{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T10:53:48Z","timestamp":1776077628661,"version":"3.50.1"},"reference-count":83,"publisher":"MIT Press - Journals","issue":"2","license":[{"start":{"date-parts":[[2022,3,8]],"date-time":"2022-03-08T00:00:00Z","timestamp":1646697600000},"content-version":"vor","delay-in-days":66,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Short texts (STs) present in a variety of scenarios, including query, dialog, and entity names. Most of the exciting studies in neural machine translation (NMT) are focused on tackling open problems concerning long sentences rather than short ones. The intuition behind is that, with respect to human learning and processing, short sequences are generally regarded as easy examples. In this article, we first dispel this speculation via conducting preliminary experiments, showing that the conventional state-of-the-art NMT approach, namely, Transformer (Vaswani et al. 2017), still suffers from over-translation and mistranslation errors over STs. After empirically investigating the rationale behind this, we summarize two challenges in NMT for STs associated with translation error types above, respectively: (1) the imbalanced length distribution in training set intensifies model inference calibration over STs, leading to more over-translation cases on STs; and (2) the lack of contextual information forces NMT to have higher data uncertainty on short sentences, and thus NMT model is troubled by considerable mistranslation errors. Some existing approaches, like balancing data distribution for training (e.g., data upsampling) and complementing contextual information (e.g., introducing translation memory) can alleviate the translation issues in NMT for STs. We encourage researchers to investigate other challenges in NMT for STs, thus reducing ST translation errors and enhancing translation quality.<\/jats:p>","DOI":"10.1162\/coli_a_00435","type":"journal-article","created":{"date-parts":[[2022,3,8]],"date-time":"2022-03-08T20:26:22Z","timestamp":1646771182000},"page":"321-342","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":24,"title":["Challenges of Neural Machine Translation for Short Texts"],"prefix":"10.1162","volume":"48","author":[{"given":"Yu","family":"Wan","sequence":"first","affiliation":[{"name":"NLP2CT Lab, University of Macau. nlp2ct.ywan@gmail.com"}]},{"given":"Baosong","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group. yangbaosong.ybs@alibaba-inc.com"}]},{"given":"Derek Fai","family":"Wong","sequence":"additional","affiliation":[{"name":"NLP2CT Lab, University of Macau. derekfw@um.edu.mo"}]},{"given":"Lidia Sam","family":"Chao","sequence":"additional","affiliation":[{"name":"NLP2CT Lab, University of Macau. lidiasc@um.edu.mo"}]},{"given":"Liang","family":"Yao","sequence":"additional","affiliation":[{"name":"Alibaba Group. yaoliang.yl@alibaba-inc.com"}]},{"given":"Haibo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group. zhanhui.zhb@alibaba-inc.com"}]},{"given":"Boxing","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group. boxing.cbx@alibaba-inc.com"}]}],"member":"281","published-online":{"date-parts":[[2022,6,9]]},"reference":[{"key":"2022061016074890200_bib1","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"ICLR","author":"Bahdanau","year":"2015"},{"key":"2022061016074890200_bib2","first-page":"42","article-title":"Neural machine translation of artwork titles using iconclass codes","volume-title":"LaTeCH-CLfL@COLING","author":"Banar","year":"2020"},{"key":"2022061016074890200_bib3","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1145\/1553374.1553380","article-title":"Curriculum learning","volume-title":"ICML","author":"Bengio","year":"2009"},{"key":"2022061016074890200_bib4","article-title":"Constraint translation candidates: A bridge between neural query translation and cross-lingual information retrieval","volume-title":"eCom@SIGIR","author":"Bi","year":"2020"},{"key":"2022061016074890200_bib5","article-title":"On identifiability in transformers","volume-title":"ICLR","author":"Brunner","year":"2020"},{"key":"2022061016074890200_bib6","doi-asserted-by":"publisher","first-page":"3042","DOI":"10.18653\/v1\/D18-1340","article-title":"Encoding gated translation memory into neural machine translation","volume-title":"EMNLP","author":"Cao","year":"2018"},{"key":"2022061016074890200_bib7","doi-asserted-by":"publisher","first-page":"6152","DOI":"10.18653\/v1\/2020.acl-main.547","article-title":"Neural graph matching networks for Chinese short text