Contextual Representation Learning beyond Masked Language Modeling
How do masked language models (MLMs) such as BERT learn contextual representations? In this work, we analyze the learning dynamics of MLMs. We find that MLMs adopt sampled embeddings as anchors to estimate and inject contextual semantics to representations, which limits the efficiency and effectiveness of MLMs. To address these issues, we propose TACO, a simple yet effective representation learning approach to directly model global semantics. TACO extracts and aligns contextual semantics hidden in contextualized representations to encourage models to attend global semantics when generating contextualized representations. Experiments on the GLUE benchmark show that TACO achieves up to 5x speedup and up to 1.2 points average improvement over existing MLMs. The code is available at https://github.com/FUZHIYI/TACO.
Code (1)
Tasks
Language ModelingLanguage ModellingMasked Language ModelingRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Contextual Representation Learning beyond Masked Language Modeling
Currently, masked language modeling (e.g., BERT) is the prime choice to learn contextualized representations. Due to the pervasiveness, it naturally raises an interesting question: how do masked language models (MLMs) le…
Language ModelingLanguage ModellingMasked Language ModelingRepresentation LearningCoT-MAE v2: Contextual Masked Auto-Encoder with Multi-view Modeling for Passage Retrieval
Growing techniques have been emerging to improve the performance of passage retrieval. As an effective representation bottleneck pretraining technique, the contextual masked auto-encoder utilizes contextual embedding to …
Passage RetrievalRetrievalSentenceMasked Modeling for Self-supervised Representation Learning on Vision and Beyond
As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and the low dependence on labeled data. Amon…
Representation LearningSelf-Supervised LearningSurveyExploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection
In this paper, we for the first time explore helpful multi-modal contextual knowledge to understand novel categories for open-vocabulary object detection (OVD). The multi-modal contextual knowledge stands for the joint r…
Knowledge DistillationLanguage ModelingLanguage ModellingMasked Language Modeling+5CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation
We study the task of weakly-supervised point cloud semantic segmentation with sparse annotations (e.g., less than 0.1% points are labeled), aiming to reduce the expensive cost of dense annotations. Unfortunately, with ex…
Representation LearningScene UnderstandingSegmentationSemantic Segmentation