Metaphor Recognition Research Articles

Enhancing Metaphor Recognition of Literary Works in Applied Artificial Intelligence: A Multi-Level Approach with Bi-LSTM and CNN Fusion

ABSTRACT Understanding metaphorical language is essential for AI to interpret and communicate with humans accurately. However, current methods often struggle with the complexity of metaphors, making it difficult for AI systems to understand human language fully. Recognizing metaphors is challenging because they are frequently ambiguous and depend on context. In this study, we propose a new approach using a combination of Bi-directional Long Short-Term Memory (Bi-LSTM) networks, Convolutional Neural Networks (CNN), and uni-directional LSTM components to create a multi-level model for recognizing metaphors. Our model uses various features, including dependency, semantics, and part-of-speech, to improve its learning ability. Additionally, we introduce a new method for recognizing the emotional context of metaphors using a random walk model to determine the emotional tone of words. Our results show that this model improves performance in recognizing metaphors, enhancing AI’s ability to understand them.

Multi-modal Chinese Text Emotion Metaphor Computation Based on Mutual Information and Information Entropy

Metaphor is to express another thing through one thing, it is not only a rhetorical means, but also embodies a kind of analogical cognition and way of thinking of people. In recent years, metaphors have made more and more progress in Chinese language recognition, so their status has gradually risen. Chinese language sentiment analysis is a relatively difficult problem in language processing. Chinese language semantics is ambiguous and complex, so it is a great challenge to construct Chinese Emotion structure. In this paper, Chinese nouns and Chinese verbs are used as test samples to conduct metaphor test calculation. The test results of mutual information and information entropy show that for the sample metaphor calculation, the correct rate of individual words is less than 70%. The ratio between the macro-average of gerund words and the baseline fluctuates relatively large. The metaphor recognition of nouns is about 20% higher than the original test results and about 10% higher for verbs. It shows that under the action of mutual information and information entropy, the metaphor recognition performance of the basic structure of Chinese Emotion constructed from the perspective of metaphor is improved, and further illustrates the feasibility of mutual information and information entropy algorithm for building the basic structure.

Novel Metaphor Recognition, Interpretation and Construction: Barriers Face Kurds as Non-native English Speakers

This study which is titled ‘Novel Metaphor Recognition and Interpretation: Barriers Face Kurds as Non-native English speakers’ considers the recognition and the interpretation process difficulty of English novel metaphors. Novel metaphor is one of the most problematic types of metaphor in which its creation, recognition and interpretation usually require a higher level of efficiency. This sort of metaphor is highly connected with personal established conceptual systems which probably cause misunderstanding among interactants: native and non-native ones. This study aims at identifying novel metaphor, determining the nature of problems that Kurds as non-native English speakers face in recognizing novel metaphors in English. Thus, it would be helpful for both non-native English learners and speakers to improve their English comprehension and construction competence. The current study makes use of both quantitative and qualitative approach in the process of data analysis; and it has come up with the conclusion that the insufficiency in English communicative language competence, cognitive analysis proficiency, and background knowledge are three main problems in the process of recognizing and interpreting novel metaphors.

Perceptual Features of Abstract Images for Metaphor Generation

In this study, the roles of shape and color features in metaphor generation for abstract images were investigated through simulations using retrained convolutional neural network (CNN) models based on the pretrained CNN model, AlexNet. A computational experiment was conducted using five types of retrained object recognition models: an object recognition model using the cleaned ILSVRC-2012 training dataset, one to recognize more shape features using edge-detected images, one to recognize fewer shape features using blurred images, one to recognize fewer color features using grayscale images, and one to recognize only shape features using Canny edge-detected images. The metaphors generated for abstract images were collected from behavioral data obtained in a psychological experiment aimed at investigating the neural mechanisms of metaphor generation for abstract images. In the computational experiment, the simulation results of the five models for abstract images were compared to examine how well they predicted the objects used in the metaphors generated for abstract images in the psychological experiment. The edge-only model using Canny edge-detected images and the color-inhibited model using grayscale images exhibited better performance in metaphor recognition for abstract images than the control condition. This indicates that shape features play a more important role than color features in metaphor generation for abstract images. Furthermore, because the Canny edge detection technique extracts only object outlines that can be regarded as the caricaturization of objects, the caricatured images, based on the shape features of the abstract images, likely influence object recognition for metaphor generation.