matching","volume-title":"ACL","author":"Chen","year":"2020"},{"key":"2022061016074890200_bib8","doi-asserted-by":"publisher","first-page":"103","DOI":"10.3115\/v1\/W14-4012","article-title":"On the properties of neural machine translation: Encoder-decoder approaches","volume-title":"SSST@EMNLP","author":"Cho","year":"2014"},{"issue":"3","key":"2022061016074890200_bib9","doi-asserted-by":"publisher","first-page":"239","DOI":"10.2478\/jesr-2019-0042","article-title":"Manipulating titles in translation","volume":"9","author":"Darwish","year":"2019","journal-title":"Journal of Educational and Social Research"},{"key":"2022061016074890200_bib10","doi-asserted-by":"publisher","first-page":"743","DOI":"10.18653\/v1\/P18-1069","article-title":"Confidence modeling for neural semantic parsing","volume-title":"ACL","author":"Dong","year":"2018"},{"issue":"2","key":"2022061016074890200_bib11","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cognitive Science"},{"key":"2022061016074890200_bib12","doi-asserted-by":"publisher","first-page":"123","DOI":"10.18653\/v1\/D19-5214","article-title":"Combining translation memory with neural machine translation","volume-title":"WAT@EMNLP-IJCNLP","author":"Eriguchi","year":"2019"},{"key":"2022061016074890200_bib13","first-page":"3752","article-title":"To case or not to case: Evaluating casing methods for neural machine translation","volume-title":"LREC","author":"Etchegoyhen","year":"2020"},{"key":"2022061016074890200_bib14","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","volume-title":"ICML","author":"Gal","year":"2016"},{"key":"2022061016074890200_bib15","doi-asserted-by":"publisher","first-page":"6111","DOI":"10.18653\/v1\/D19-1633","article-title":"Mask-predict: Parallel decoding of conditional masked language models","volume-title":"EMNLP-IJCNLP","author":"Ghazvininejad","year":"2019"},{"key":"2022061016074890200_bib16","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"ICML","author":"Guo","year":"2017"},{"key":"2022061016074890200_bib17","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/j.csl.2016.12.001","article-title":"Source sentence simplification for statistical machine translation","volume":"45","author":"Hasler","year":"2017","journal-title":"Computer Speech & Language"},{"key":"2022061016074890200_bib18","first-page":"151","article-title":"Improved neural machine translation with SMT features","volume-title":"AAAI","author":"He","year":"2016"},{"key":"2022061016074890200_bib19","first-page":"10477","article-title":"Using trusted data to train deep networks on labels corrupted by severe noise","volume-title":"NeurIPS","author":"Hendrycks","year":"2018"},{"issue":"8","key":"2022061016074890200_bib20","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"2022061016074890200_bib21","doi-asserted-by":"publisher","first-page":"6020","DOI":"10.1109\/ICASSP.2016.7472833","article-title":"Machine translation based data augmentation for Cantonese keyword spotting","volume-title":"ICASSP","author":"Huang","year":"2016"},{"key":"2022061016074890200_bib22","first-page":"2694","article-title":"Self-paced curriculum learning","volume-title":"AAAI","author":"Jiang","year":"2015"},{"key":"2022061016074890200_bib23","first-page":"1629","article-title":"Named entity translation with web mining and transliteration","volume-title":"IJCAI","author":"Jiang","year":"2007"},{"issue":"1","key":"2022061016074890200_bib24","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s10590-017-9203-5","article-title":"Neural machine translation for low-resource languages without parallel corpora","volume":"32","author":"Karakanta","year":"2018","journal-title":"Machine Translation"},{"key":"2022061016074890200_bib25","doi-asserted-by":"publisher","first-page":"24","DOI":"10.18653\/v1\/D19-6503","article-title":"When and why is document-level context useful in neural machine translation?","volume-title":"DiscoMT@EMNLP","author":"Kim","year":"2019"},{"key":"2022061016074890200_bib26","doi-asserted-by":"publisher","first-page":"379","DOI":"10.26615\/978-954-452-049-6_050","article-title":"Curriculum learning and minibatch bucketing in neural machine translation","volume-title":"RANLP","author":"Kocmi","year":"2017"},{"key":"2022061016074890200_bib27","first-page":"388","article-title":"Statistical significance tests for machine translation evaluation","volume-title":"EMNLP","author":"Koehn","year":"2004"},{"key":"2022061016074890200_bib28","doi-asserted-by":"publisher","first-page":"28","DOI":"10.18653\/v1\/W17-3204","article-title":"Six challenges for neural machine