-
-
Hi, I am working on PIE-BERT-Base, when I use the released synthetic data ( actually, I chose a2 ), I performed 2 epochs of training on a2 and fine-tune on the Lang8+fce+nucle for 2 epochs, using PIE-…
-
Join us on Hangout: https://hangouts.google.com/group/kUxBAunjGittAkBUA
Active Learning Tutorial (blog post)
Simple inro: https://towardsdatascience.com/introduction-to-active-learning-117e0740d7c…
-
我认为这个论文无效：
在中文数据集上的试验，使用 jieba 分词，代码tf 如下：
with tf.variable_scope('word_char_embedding_combine'):
with tf.variable_scope('word_freq_conversion'):
…
-
# Description
Question answering over Linked Data can be broadly segmented into three tasks. Identifying named entities, identifying predicates (relation extraction) and finally generating a precise …
-
Hi https://github.com/bfelbo
Sorry for pestering you! I am currently building a similar model for Emoji prediction for Hindi(India) language. I couldn't understand how are you treating emojis gather…
-
I am trying to better understand the difference between the different types of embeddings that BERT uses (from the BERT paper: token, segment, position). For this purpose, I was hoping to put some pri…
-
From FAQ: "Note that publications must be at least 6 pages long to be counted."
In the natural language processing field, all the top conferences (ACL, EMNLP, NAACL) have short papers that are limi…
-
Here is a script I just wrote to load a model with the custom LSTM kernel and re-pack it into a new model so we can put it in the demo and distribute it. Turned out that we don't have any functionalit…
-
Lets keep a checklist of the proposal w.r.t. to the requirements from https://acl2020.org/calls/workshops/
**First two pages:**
- [x] A title and brief description of the workshop topic and co…