{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:12:09Z","timestamp":1766268729720,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789811955372"},{"type":"electronic","value":"9789811955389"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-981-19-5538-9_21","type":"book-chapter","created":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T11:02:45Z","timestamp":1667214165000},"page":"291-306","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Investigating the Impact of Pre-trained Language Models on Dialog Evaluation"],"prefix":"10.1007","author":[{"given":"Chen","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis Fernando","family":"D\u2019Haro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Friedrichs","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,1]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Yeh YT, Eskenazi M, Mehri S (2021) A comprehensive assessment of dialog evaluation metrics. arXiv:2106.03706","DOI":"10.18653\/v1\/2021.eancs-1.3"},{"key":"21_CR2","unstructured":"Mehri S, Choi J, D\u2019Haro LF, Deriu J, Eskenazi M, Gasic M, ... Zhang C (2022) Report from the NSF future directions workshop on automatic evaluation of dialog: research directions and challenges. arXiv:2203.10012"},{"key":"21_CR3","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, Vol 1 (Long and Short Papers), pp 4171\u20134186"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Zhang C, D\u2019Haro LF, Banchs RE, Friedrichs T, Li H (2021) Deep AM-FM: toolkit for automatic dialogue evaluation. In: Conversational dialogue systems for the next decade. Springer, Singapore, pp 53\u201369","DOI":"10.1007\/978-981-15-8395-7_5"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Mehri S, Eskenazi M (2020) USR: an unsupervised and reference free evaluation metric for dialog generation. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 681\u2013707","DOI":"10.18653\/v1\/2020.acl-main.64"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Zhang C, Lee G, D\u2019Haro LF, Li H (2021) D-score: holistic dialogue evaluation without reference. IEEE\/ACM Trans Audio Speech Lang Proc","DOI":"10.1109\/TASLP.2021.3074012"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Zhang C, Chen Y, D\u2019Haro LF, Zhang Y, Friedrichs T, Lee G, Li H (2021) DynaEval: unifying turn and dialogue level evaluation. In: Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing, pp 5676\u20135689","DOI":"10.18653\/v1\/2021.acl-long.441"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Zhang C, D\u2019Haro LF, Friedrichs T, Li H (2022) MDD-Eval: self-training on augmented data for multi-domain dialogue evaluation. arXiv:2112.07194","DOI":"10.1609\/aaai.v36i10.21420"},{"key":"21_CR9","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, ... Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Liu NF, Gardner M, Belinkov Y, Peters ME, Smith NA (2019) Linguistic knowledge and transferability of contextual representations. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, Vol 1 (Long and Short Papers), pp 1073\u20131094","DOI":"10.18653\/v1\/N19-1112"},{"key":"21_CR11","unstructured":"Tenney I, Xia P, Chen B, Wang A, Poliak A, McCoy RT, ... Pavlick E (2018) What do you learn from context? Probing for sentence structure in contextualized word representations. In: International conference on learning representations"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Zhou X, Zhang Y, Cui L, Huang D (2020) Evaluating commonsense in pre-trained language models. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, No 05, pp 9733\u20139740","DOI":"10.1609\/aaai.v34i05.6523"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Lan Z, Chen M, Goodman S, Gimpel K, Sharma P, Soricut R (2020) ALBERT: a lite BERT for self-supervised learning of language representations","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"21_CR14","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, ... Stoyanov V (2019) Roberta: a robustly optimized bert pretraining approach. arXiv:1907.11692"},{"key":"21_CR15","unstructured":"He P, Liu X, Gao J, Chen W (2020) Deberta: decoding-enhanced bert with disentangled attention. arXiv:2006.03654"},{"key":"21_CR16","unstructured":"Clark K, Luong MT, Le QV, Manning CD (2019) ELECTRA: pre-training text encoders as discriminators rather than generators. In: International conference on learning representations"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Zhang Y, Sun S, Galley M, Chen YC, Brockett C, Gao X, ... Dolan WB (2020) DIALOGPT: large-scale generative pre-training for conversational response generation. In: Proceedings of the 58th annual meeting of the association for computational linguistics: system demonstrations, pp 270\u2013278","DOI":"10.18653\/v1\/2020.acl-demos.30"},{"key":"21_CR18","unstructured":"Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I (2019) Language models are unsupervised multitask learners. OpenAI blog 1(8):9"},{"key":"21_CR19","unstructured":"Yang Z, Dai Z, Yang Y, Carbonell J, Salakhutdinov RR, Le QV (2019) Xlnet: generalized autoregressive pretraining for language understanding. Adv Neural Inf Proc Syst 32"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Reimers N, Gurevych I (2019) Sentence-BERT: sentence embeddings using siamese BERT-Networks. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 3982\u20133992","DOI":"10.18653\/v1\/D19-1410"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Bowman S, Angeli G, Potts C, Manning CD (2015) A large annotated corpus for learning natural language inference. In: Proceedings of the 2015 conference on empirical methods in natural language processing, pp 632\u2013642","DOI":"10.18653\/v1\/D15-1075"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Williams A, Nangia N, Bowman S (2018) A broad-coverage challenge corpus for sentence understanding through inference. In: Proceedings of the 2018 conference of the North American chapter of the association for computational linguistics: human language technologies, vol 1 (Long Papers), pp 1112\u20131122","DOI":"10.18653\/v1\/N18-1101"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Gao T, Yao X, Chen D (2021) SimCSE: simple contrastive learning of sentence embeddings. arXiv:2104.08821","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the association for computational linguistics, pp 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"21_CR25","unstructured":"Lin CY (2004) Rouge: a package for automatic evaluation of summaries. In: Text summarization branches out, pp 74\u201381"},{"key":"21_CR26","unstructured":"Zhang T, Kishore V, Wu F, Weinberger KQ, Artzi Y (2019) BERTScore: evaluating text generation with BERT. In: International conference on learning representations"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Sellam T, Das D, Parikh A (2020) BLEURT: learning robust metrics for text generation. In: Proceedings of the 58th annual meeting of the association for computational linguistics. pp 7881\u20137892","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Cervone A, Riccardi G (2020) Is this dialogue coherent? Learning from dialogue acts and entities. In: Proceedings of the 21th annual meeting of the special interest group on discourse and dialogue, pp 162\u2013174","DOI":"10.18653\/v1\/2020.sigdial-1.21"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Zhao T, Lala D, Kawahara T (2020) Designing precise and robust dialogue response evaluators. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 26\u201333","DOI":"10.18653\/v1\/2020.acl-main.4"}],"container-title":["Lecture Notes in Electrical Engineering","Conversational AI for Natural Human-Centric Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-19-5538-9_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T20:47:55Z","timestamp":1701290875000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-19-5538-9_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9789811955372","9789811955389"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-19-5538-9_21","relation":{},"ISSN":["1876-1100","1876-1119"],"issn-type":[{"type":"print","value":"1876-1100"},{"type":"electronic","value":"1876-1119"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}