Rethinking the Evaluation of Neural Machine Translation

by   Jianhao Yan, et al.

The evaluation of neural machine translation systems is usually built upon generated translation of a certain decoding method (e.g., beam search) with evaluation metrics over the generated translation (e.g., BLEU). However, this evaluation framework suffers from high search errors brought by heuristic search algorithms and is limited by its nature of evaluation over one best candidate. In this paper, we propose a novel evaluation protocol, which not only avoids the effect of search errors but provides a system-level evaluation in the perspective of model ranking. In particular, our method is based on our newly proposed exact top-k decoding instead of beam search. Our approach evaluates model errors by the distance between the candidate spaces scored by the references and the model respectively. Extensive experiments on WMT'14 English-German demonstrate that bad ranking ability is connected to the well-known beam search curse, and state-of-the-art Transformer models are facing serious ranking errors. By evaluating various model architectures and techniques, we provide several interesting findings. Finally, to effectively approximate the exact search algorithm with same time cost as original beam search, we present a minimum heap augmented beam search algorithm.


page 1

page 2

page 3

page 4


Learning to Stop in Structured Prediction for Neural Machine Translation

Beam search optimization resolves many issues in neural machine translat...

Fast Locality Sensitive Hashing for Beam Search on GPU

We present a GPU-based Locality Sensitive Hashing (LSH) algorithm to spe...

If beam search is the answer, what was the question?

Quite surprisingly, exact maximum a posteriori (MAP) decoding of neural ...

On the Depth between Beam Search and Exhaustive Search for Text Generation

Beam search and exhaustive search are two extreme ends of text decoding ...

A Simple Baseline for Beam Search Reranking

Reranking methods in machine translation aim to close the gap between co...

Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models

In many natural language processing (NLP) tasks the same input (e.g. sou...

Breaking the Beam Search Curse: A Study of (Re-)Scoring Methods and Stopping Criteria for Neural Machine Translation

Beam search is widely used in neural machine translation, and usually im...

Please sign up or login with your details

Forgot password? Click here to reset