幽默在人类交流中扮演着重要角色,并大量存在于情景喜剧中。笑点(punchline)是情景喜剧实现幽默效果的形式之一,在情景喜剧笑点识别任务中,每条句子的标签代表该句是否为笑点,但是以往的笑点识别工作通常只通过建模上下文语义关系识别笑点,对标签的利用并不充分。为了充分利用标签序列中的信息,该文提出了一种结合条件随机场的单词级-句子级多任务学习方法,该方法在两方面进行了改进,首先将标签序列中相邻两个标签之间的转移关系看作幽默理论中不一致性的一种体现,并使用条件随机场学习这种转移关系。其次,由于通过相邻标签之间的转移关系以及上下文语义关系均能够学习到铺垫和笑点之间的不一致性,我们引入了多任务学习方法,让模型同时学习每条句子的句义、 组成每条句子的所有字符的词义、 单词级别的标签转移关系, 以及句子级别的标签转移关系,使模型能够结合两种关系信息提高笑点识别的性能。该文在CCL2020“小牛杯”幽默计算——情景喜剧笑点识别评测任务的英文数据集上进行实验,结果表明,该文提出的方法比同期最好的方法F1值上提高了3.2%,在情景喜剧幽默笑点识别任务上取得了最好的效果,并通过消融实验证明了上述两方面改进的有效性。
Abstract
Humor plays an important role in human communication and is abundant in sitcoms. Punchline is one of a form to achieve humorous effects in sitcoms. The existing punchlines recognition methods only recognize the punchline by modeling the contextual semantic relationship. In contrast, this paper proposes a new method based on multi-task learning model. First, we regard the transfer relationship between two tags as a manifestation of inconsistency in humor theory, and we use the conditional random field to learn this transfer relationship. Secondly, learning the transfer relationship between adjacent tags and the contextual semantic relationship can both capture the inconsistency between the setup and punchline, and we introduce the multi-task learning method to learn the meaning of each sentence, the meaning of all the characters that make up each sentence, the label transfer relationship at the word level and the label transfer relationship at the sentence level. Experiments on the English data set of CCL2020 ”Mavericks Cup” humorous calculation-sitcom punchlines recognition and evaluation task. show that the proposed method is 3.2% higher than the current best method, achieving the best effect on the punchlines recognition task.
关键词
情感分析 /
幽默计算 /
多任务学习 /
条件随机场
{{custom_keyword}} /
Key words
sentiment analysis /
humorous calculation /
multi-task learning /
conditional random field
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] BRIGHT W. International encyclopedia[J]. Psychology, 1992, 9: 151.
[2] RASKIN V. Semantic mechanisms of humor[M]. Springer Science & Business Media, 2012.
[3] BINSTED K, NIJHOLT A, STOCK O, et al. Computational humor[J]. IEEE Intelligent Systems, 2006, 21(2): 59-69.
[4] SUTTON C, MCCALLUM A. An introduction to conditional random fields for relational learning[J]. Introduction to Statistical Relational Learning, 2006, 2: 93-128.
[5] MIHALCEA R, STRAPPARAVA C. Making computers laugh: Investigations in automatic humor recognition[C]//Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, 2005: 531-538.
[6] YANG D, LAVIE A, DYER C, et al. Humor recognition and humor anchor extraction[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2015: 2367-2376.
[7] MORALES A, ZHAI C X. Identifying humor in reviews using background text sources[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2017: 492-501.
[8] CHEN P Y, SOO V W. Humor recognition using deep learning[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018: 113-117.
[9] ZHOU Y, JIANG J Y, ZHAO J, et al. “The boating store had its best sail ever”: Pronunciation-attentive contextualized pun recognition[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 813-822.
[10] DIAO Y, FAN X, YANG L, et al. Phonetics and ambiguity comprehension gated attention network for humor recognition[J]. Complexity, 2020: 1-9.
[11] XIE Y, LI J, PU P. Uncertainty and surprisal jointly deliver the punchline: exploiting incongruity-based features for humor recognition[J]. arXiv preprint arXiv:2012.12007, 2020.
[12] MIHALCEA R, STRAPPARAVA C, PULMAN S. Computational models for incongruity detection in humour[C]//Proceedings of the International Conference on Intelligent Text Processing and Computation-al Linguistics. Springer, Berlin, Heidelberg, 2010: 364-374.
[13] CATTLE A, MA X. Effects of semantic relatedness between setups and punchlines in twitter hashtag games[C]//Proceedings of the Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media, 2016: 70-79.
[14] BERTERO D, FUNG P. A long short-term memory framework for predicting humor in dialogues[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016: 130-135.
[15] CHOUBE A, SOLEYMANI M. Punchline detection using context-aware hierarchical multimodal fusion[C]//Proceedings of the International Conference on Multimodal Interaction, 2020: 675-679.
[16] DEVLIN J, CHANG M W, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 4171-4186.
[17] YANG Z, DAI Z, YANG Y, et al. XLNet: Generalized autoregressive pretraining for language understanding[J]. Advances in Neural Information Processing Systems, 2019, 32: 5753-5763.
[18] LIU Y, OTT M, GOYAL N, et al. RoBERTA: A robustly optimized bert pretraining approach[J]. arXiv preprint arXiv:1907.11692, 2019.
[19] GU J, WANG Z, KUEN J, et al. Recent advances in convolutional neural networks[J]. Pattern Recognition, 2018, 77: 354-377.
[20] GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[C]//Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 2011: 315-323.
[21] TAX D M J, DUIN R P W. Support vector domain description[J]. Pattern Recognition Letters, 1999, 20(11-13): 1191-1199.
[22] LI B, LIU Y, WANG X. Gradient harmonized single-stage detector[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(01): 8577-8584..
[23] YOON K. Convolutional neural networks for sentence classification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. 2014: 1746-1751.
[24] Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[25] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 6000-6010.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(62076046,62076051)
{{custom_fund}}
PDF(1165 KB)