A Study on Recognizing and Communicating Metaphors in Picture Book Creation in the Digital Age

Abstract Picture book creation has a rich metaphorical connotation, which is becoming more and more popular along with the development of digitalization. In this paper, the textual metaphors of picture book creation are extracted by combining the textual feature extraction model of the BERT pre-training model and HAN network, the ResNet50 network extracts the illustration metaphors of picture book creation, and the extracted metaphorical features are multimodal fused and recognized with the help of fully connected layer. In addition, a picture book metaphor dataset was constructed, and after analyzing the basic features of picture book metaphors, the effect of the constructed multimodal metaphor recognition was explored, and the recognition and communication of metaphors in picture book creation was studied. The results showed that the recognition accuracy in picture book creation ranged from 0.67 to 0.77, and the high degree of metaphor recognition in picture book creation showed a positive correlation with the average response time of communication, with the regression equation RT=138.45*IdentificationStd+1045.The results of the analysis of the metaphorical picture book creation pictures with textual references showed that the degree of communication comprehension (M=22.38. Std.=3.68), communication liking (M=94.86, Std.=13.58) and reaction time (M=82.44s, Std.=14.15s). Picture books facilitate better interactive communication through their metaphorical expression.

An Inquiry into the Translation of English Literary Metaphors Based on Text Mining Techniques

Abstract In this paper, the vector space model is used to convert the English literature text to be processed into a feature vector composed of feature items, and after adding weights to the feature items, it is composed into an N -dimensional space. After calculating the text similarity using the vector angle cosine, the knowledge base of English literature metaphors and an automatic recognition model are constructed by combining them with a Bayesian classification algorithm. Starting from the research purpose, we determine the research object and tools and analyze an example of English literary metaphor translation through the combination of simulation analysis and statistical analysis. The results show that the running speed of NBC is 10.2% faster than that of CFC, the speed of SOFMC is 70.1% faster than that of CFC, the accuracy rate of NBC is 32.8% higher than that of SOFMC, and that of CFC is 41.8% higher than that of SOFMC, and in terms of the combined running speed and accuracy rate, NBC performs better than SOFMC and CFC, i.e., it shows that the Bayesian classification algorithm is useful for dealing with English metaphor recognition and Chinese translation with excellent performance. In terms of lexical translation accuracy, the translated English literary metaphor texts with labeled lexical categories are significantly higher than the translated English literary metaphor texts without labeled lexical categories, with a difference value of 6.31%. This study extends the scope of cognitive linguistics research and offers a guiding reference value for translating English literary metaphors.

Paradoxical Metaphors in Poetic Song Discourse

The paper focuses on highlighting the differences between recognition and interpretation of active conceptual metaphors indicating universal truth and specific author’s metaphors grounded in his own life experience. It has been proven that due to their complexity, paradoxical nature, and the variability of language expressions metaphors are effectively used to deliver universal truth in poetic discourse, namely in bard song lyrics and singing poetry. The analysis is based on the material of Leonard Cohen’s posthumous album “Thanks for The Dance”. The well-known features of active metaphors such as clarity and communicative power are opposed to unique paradoxical and mirroring metaphors used by the author to impose multiple levels of metaphor recognition in poetics song discourses. The metaphorical coding of poetry is achieved through establishing an intercode agreement between the recipients and the poet.

