Choose vocabulary size of tokenizer...

How do we generate the first target words in machine translation?...

R-Package "translateR" and Microsoft API...

Automatic text translation...

How to save Python NLTK alignment models for later use?...

Creating a Neural Machine Translation basics...

How to translate text from one language to another language android?...

How to reduce the inference time of Helsinki-NLP/opus-mt-es-en (translation model) from transformer...

How to strip a certain piece of text from each line of a text file?...

What is the difference between MarianMT and OpusMT?...

using gpu with simple transformer mt5 training...

Understanding introductory example on transformers in Trax...

Machine translation transformer output - "unknown" tokens?...

How to specify a forced_bos_token_id when using Facebook's M2M-100 HuggingFace model through AWS...

BLEU score implementation for sentence similarity detection...

I compare two identical sentences with RIBES NLTK and get an error. Why?...

I compare two identical sentences with GLEU NLTK and don't get 1.0. Why?...

Failing to Compile InferenceEngine Openvino using MVN operation...

Why would a Torchscript trace return different looking encoded_inputs compared to the original Trans...

How can multiple "text" parameters be passed to the DeepL API using Python?...

The role of initial state of lstm layer in seq2seq encoder...

SentencePiece in Google Colab...

(OpenNMT) Spanish to English Model Improvement...

Find phrase/word equivalent in translated sentence...

Sentence Indicating in Neural Machine Translation Tasks...

Is there a limit to the size of target word vocabulary that should be used in seq2seq models?...

What's the difference between NLTK's BLEU score and SacreBLEU?...

Conflicts in the training data for Microsoft Custom Translator...

Sockeye WMT German to English news translation stopping criterium...

Why special characters like () "" : [] are often removed from data before training transla...