amplified Pretraining

2026-04-08 · Jiang Zhou, Yunhao Wang, Xing Wu, Tinghao Yu 외 arxiv

Synthetic data rephrasing has emerged as a powerful technique for enhancing knowledge acquisition during large language model (LLM) pretraining. However, existing approaches operate at the single-document level, rewritin…

DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents

2023-06-09 · Fuxiao Liu, Hao Tan, Chris Tensmeyer

Vision-language pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text. While existing vision-language pretraining models primarily fo…

Contrastive Learningdocument understanding

Patton: Language Model Pretraining on Text-Rich Networks

2023-05-20 · Bowen Jin, Wentao Zhang, Yu Zhang, Yu Meng 외

A real-world text corpus sometimes comprises not only text documents but also semantic links between them (e.g., academic papers in a bibliographic network are linked by citations and co-authorships). Text documents and …

Language ModelingLanguage ModellingMasked Language Modelingmodel+1

DOCmT5: Document-Level Pretraining of Multilingual Language Models

2021-12-16 · Findings (NAACL) 2022 7 · Chia-Hsuan Lee, Aditya Siddhant, Viresh Ratnakar, Melvin Johnson

In this paper, we introduce DOCmT5, a multilingual sequence-to-sequence language model pretrained with large scale parallel documents. While previous approaches have focused on leveraging sentence-level parallel data, we…

de-enDocument SummarizationDocument TranslationLanguage Modeling+4

In-context Pretraining: Language Modeling Beyond Document Boundaries

2023-10-16 · Weijia Shi, Sewon Min, Maria Lomeli, Chunting Zhou 외

Large language models (LMs) are currently trained to predict tokens given document prefixes, enabling them to directly perform long-form generation and prompting-style tasks which can be reduced to document completion. E…

In-Context LearningLanguage ModelingLanguage ModellingReading Comprehension