Results of the WMT19 Metrics Shared Task: Segment-Level and Strong MT Systems Pose Big Challenges

This paper presents the results of the WMT19 Metrics Shared Task. Participants were asked to score the outputs of the translations systems competing in the WMT19 News Translation Task with automatic metrics. 13 research groups submitted 24 metrics, 10 of which are reference-less “metrics” and constitute submissions to the joint task with WMT19 Quality Estimation Task, “QE as a Metric”. In addition, we computed 11 baseline metrics, with 8 commonly applied baselines (BLEU, SentBLEU, NIST, WER, PER, TER, CDER, and chrF) and 3 reimplementations (chrF+, sacreBLEU-BLEU, and sacreBLEU-chrF). Metrics were evaluated on the system level, how well a given metric correlates with the WMT19 official manual ranking, and segment level, how well the metric correlates with human judgements of segment quality. This year, we use direct assessment (DA) as our only form of manual evaluation.

[1]  H. Ney,et al.  A novel string-to-string distance measure with applications to machine translation evaluation , 2003, MTSUMMIT.

[2]  Philipp Koehn,et al.  Statistical Significance Tests for Machine Translation Evaluation , 2004, EMNLP.

[3]  Chris Callison-Burch,et al.  Paraphrasing with Bilingual Parallel Corpora , 2005, ACL.

[4]  Chris Brockett,et al.  Automatically Constructing a Corpus of Sentential Paraphrases , 2005, IJCNLP.

[5]  Philipp Koehn,et al.  Manual and Automatic Evaluation of Machine Translation between European Languages , 2006, WMT@HLT-NAACL.

[6]  Hermann Ney,et al.  CDER: Efficient MT Evaluation Using Block Movements , 2006, EACL.

[7]  Cyril Goutte.  Automatic Evaluation of Machine Translation Quality , 2006 .

[8]  Lidia S. Chao,et al.  LEPOR: A Robust Evaluation Metric for Machine Translation with Augmented Factors , 2012, COLING.

[9]  Ondrej Bojar,et al.  Results of the WMT14 Metrics Shared Task , 2013 .

[10]  Xiaodong Zeng,et al.  Language-independent Model for Machine Translation Evaluation with Reinforced Factors , 2013, MTSUMMIT.

[11]  Alon Lavie,et al.  Meteor Universal: Language Specific Translation Evaluation for Any Target Language , 2014, WMT@ACL.

[12]  Philipp Koehn,et al.  Results of the WMT15 Metrics Shared Task , 2015, WMT@EMNLP.

[13]  Philipp Koehn,et al.  Ten Years of WMT Evaluation Campaigns: Lessons Learnt , 2016 .

[14]  Hermann Ney,et al.  CharacTer: Translation Edit Rate on Character Level , 2016, WMT.

[15]  Zhen-Hua Ling,et al.  Enhanced LSTM for Natural Language Inference , 2016, ACL.

[16]  Ondrej Bojar,et al.  Results of the WMT17 Metrics Shared Task , 2017, WMT.

[17]  Ondrej Bojar,et al.  Results of the WMT18 Metrics Shared Task: Both characters and embeddings achieve good performance , 2018, WMT.

[18]  Chi-kiu Lo,et al.  YiSi - a Unified Semantic MT Quality Evaluation and Estimation Metric for Languages with Different Levels of Available Resources , 2019, WMT.

[19]  Mamoru Komachi,et al.  Filtering Pseudo-References by Paraphrasing for Automatic Evaluation of Machine Translation , 2019, WMT.

[20]  Mark Fishel,et al.  Quality Estimation and Translation Metrics via Pre-trained Word and Sentence Embeddings , 2019, WMT.

[21]  Lucia Specia,et al.  WMDO: Fluency-based Word Mover’s Distance for Machine Translation Evaluation , 2019, WMT.

[22]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[23]  Marta R. Costa-jussà,et al.  Findings of the 2019 Conference on Machine Translation (WMT19) , 2019, WMT.