Abstract | ||
---|---|---|
Lexical-based metrics such as BLEU, NIST, and WER have been widely used in machine translation (MT) evaluation. However, these metrics badly represent semantic relationships and impose strict identity matching, leading to moderate correlation with human judgments. In this paper, we propose a novel MT automatic evaluation metric
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Semantic Travel Distance</italic>
(STD) based on word embeddings. STD incorporates both semantic and lexical features (word embeddings and
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</italic>
-gram and word order) into one metric. It measures the semantic distance between the hypothesis and reference by calculating the minimum cumulative cost that the embedded
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</italic>
-grams of the hypothesis need to “travel” to reach the embedded
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</italic>
-grams of the reference. Experiment results show that STD has a better and more robust performance than a range of state-of-the-art metrics for both the segment-level and system-level evaluation. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TASLP.2019.2922845 | IEEE/ACM Transactions on Audio, Speech, and Language Processing |
Keywords | Field | DocType |
Measurement,Semantics,Syntactics,NIST,Speech processing,Earth,Linguistics | Semantic similarity,BLEU,Word order,Computer science,Machine translation,Speech recognition,NIST,Correlation | Journal |
Volume | Issue | ISSN |
27 | 10 | 2329-9290 |
Citations | PageRank | References |
1 | 0.43 | 18 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pairui Li | 1 | 1 | 0.43 |
Chuan Chen | 2 | 54 | 9.82 |
Wujie Zheng | 3 | 254 | 15.92 |
Yuetang Deng | 4 | 59 | 4.81 |
Fanghua Ye | 5 | 3 | 1.15 |
Zibin Zheng | 6 | 3731 | 199.37 |