-
Hi @humanlee1011, thank you for providing the implementation.
when I try to run perf_train.py,the program shows" can not find hdfs_sentence2vec.pkl",and I cannot find the code which generate the fi…
-
Exact matching definitely misses some data that we want, so implement something better in `utils.participants.py`.
- [x] levenshtein
- [ ] sentence2vec
- [ ] trigrams, etc
-
#### Issue Description
Google published [pretrainend sentence2vec models for tensorflow](https://tfhub.dev/google/universal-sentence-encoder/2). It would be a nice addition to dl4j, if it supported…
-
Some resources about word and sentence embedding.
- [_The Current Best of Universal Word Embeddings and Sentence Embeddings_](https://medium.com/huggingface/universal-word-sentence-embeddings-ce48d…
-
I copied a sentence in sent.txt. so a sentence is duplicated.
But, after executing demo.py vector value is not same to two same sentence.
my sent.txt file is below
```
Harbin Institute of Technolog…
-
请问你做过句子向量吗？
-
Would it be possible to add a sample tsv file that this project use?
-
Pre-filter words whose non-diacrictized word-forms are not in the dictionary, before asking the model to do ADR. This way we can get more predictable results and error messages for Out-Of-Vocabulary w…
-
Hey there, @weiyinwei
Thanks for your paper and the approach to tackle multi-modal deep learning here.
My question is , I can see and get the datasets mentioned, but I see there is no code for pre-…
-
如果两段文本大差不差，但是又不是每个字都相同的话，也可以检测出来吗