Exploring the Role of Part of Speech in the Formation of Conceptual Metaphors

Most scholarly research on conceptual metaphor has been concerned with measuring the breadth with which a given conceptual metaphor is used in language, while there has been a lack of literature on how such metaphors are formulated in the first place or what parts of speech are typically involved in their construction. This paper aims to research the influence of word class on metaphor recognition and construction. Results of the study show that high-frequency noun keywords, especially those that denote abstract ideas and concepts, tend to be employed as major target domains for conceptual metaphors in discourse. In addition, they indicate that linguistic expressions of conceptual metaphors tend to take the form of verbs. They also prove that using a corpus-based approach offers a reliable means for determining what constitutes a conceptual metaphor.

A corpus-based study on metaphors of war in maritime English news

This study analyzes the use of WAR metaphors in maritime English news and thus explores the relationship between metaphorical expressions and their collocates by using corpus analysis tools and a semi-artificial metaphor recognition method. Qualitative analysis indicates that three types of WAR metaphors are employed, FRONTLINE, BULLET and INVASION. Additionally, we investigate the regularity of the metaphor words and find that these metaphorical expressions often occur with less frequently used content words, and typically collocate with words that are found in the keyword list. Our results also demonstrate that while keywords serve as indicators of the text’s main content, metaphors act as implicit indicators of the underlying attitudes conveyed in the text.

Metaphor Recognition Method based on Graph Neural Network

This Metaphor is a very common language phenomenon. Human language often uses metaphor to express emotion, and metaphor recognition is also an important research content in the field of NLP. Official documents are a serious style and do not usually use rhetorical sentences. This paper aims to identify rhetorical metaphorical sentences in official documents. The use of metaphors in metaphorical sentences depends on the context. Based on this linguistic feature, this paper proposes a BertGAT model, which uses Bert to extract semantic features of sentences and transform the dependency relationship between Chinese text and sentences into connected graphs. Finally, the graph attention neural network is used to learn semantic features and syntactic structure information to complete sentence metaphor recognition. The proposed model is tested on the constructed domain dataset and the sentiment public dataset respectively. Experimental results show that the method proposed in this paper can effectively improve the recognition ability of metaphorical emotional sentences.

Analysis of Multimodal Metaphor and Metonymy in China-related Front Covers of The Economist

Most of previous studies on metaphor and metonymy at home and abroad are limited to the verbal mode, ignoring non-verbal mode. A few studies on multimodality mainly focus on the basic role of metonymy, lacking adequate attention to the representation of multimodal metaphor and metonymy, and the role in constructing specific images from the perspective of social pragmatic function. This paper takes the cover cartoons of the Economist as data to analyze the recognition and representation of multimodal metaphors and metonymy. Then, from the perspective of social pragmatics, we quantitatively analyze the symbolic signs of the source domain of the covers in the past decade, and reveal their roles in constructing the image of China. This research is to understand the linguistic approach of “how to reconstruct China’s image” and “how to construct” by international media, which can provide implication for Chinese dissemination and diplomatic strategy in the digital age.

Evaluation Method of English Learning Engagement Based on Wireless Communication Network and Big Data

The existing English learning engagement assessment methods still have some deficiencies, which cannot predict students’ interest in English learning, and the teaching effect is not good enough, resulting in the improvement of students’ performance which is not obvious. Therefore, an English learning engagement assessment method based on wireless communication network and big data is proposed. Firstly, build a mobile wireless communication network model, analyze the metaphor processing and evaluation methods adopted by English learners according to big data, and realize the acquisition and interpretation of metaphor meaning through three steps: the establishment of metaphor knowledge base, the analysis and description of metaphor language, and the classification and recognition of metaphor; build an evaluation framework based on wireless communication network and big data, propose a Java application platform for English learning engagement evaluation, and realize the English learning engagement evaluation method. The experimental research shows that the evaluation method has good stability, short evaluation time, and high efficiency and has practical application effect.

