Comments (3)
Yes, we used BERT only as the subword tokenizer. We will release the codes and the labeled data to help quick implement, hopefully in the next week.
from sembert.
The manner you provide rich semantic embeddings is a great insight. Thanks for sharing the source code.
from sembert.
Yes, we used BERT only as the subword tokenizer.
Hi, @cooelf. I think I am a bit confused by this. The paper seems to imply that BERT is used not just to tokenize words into subwords, but also to get contextualized representations for the subwords. For example, you have this figure, which shows the interactions between tokens:
Then there is also the following passage in the paper (I added bolding):
The raw text sequences and semantic role label sequences are firstly represented as embedding vectors to feed a pre-trained BERT. The input sentence X = {x1, . . . , xn} is a sequence of words of length n, which is first tokenized to word pieces (subword tokens). Then the transformer encoder captures the contextual information for each token via self-attention and produces a sequence of contextual embeddings.
Can you clarify, @cooelf?
from sembert.
Related Issues (20)
- srl is not a registered name for model HOT 1
- Allennlp预测SRL结果不一致 HOT 7
- 数据集下载失败 HOT 1
- About SQuAD task HOT 1
- srl is not a registered name for Model. HOT 1
- why the info of SRL is not used as additional embedding layers
- Why is the SRL information not used as an additional embedding layer. HOT 2
- Error: online data annotation HOT 1
- Missing key(s) in state_dict: "bert_model.embeddings.position_ids". HOT 1
- when using allennlp srl model for predicting, the speed is slow HOT 1
- forward计算中只用了cls,所以bert后的cnn对齐还有必要吗?另外请教是否尝试过融入词性特征呢? HOT 2
- 请问是否提供了在SQuAD2.0数据集上运行的代码? HOT 1
- 请问是否有在SQuAD2.0上的代码呢 HOT 1
- Use pre-trained SemBERT as a sentence encoder? HOT 1
- RuntimeError: size mismatch, m1: [32 x 78], m2: [778 x 778] HOT 2
- Pool function dimension not match HOT 4
- allennlp-models version HOT 2
- Cannot re-produce the result on SNLI HOT 2
- 请问为什么要用max处理sequence_out HOT 1
- Errors from allennlp
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from sembert.