Evaluating Explanation Methods for Neural Machine Translation

05/04/2020
by   Jierui Li, et al.
Tencent
0

Recently many efforts have been devoted to interpreting the black-box NMT models, but little progress has been made on metrics to evaluate explanation methods. Word Alignment Error Rate can be used as such a metric that matches human understanding, however, it can not measure explanation methods on those target words that are not aligned to any source word. This paper thereby makes an initial attempt to evaluate explanation methods from an alternative viewpoint. To this end, it proposes a principled metric based on fidelity in regard to the predictive behavior of the NMT model. As the exact computation for this metric is intractable, we employ an efficient approach as its approximation. On six standard translation tasks, we quantitatively evaluate several explanation methods in terms of the proposed metric and we reveal some valuable findings for these explanation methods in our experiments.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/07/2016

Incorporating Discrete Translation Lexicons into Neural Machine Translation

Neural machine translation (NMT) often makes mistakes in translating low...
07/24/2018

Otem&Utem: Over- and Under-Translation Evaluation Metric for NMT

Although neural machine translation(NMT) yields promising translation pe...
04/26/2022

When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?

Word alignment has proven to benefit many-to-many neural machine transla...
05/31/2021

On Compositional Generalization of Neural Machine Translation

Modern neural machine translation (NMT) models have achieved competitive...
09/01/2019

Towards Understanding Neural Machine Translation with Word Importance

Although neural machine translation (NMT) has advanced the state-of-the-...
04/05/2020

Neural Machine Translation with Imbalanced Classes

We cast neural machine translation (NMT) as a classification task in an ...
05/13/2022

Comparison of attention models and post-hoc explanation methods for embryo stage identification: a case study

An important limitation to the development of AI-based solutions for In ...

Please sign up or login with your details

Forgot password? Click here to reset