Metaphor Recognition of English Learners Based on Machine Learning Algorithm

The advantage of machine learning algorithm lies in predicting the semantic category of new language features according to the joint probability distribution of existing language features and their semantic categories. Based on a machine learning algorithm, this paper studies the metaphor recognition of English learners. The process of metaphor recognition is described as the classification of metaphorical meaning and literal meaning. Metaphor modeling is carried out by maximum entropy and naive Bayes. Check whether the sentences in the verification set contain the language rules in the knowledge base, and semantically identify the words in the sentences according to the annotations of the knowledge base. For sentences that do not meet the language rules of the knowledge base, the machine learning module is used for further verification and identification. Based on the comprehensive features of context words and parts of speech, the ideal window of maximum entropy recognition is determined, and then the left and right position features are introduced to improve the experimental effect. In the comparative experiments of the three models, this model has obvious advantages in English learners’ metaphor recognition. Its recognition accuracy is high, and it has certain practical value.

РАСПОЗНАВАНИЕ НОВЫХ МЕТАФОР В РАЗНЫХ СИНТАКСИЧЕСКИХ ПОЗИЦИЯХ В РОДНОМ И ИНОСТРАННОМ ЯЗЫКЕ: РЕЗУЛЬТАТЫ ОКУЛОГРАФИЧЕСКОГО ИССЛЕДОВАНИЯ

The study explores gaze behavior in novel metaphor recognition in L1 and L2 as affected by the syntactic position of a metaphor; therefore, we test the contrastive role of syntactic foregrounding in information processing. Following cognitive linguistic theories of foregrounding [Talmy 2000; Iriskhanova 2014], we expect its effects on both gaze behavior and metaphor recognition in subject and predicate positions. Following the theories exploring the role of cognitive mechanisms of analogical reasoning and associative fluency [Gentner & Bowdler 2008; Holyoak & Stamenković 2020] in L1 and L2 [Littlemore et al. 2011, Heredia and Cieślicka 2016], we expect differences in L1 and L2 participants in reading and recognition of novel metaphors. The results show that novel metaphor recognition in less foregrounded syntactic position is better in both L1 and L2, which might be explained by the fact that in syntactically foregrounded positions the participants were more likely to search for the source of metaphor, rather than for its target. Additionally, we revealed significant differences in L1 and L2 gaze performance in mean fixation duration, which is higher in syntactically foregrounded position for L2, which might be explained by higher effects of syntactic foregrounding in L2.

SCHӦPFUNG, VERSTÄNDNISUND ERKENNENDERINDIVIDUELLEN AUTORENMETAPHER IM RAHMEN DES KÜNSTLERISCHEN DISKURSES

The article discusses the issues of generating, understanding and recognizing an individual author’s metaphor within the framework of artistic discourse. The subjectivity of metaphorical modeling the world is understood as an individual and selective understanding of it which determines the peculiarities of its perception. The issues of the connection of the process of metaphorical modeling with intuition and cognition are considered. The author makesan assumption about four possible variants of the process of generating metaphors. It is emphasized that in the process of metaphorical interpretation of the world, the personal-physiological context, the historical, socio-cultural context of the author, the situational context, as well as the context of discourse become dominant. It is noted that for successful identification and understanding of a metaphor, it is necessary, among otherthings, to havecommon knowledge about the world in the form of cognitive images of consciousness and the author’s contexts listed above, which prevail in the process of his individual creativity when generating a metaphor. The possibilities and problems of automatic recognition and identification of metaphors are considered.

