-
## 概要
深層強化学習を用いて文単純化．
モデルはよくあるencoder-decoder attentionモデル．
報酬として，文の単純さ, 文法の正しさ，流暢さ(文の自然さ)の3つの重み付き和を導入．
BLEUなどの自動評価の結果はイマイチだが，人手評価では最も高い評価を得ている．
## 著者
Xingxing Zhang and Mirella Lapata
…
-
Using TensorFlow backend.
Generate new embeddings files for a dataset
Read file: komninos_english_embeddings.gz
Added words: 3
:: Transform agac_chunking dataset ::
Traceback (most recent call la…
-
Hi,
I am facing the following error when trying to run python3 Train_POS.py . How could I fix this?
`WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.p…
-
In your paper, The EMNLP2017 WMT News dataset5 contains 268,586 sentences, but there are lots of datasets in url http://www.statmt.org/wmt17/ and I have no sense which one is the dataset used in exper…
-
## 概要
建設的なコメントか否かの分類の話．明示的にラベル付けされたデータがないので，実サービス上で専門家が選定したコメントを利用する．
SVMでF1スコア0.84の分類精度を得られた．
## 著者
Varada Kolhatkar, Maite Taboada
## リンク
https://www.sfu.ca/~mtaboada/docs/publications/…
-
Hi there,
No matter which script I run, I get the same error in ChainCRF, i.e.,
`Traceback (most recent call last):
File "Train_POS.py", line 69, in
model.fit(epochs=25)
File "/mnt/b…
-
Dear Team,
I get following error while running docker-compose up. I have downloaded the files and also placed them at right location.539106
backend_1 | Using TensorFlow backend.
backend_1 | …
-
Is it true ? I chang the embeddingsPath = 'reimers_german_embeddings.gz' to embeddingsPath = 'komninos_english_embeddings.gz'
-
Hi,
Can I use this model for transfer learning? Training on one corpus and then using that pretrained model for a new corpus? How can I do that? or it's not possible with this ?
ghost updated
5 years ago
-
I am trying to run this on GPU but having memory issue. Where can I modify the batch size?
Thanks.