HilMeMe: A Human-in-the-Loop Machine Translation Evaluation Metric Looking into Multi-Word Expressions
This addresses the need for better evaluation metrics in machine translation, particularly for distinguishing high-quality systems, but it is incremental as it builds on existing linguistic insights.
The paper tackles the problem of evaluating machine translation systems by focusing on multi-word expressions (MWEs), proposing a human-in-the-loop metric to assess how well systems translate MWEs, with results indicating it can distinguish between state-of-the-art systems based on this factor.
With the fast development of Machine Translation (MT) systems, especially the new boost from Neural MT (NMT) models, the MT output quality has reached a new level of accuracy. However, many researchers criticised that the current popular evaluation metrics such as BLEU can not correctly distinguish the state-of-the-art NMT systems regarding quality differences. In this short paper, we describe the design and implementation of a linguistically motivated human-in-the-loop evaluation metric looking into idiomatic and terminological Multi-word Expressions (MWEs). MWEs have played a bottleneck in many Natural Language Processing (NLP) tasks including MT. MWEs can be used as one of the main factors to distinguish different MT systems by looking into their capabilities in recognising and translating MWEs in an accurate and meaning equivalent manner.