translation","volume-title":"NMT@ACL","author":"Koehn","year":"2017"},{"key":"2022061016074890200_bib29","doi-asserted-by":"publisher","DOI":"10.21236\/ADA461156","article-title":"Statistical phrase-based translation","volume-title":"HLT-NAACL","author":"Koehn","year":"2003"},{"key":"2022061016074890200_bib30","doi-asserted-by":"publisher","first-page":"92","DOI":"10.18653\/v1\/N18-3012","article-title":"Can neural machine translation be improved with user feedback?","volume-title":"NAACL-HLT (Industry Papers)","author":"Kreutzer","year":"2018"},{"key":"2022061016074890200_bib31","first-page":"21","article-title":"Improving sequence to sequence neural machine translation by utilizing syntactic dependency information","volume-title":"IJCNLP","author":"Le","year":"2017"},{"key":"2022061016074890200_bib32","doi-asserted-by":"publisher","first-page":"328","DOI":"10.18653\/v1\/D19-5543","article-title":"Improving neural machine translation robustness via data augmentation: Beyond back-translation","volume-title":"W-NUT@EMNLP","author":"Li","year":"2019"},{"key":"2022061016074890200_bib33","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv preprint arXiv:1907.11692"},{"key":"2022061016074890200_bib34","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1145\/3238147.3238190","article-title":"Neural-machine-translation-based commit message generation: How far are we?","volume-title":"ASE","author":"Liu","year":"2018"},{"key":"2022061016074890200_bib35","doi-asserted-by":"publisher","first-page":"1412","DOI":"10.18653\/v1\/D15-1166","article-title":"Effective approaches to attention-based neural machine translation","volume-title":"EMNLP","author":"Luong","year":"2015"},{"key":"2022061016074890200_bib36","first-page":"13498","article-title":"LET: Linguistic knowledge enhanced graph transformer for Chinese short text matching","volume-title":"AAAI","author":"Lyu","year":"2021"},{"key":"2022061016074890200_bib37","doi-asserted-by":"publisher","first-page":"3092","DOI":"10.18653\/v1\/N19-1313","article-title":"Selective attention for context-aware neural machine translation","volume-title":"NAACL-HLT","author":"Maruf","year":"2019"},{"key":"2022061016074890200_bib38","first-page":"4696","article-title":"When does label smoothing help?","volume-title":"NeurIPS","author":"M\u00fcller","year":"2019"},{"key":"2022061016074890200_bib39","doi-asserted-by":"publisher","first-page":"212","DOI":"10.18653\/v1\/W18-6322","article-title":"Correcting length bias in neural machine translation","volume-title":"WMT","author":"Murray","year":"2018"},{"key":"2022061016074890200_bib40","first-page":"1979","article-title":"Optimizing for sentence-level BLEU+1 yields short translations","volume-title":"COLING","author":"Nakov","year":"2012"},{"key":"2022061016074890200_bib41","doi-asserted-by":"publisher","first-page":"328","DOI":"10.18653\/v1\/K19-1031","article-title":"On the relation between position information and sentence length in neural machine translation","volume-title":"CoNLL","author":"Neishi","year":"2019"},{"key":"2022061016074890200_bib42","first-page":"10018","article-title":"Data diversification: An elegant strategy for neural machine translation","volume-title":"NeurIPS","author":"Nguyen","year":"2020"},{"key":"2022061016074890200_bib43","doi-asserted-by":"publisher","first-page":"160","DOI":"10.3115\/1075096.1075117","article-title":"Minimum error rate training in statistical machine translation","volume-title":"ACL","author":"Och","year":"2003"},{"key":"2022061016074890200_bib44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18653\/v1\/W18-6301","article-title":"Scaling neural machine translation","volume-title":"WMT","author":"Ott","year":"2018"},{"key":"2022061016074890200_bib45","doi-asserted-by":"publisher","first-page":"311","DOI":"10.3115\/1073083.1073135","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"ACL","author":"Papineni","year":"2002"},{"key":"2022061016074890200_bib46","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.18653\/v1\/N19-1119","article-title":"Competence-based curriculum learning for neural machine translation","volume-title":"NAACL:HLT","author":"Platanios","year":"2019"},{"key":"2022061016074890200_bib47","article-title":"Sequence level training with recurrent neural networks","volume-title":"ICLR","author":"Ranzato","year":"2016"},{"key":"2022061016074890200_bib48","doi-asserted-by":"publisher","first-page":"6849","DOI":"10.18653\/v1\/2020.acl-main.613","article-title":"Document translation vs. query translation for cross-lingual information retrieval in the medical