In this paper, Bi-LSTM is taken as the core, and CNN and one-way LSTM are combined to construct a multi-level English metaphor recognition model. Based on the idea of multi-feature synergy, dependency feature, semantic feature and part of speech feature are used to enrich the learning information of the model. Meanwhile, the random walk model is used to determine the emotional labels of candidate words, where a metaphorical emotion recognition method integrating emotional scenes is constructed. The experimental results verify that the model can improve the performance of different levels of metaphor recognition tasks.
MandelbrotBB. Selected topics in mathematics, physics, and finance originating in fractal geometry. Thinking In Patterns2004; 1–33.
2.
KusalSPatilSChoudrieJ, et al.A systematic review of applications of natural language processing and future challenges with special emphasis in text-based emotion detection. Artif Intell Rev2023; 56(12): 15129–15215.
3.
WangXTongY. Application of BERT+Attention model in emotion recognition of metizens during epidemic period. J Phys: Conf Ser2021; 1982(1): 012102.
4.
KhoshnamFBaraani-DastjerdiA. A dual framework for implicit and explicit emotion recognition: an ensemble of language models and computational linguistics. Expert Syst Appl2022; 198: 116686.
5.
WuFHuangYSongY, et al.Towards building a high-quality microblog-specific Chinese sentiment lexicon. Decis Support Syst2016; 87(C): 39–49.
6.
TurneyPDNeumanYAssafD, et al.Literal and metaphorical sense identification through concrete and abstract context. In: Proceedings of the conference on empirical methods in natural language processing (EMNLP 2011), July 27–31, 2011, pp. 680–690. Edinburgh, UK. Association for Computational Linguistics.
7.
TsvetkovYBoytsovLGershmanA. Metaphor detection with cross-lingual model transfer. In: Proceedings of the 52nd annual meeting of the association for computational linguistics (ACL 2014),Baltimore, MD, USA, June 22–27, 2014, I, pp. 248–258.
8.
BulatLClarkSShutovaE. Modelling metaphor with attribute-based semantics. In: Proccedings of the 15th conference of the European chapter of the association for computational linguistics (EACL 2017), Short Papers, April 3–7, 2017, 2, Valencia, Spain. pp. 523–528.
9.
LanlanPLiangyuHZhengyaL. Simulation of English part-of-speech recognition based on machine learning prediction algorithm. J Intell Fuzzy Syst2021; 40(2): 2409–2419.
10.
RaiSChakravertySTayalDK. Supervised metaphor detection using conditional random fields. In: Proceedings of the fourth workshop on metaphor in NLP, San Diego, 2016, pp. 18–27. Association for Computational Linguistics.
11.
PramanickMGuptaAMitraP. An LSTM-CRF based approach to token-level metaphor detection. In: Proceedings of the workshop on figurative language processing (FigLang 2018, at NAACL-HLT 2018), New Orleans, LA, USA, June 5–6, 2018, pp. 67–75. Association for Computational Linguistics.
12.
BizzoniYGhanimifardM. Bigrams and BiLSTMs: Two neural networks for sequential metaphor detection. In: Proceedings of the workshop on figurative language processing (FigLang 2018, at NAACL-HLT 2018), New Orleans, LA, USA, June 5–6, 2018, pp. 91–101. Association for Computational Linguistics.
13.
KuoKCarpuatM. Evaluating a Bi-LSTM model for metaphor detection in TOEFL essays. In: Proceedings of the second workshop on figurative language processing (FigLang 2020, at ACL 2020).July9, 2020, Online. pp.192–196.
14.
KlingerRDe ClercqOMohammadS, et al.IEST: WASSA-2018 implicit emotions shared task. In: Proceedings of the 9th workshop on computational approaches to subjectivity, sentiment and social media analysis (WASSA 2018, co-located with EMNLP 2018), October 31, 2018,Brussels, Belgium. pp. 31–42.
15.
RozentalAFleischerDKelrichZ. Amobee at IEST 2018: transfer learning from language models. In: Proceedings of WASSA 2018 (co-located with EMNLP 2018), October 31,2018. Brussels, Belgium. pp. 43–49.
16.
ChronopoulouAMargatinaABaziotisC, et al.NTUA-SLP at IEST 2018: ensemble of neural transfer methods for implicit emotion classification. In: Proceedings of WASSA 2018 (co-located with EMNLP 2018), October 31, 2018,Brussels, Belgium. pp. 57–64.
17.
RíssolaEGiachanouACrestaniF. USI-IR at IEST 2018: sequence modeling and pseudo-relevance feedback for implicit emotion detection In: Proceedings of WASSA 2018 (co-located with EMNLP 2018), October 31, 2018,Brussels, Belgium. pp. 231–234.
18.
WangWT. HGSGNLPat IEST 2018: an ensemble of machine learning and deep neural architectures for implicit emotion classification in tweets In: Proceedings of WASSA 2018 (co-located with EMNLP 2018), October 31, 2018,Brussels, Belgium. pp. 205–210.
19.
WeiJLiaoJYangZ, et al.BiLSTM with multi-polarity orthogonal attention for implicit sentiment analysis. Neurocomputing2020; 383: 165–173.
20.
DankersVReiMLewisM, et al.Modelling theinterplay of metaphor and emotion through multitask learning. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing, 2019, pp. 2218–2229.
21.
WanMAhrensKChersoniE, et al.Using conceptual norms for metaphor detection. In: Proceedings of the Second Workshop on Figurative Language Processing(FigLang 2020, at ACL 2020), Online, July 9, 2020. Association for Computational Linguistics, 2020; pp. 61–66.
22.
DongyuZZijuanCYingxiaL, et al.Identifying noun metaphors with transformer and BERT. Data Analysis and Knowledge Discovery2020; 4(4): 100–108.
23.
WuCHWuFZChenYB, et al.Neural metaphor detecting with CNN-LSTM model. In: Proceedings of the workshop on figurative language processing (FigLang 2018, at NAACL-HLT 2018), New Orleans, LA, USA, June 5–6, 2018, pp. 110–114. Association for Computational Linguistics.
