# Machine Translation Explanations

This notebook demonstrates model explanations for a text to text scenario using a pretrained transformer model for machine translation. In this demo, we showcase explanations on two different models: English to Spanish (https://huggingface.co/Helsinki-NLP/opus-mt-en-es), and English to French (https://huggingface.co/Helsinki-NLP/opus-mt-en-fr).

[1]:

import numpy as np
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import shap
import torch


## English to Spanish model

[2]:

# load the model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-es")
model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-es").cuda()

# define the input sentences we want to translate
data = [
"Transformers have rapidly become the model of choice for NLP problems, replacing older recurrent neural network models"
]


### Explain the model’s predictions

[3]:

# we build an explainer by passing the model we want to explain and
# the tokenizer we want to use to break up the input strings
explainer = shap.Explainer(model, tokenizer)

# explainers are callable, just like models
shap_values = explainer(data, fixed_context=1)

floor_divide is deprecated, and will be removed in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values.
To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). (Triggered internally at  /pytorch/aten/src/ATen/native/BinaryOps.cpp:467.)


### Visualize shap explanations

[4]:

shap.plots.text(shap_values)


[0]
outputs
Los
es
se
han
convertido
rápidamente
en
el
modelo
de
elección
para
problemas
N
LP
,
reemplaza
ndo
modelos
de
red
neuro
nal
recurrente
s
más
antiguos

inputs
1.965
▁Transform
5.114
ers
1.903
▁have
-0.505
▁rapidly
0.186
▁become
0.101
▁the
-0.225
▁model
0.325
▁of
-0.114
▁choice
0.081
▁for
-0.096
▁N
0.021
LP
-0.247
▁problems
-0.417
,
0.053
▁replacing
0.025
▁older
0.05
▁recurrent
0.172
▁neural
0.105
▁network
-0.114
▁models
-0.1