domain","volume-title":"ACL","author":"Saleh","year":"2020"},{"key":"2022061016074890200_bib49","doi-asserted-by":"publisher","first-page":"3795","DOI":"10.18653\/v1\/N19-1380","article-title":"Cross-lingual transfer learning for multilingual task oriented dialog","volume-title":"NAACL-HLT","author":"Schuster","year":"2019"},{"key":"2022061016074890200_bib50","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.18653\/v1\/P16-1162","article-title":"Neural machine translation of rare words with subword units","volume-title":"ACL","author":"Sennrich","year":"2016"},{"key":"2022061016074890200_bib51","doi-asserted-by":"publisher","first-page":"464","DOI":"10.18653\/v1\/N18-2074","article-title":"Self-attention with relative position representations","volume-title":"NAACL-HLT","author":"Shaw","year":"2018"},{"key":"2022061016074890200_bib52","doi-asserted-by":"publisher","first-page":"1683","DOI":"10.18653\/v1\/P16-1159","article-title":"Minimum risk training for neural machine translation","volume-title":"ACL","author":"Shen","year":"2016"},{"key":"2022061016074890200_bib53","first-page":"223","article-title":"A study of translation edit rate with targeted human annotation","volume-title":"ATMA","author":"Snover","year":"2006"},{"key":"2022061016074890200_bib54","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1145\/3077136.3080691","article-title":"Translation of natural language query into keyword query using a RNN encoder-decoder","volume-title":"SIGIR","author":"Song","year":"2017"},{"issue":"56","key":"2022061016074890200_bib55","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"2022061016074890200_bib56","doi-asserted-by":"publisher","first-page":"35","DOI":"10.18653\/v1\/D19-6504","article-title":"Data augmentation using back-translation for context-aware neural machine translation","volume-title":"DiscoMT@EMNLP","author":"Sugiyama","year":"2019"},{"key":"2022061016074890200_bib57","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"NIPS","author":"Sutskever","year":"2014"},{"key":"2022061016074890200_bib58","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.18653\/v1\/E17-1100","article-title":"A multifaceted evaluation of neural versus phrase-based machine translation for 9 language directions","volume-title":"EACL","author":"Toral","year":"2017"},{"key":"2022061016074890200_bib59","doi-asserted-by":"publisher","first-page":"76","DOI":"10.18653\/v1\/P16-1008","article-title":"Modeling coverage for neural machine translation","volume-title":"ACL","author":"Tu","year":"2016"},{"key":"2022061016074890200_bib60","first-page":"5998","article-title":"Attention is all you need","volume-title":"NIPS","author":"Vaswani","year":"2017"},{"key":"2022061016074890200_bib61","doi-asserted-by":"publisher","first-page":"1198","DOI":"10.18653\/v1\/P19-1116","article-title":"When a good translation is wrong in context: Context-aware machine translation improves on deixis, ellipsis, and lexical cohesion","volume-title":"ACL","author":"Voita","year":"2019"},{"key":"2022061016074890200_bib62","doi-asserted-by":"publisher","first-page":"9130","DOI":"10.1609\/aaai.v34i05.6448","article-title":"Unsupervised neural dialect translation with commonality and diversity modeling","volume-title":"AAAI","author":"Wan","year":"2020"},{"key":"2022061016074890200_bib63","doi-asserted-by":"publisher","first-page":"1074","DOI":"10.18653\/v1\/2020.emnlp-main.80","article-title":"Self-paced learning for neural machine translation","volume-title":"EMNLP","author":"Wan","year":"2020"},{"key":"2022061016074890200_bib64","first-page":"33","article-title":"Semantics-enhanced task-oriented dialogue translation: A case study on hotel booking","volume-title":"IJCNLP","author":"Wang","year":"2017"},{"key":"2022061016074890200_bib65","doi-asserted-by":"publisher","first-page":"791","DOI":"10.18653\/v1\/D19-1073","article-title":"Improving back-translation with uncertainty-based confidence estimation","volume-title":"EMNLP-IJCNLP","author":"Wang","year":"2019"},{"key":"2022061016074890200_bib66","doi-asserted-by":"publisher","first-page":"3070","DOI":"10.18653\/v1\/2020.acl-main.278","article-title":"On the inference calibration of neural machine translation","volume-title":"ACL","author":"Wang","year":"2020"},{"key":"2022061016074890200_bib67","doi-asserted-by":"publisher","first-page":"856","DOI":"10.18653\/v1\/D18-1100","article-title":"SwitchOut: An efficient data augmentation algorithm for neural machine translation","volume-title":"EMNLP","author":"Wang","year":"2018"},{"key":"2022061016074890200_bib68","article-title":"Pay