Incorporate Semantic Structures into Machine Translation Evaluation via UCCA
Jin Xu | Yinuo Guo | Junfeng Hu
Proceedings of the Fifth Conference on Machine Translation
Copying mechanism has been commonly used in neural paraphrasing networks and other text generation tasks, in which some important words in the input sequence are preserved in the output sequence. Similarly, in machine translation, we notice that there are certain words or phrases appearing in all good translations of one source text, and these words tend to convey important semantic information. Therefore, in this work, we define words carrying important semantic meanings in sentences as semantic core words. Moreover, we propose an MT evaluation approach named Semantically Weighted Sentence Similarity (SWSS). It leverages the power of UCCA to identify semantic core words, and then calculates sentence similarity scores on the overlap of semantic core words. Experimental results show that SWSS can consistently improve the performance of popular MT evaluation metrics which are based on lexical similarity.
Meteor++ 2.0: Adopt Syntactic Level Paraphrase Knowledge into Machine Translation Evaluation
Yinuo Guo | Junfeng Hu
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
This paper describes Meteor++ 2.0, our submission to the WMT19 Metric Shared Task. The well known Meteor metric improves machine translation evaluation by introducing paraphrase knowledge. However, it only focuses on the lexical level and utilizes consecutive n-grams paraphrases. In this work, we take into consideration syntactic level paraphrase knowledge, which sometimes may be skip-grams. We describe how such knowledge can be extracted from Paraphrase Database (PPDB) and integrated into Meteor-based metrics. Experiments on WMT15 and WMT17 evaluation datasets show that the newly proposed metric outperforms all previous versions of Meteor.
Meteor++: Incorporating Copy Knowledge into Machine Translation Evaluation
Yinuo Guo | Chong Ruan | Junfeng Hu
Proceedings of the Third Conference on Machine Translation: Shared Task Papers
In machine translation evaluation, a good candidate translation can be regarded as a paraphrase of the reference. We notice that some words are always copied during paraphrasing, which we call copy knowledge. Considering the stability of such knowledge, a good candidate translation should contain all these words appeared in the reference sentence. Therefore, in this participation of the WMT’2018 metrics shared task we introduce a simple statistical method for copy knowledge extraction, and incorporate it into Meteor metric, resulting in a new machine translation metric Meteor++. Our experiments show that Meteor++ can nicely integrate copy knowledge and improve the performance significantly on WMT17 and WMT15 evaluation sets.