Semanlink - NLP@Harvard

Recherche de Mot-clé

Recherche de Doc

Préférences...

Mots-clés liés

BERT - Biomedical NLP - Deep latent variable models - Domain adaptation (NLP) - EMNLP 2018 - EMNLP 2020 - Tutorial - Variational Bayesian methods -

Parents :

NLP@Harvard

Amis :

Descendants

2 Documents (Liste longue)

exBERT: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources - ACL Anthology

Tags:

**Focus on the Embedding of Domain-specific Vocabulary.**

> exBERT
adds a new domain-specific vocabulary and the corresponding
embedding layer, as well as a small
extension module to the original unmodified model

> a pretraining
method allowing **low-cost embedding of
domain-specific vocabulary in the context of an
existing large pre-trained model such as BERT**

> exBERT... explicitly incorporates
the new domain’s vocabulary, while being able to
**reuse the original pre-trained model’s weights as is**
to reduce required computation and training data. Specifically, exBERT extends BERT by augmenting
its embeddings for the original vocabulary with
new embeddings for the domain-specific vocabulary
via **a learned small “extension” module**. **The
output of the original and extension modules are
combined via a trainable weighted sum operation**

In a way similar to concept developed in

> [[1902.00751] Parameter-Efficient Transfer Learning for NLP](doc:2021/04/1902_00751_parameter_efficien), but not in the fine-tuning paradigm.

[Github](https://github.com/cgmhaicenter/exBERT)

2021-04-11 A propos

Deep Latent-Variable Models for Natural Language - Tutorial - harvardnlp

Tags:

2018-11-01 A propos

Propriétés

sl:creationDate : 2021-04-11
sl:creationTime : 2021-04-11T16:12:06Z
rdf:type : sl:Tag
skos:prefLabel : NLP@Harvard