less attention with lightweight and dynamic convolutions","volume-title":"ICLR","author":"Wu","year":"2019"},{"key":"2022061016074890200_bib69","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016","journal-title":"arXiv preprint arXiv:1609.08144"},{"key":"2022061016074890200_bib70","doi-asserted-by":"publisher","first-page":"7322","DOI":"10.1609\/aaai.v33i01.33017322","article-title":"Quantifying uncertainties in natural language processing tasks","volume-title":"AAAI","author":"Xiao","year":"2019"},{"key":"2022061016074890200_bib71","article-title":"Leveraging advantages of interactive and non-interactive models for vector-based cross-lingual information retrieval","author":"Xu","year":"2021","journal-title":"arXiv preprint arXiv:2111.01992"},{"key":"2022061016074890200_bib72","doi-asserted-by":"publisher","first-page":"8435","DOI":"10.18653\/v1\/2021.emnlp-main.663","article-title":"Document graph for neural machine translation","volume-title":"EMNLP","author":"Xu","year":"2021"},{"key":"2022061016074890200_bib73","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.18653\/v1\/P19-1295","article-title":"Leveraging local and global patterns for self-attention networks","volume-title":"ACL","author":"Xu","year":"2019"},{"key":"2022061016074890200_bib74","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1609\/aaai.v33i01.3301387","article-title":"Context-aware self-attention networks","volume-title":"AAAI","author":"Yang","year":"2019"},{"key":"2022061016074890200_bib75","doi-asserted-by":"publisher","first-page":"4449","DOI":"10.18653\/v1\/D18-1475","article-title":"Modeling localness for self-attention networks","volume-title":"EMNLP","author":"Yang","year":"2018"},{"key":"2022061016074890200_bib76","doi-asserted-by":"publisher","first-page":"3054","DOI":"10.18653\/v1\/D18-1342","article-title":"Breaking the beam search curse: A study of (re-)scoring methods and stopping criteria for neural machine translation","volume-title":"EMNLP","author":"Yang","year":"2018"},{"key":"2022061016074890200_bib77","doi-asserted-by":"publisher","first-page":"4521","DOI":"10.18653\/v1\/2020.coling-main.399","article-title":"Domain transfer based data augmentation for neural query translation","volume-title":"COLING","author":"Yao","year":"2020"},{"key":"2022061016074890200_bib78","article-title":"Exploiting neural query translation into cross lingual information retrieval","volume-title":"eCom@SIGIR","author":"Yao","year":"2020"},{"key":"2022061016074890200_bib79","doi-asserted-by":"publisher","first-page":"521","DOI":"10.18653\/v1\/D16-1050","article-title":"Variational neural machine translation","volume-title":"EMNLP","author":"Zhang","year":"2016"},{"key":"2022061016074890200_bib80","doi-asserted-by":"publisher","first-page":"3953","DOI":"10.18653\/v1\/2021.naacl-main.309","article-title":"Multi-hop transformer for document-level machine translation","volume-title":"NAACL: HLT","author":"Zhang","year":"2021"},{"key":"2022061016074890200_bib81","article-title":"An empirical exploration of curriculum learning for neural machine translation","author":"Zhang","year":"2018","journal-title":"arXiv preprint arXiv:1811.00739"},{"key":"2022061016074890200_bib82","doi-asserted-by":"publisher","first-page":"4039","DOI":"10.24963\/ijcai.2020\/559","article-title":"Knowledge graphs enhanced neural machine translation","volume-title":"IJCAI","author":"Zhao","year":"2020"},{"key":"2022061016074890200_bib83","doi-asserted-by":"publisher","first-page":"6934","DOI":"10.18653\/v1\/2020.acl-main.620","article-title":"Uncertainty-aware curriculum learning for neural machine translation","volume-title":"ACL","author":"Zhou","year":"2020"}],"container-title":["Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/coli\/article-pdf\/48\/2\/321\/2029089\/coli_a_00435.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/coli\/article-pdf\/48\/2\/321\/2029089\/coli_a_00435.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T16:08:49Z","timestamp":1654877329000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/coli\/article\/48\/2\/321\/109902\/Challenges-of-Neural-Machine-Translation-for-Short"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":83,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,6,9]]},"published-print":{"date-parts":[[2022,6,9]]}},"URL":"https:\/\/doi.org\/10.1162\/coli_a_00435","relation":{},"ISSN":["0891-2017","1530-9312"],"issn-type":[{"value":"0891-2017","type":"print"},{"value":"1530-9312","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022]]},"published":{"date-parts":[[2022]]}}}