1 |
Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
It Is Not As Good As You Think! Evaluating Simultaneous Machine Translation on Interpretation Data ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Self-Alignment Pretraining for Biomedical Entity Representations
|
|
|
|
Abstract:
Despite the widespread success of self-supervised learning via masked language models (MLM), accurately capturing fine-grained semantic relationships in the biomedical domain remains a challenge. This is of paramount importance for entity-level tasks such as entity linking where the ability to model entity relations (especially synonymy) is pivotal. To address this challenge, we propose SapBERT, a pretraining scheme that self-aligns the representation space of biomedical entities. We design a scalable metric learning framework that can leverage UMLS, a massive collection of biomedical ontologies with 4M+ concepts. In contrast with previous pipeline-based hybrid systems, SapBERT offers an elegant one-model-for-all solution to the problem of medical entity linking (MEL), achieving a new state-of-the-art (SOTA) on six MEL benchmarking datasets. In the scientific domain, we achieve SOTA even without task-specific supervision. With substantial improvement over various domain-specific pretrained MLMs such as BioBERT, SciBERTand and PubMedBERT, our pretraining scheme proves to be both effective and robust. ; FL is supported by Grace & Thomas C.H. Chan Cambridge Scholarship. NC and MB would like to acknowledge funding from Health Data Research UK as part of the National Text Analytics project.
|
|
URL: https://doi.org/10.17863/CAM.72095 https://www.repository.cam.ac.uk/handle/1810/324645
|
|
BASE
|
|
Hide details
|
|
5 |
A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Show Some Love to Your n-grams: A Bit of Progress and Stronger n-gram Language Modeling Baselines ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Fast, Small and Exact: Infinite-order Language Modelling with Compressed Suffix Trees ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Structured Prediction of Sequences and Trees using Infinite Contexts ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|