ASSOCIATIONS WITH AND RECOGNITION OF PRODUCT METAPHORS

ASSOCIATIONS WITH AND RECOGNITION OF PRODUCT METAPHORS

Lost in Machine Translation: Contextual Linguistic Uncertainty

The article considers the issues related to the semantic, grammatical, stylistic and technical difficulties currently present in machine translation and compares its four main approaches: Rule-based (RBMT), Corpora-based (CBMT), Neural (NMT), and Hybrid (HMT). It also examines some "open systems", which allow the correction or augmentation of content by the users themselves ("crowdsourced translation"). The authors of the article, native speakers presenting different countries (Russia, Greece, Malaysia, Japan and Serbia), tested the translation quality of the most representative phrases from the English, Russian, Greek, Malay and Japanese languages by using different machine translation systems: PROMT (RBMT), Yandex. Translate (HMT) and Google Translate (NMT). The test results presented by the authors show low "comprehension level" of semantic, linguistic and pragmatic contexts of translated texts, mistranslations of rare and culture-specific words,unnecessary translation of proper names, as well as a low rate of idiomatic phrase and metaphor recognition. It is argued that the development of machine translation requires incorporation of literal, conceptual, and content-and-contextual forms of meaning processing into text translation expansion of metaphor corpora and contextological dictionaries, and implementation of different types and styles of translation, which take into account gender peculiarities, specific dialects and idiolects of users. The problem of untranslatability ('linguistic relativity') of the concepts, unique to a particular culture, has been reviewed from the perspective of machine translation. It has also been shown, that the translation of booming Internet slang, where national languages merge with English, is almost impossible without human correction.

Harnessing the power of metaphor: uncovering a hidden language of interoperability within the natural speech of emergency managers

This study harnesses the non-literal communicative power of metaphor to enable quicker transferal of rich detailed information within and across emergency management organisations to promote multi-agency interoperability. A series of inductive semi-structured interviews with emergency managers from the UK and USA were completed. The collated data was then analysed with content and metaphorical analysis to create two theories. First, the Trivial Pursuit Pie, a conceptual metaphor that demonstrates the interoperability problem whereby intrinsic barriers within Command and Control restrict interoperability. This metaphor can be used as a learning tool to heighten awareness of barriers to multi-agency interoperability in both academic and practitioner environments. Secondly, the theory of interoperability metaphors (TIM) provides a metaphor-based lexicon for interoperability grounded in the natural language of emergency managers. TIM stimulates interoperability through the recognition and usage of linguistic metaphors to develop shared meanings and understanding.

Harnessing the power of metaphor: uncovering a hidden language of interoperability within the natural speech of emergency managers

This study harnesses the non-literal communicative power of metaphor to enable quicker transferal of rich detailed information within and across emergency management organisations to promote multi-agency interoperability. A series of inductive semi-structured interviews with emergency managers from the UK and USA were completed. The collated data was then analysed with content and metaphorical analysis to create two theories. First, the Trivial Pursuit Pie, a conceptual metaphor that demonstrates the interoperability problem whereby intrinsic barriers within Command and Control restrict interoperability. This metaphor can be used as a learning tool to heighten awareness of barriers to multi-agency interoperability in both academic and practitioner environments. Secondly, the theory of interoperability metaphors (TIM) provides a metaphor-based lexicon for interoperability grounded in the natural language of emergency managers. TIM stimulates interoperability through the recognition and usage of linguistic metaphors to develop shared meanings and understanding.

ОСОБЕННОСТИ РАЗВИТИЯ ОБРАЗНОСТИ РЕЧИ СТАРШИХ ДОШКОЛЬНИКОВ НА МАТЕРИАЛЕ МЕТАФОРИЧЕСКИХ ЗАГАДОК

The issue of formation of speech culture of senior preschoolers is one of the most important tasks of modern education. The paper shows the role of communicative competence as the tool for the socialization of a preschooler personality, mental formation and development of thinking of senior preschoolers. The author says about the comprehensiveness of the notion of “imagery” in modern science, notes that the emotional-expressive tone becomes the unique characteristic of imagery speech. The paper pays particular attention to the senior preschool age as the most sensitive period of formation of imagery speech and understanding of imagery means by the senior preschoolers using the material of metaphorical riddles. The process of development of speech imagery of senior preschool children on the material of metaphorical riddles is the subject of the study. The paper analyzes the data of ascertaining experiment, which was aimed at the study of special aspects of understanding and application of metaphors and other imagery means by senior preschool children. The author gives the results of the experiment showing the nature of difficulties during the interpretation of metaphors by children and self-selection of metaphors for the description of an object. In particular, the author notes the difficulties in understanding the figurative meanings of the words, recognition of metaphor in the text, understanding its figurative meaning and difficulties in creation own metaphorical riddles. These data allow making the conclusion that children under test have the insufficient level of development of speech imagery. At the same time, the individual cases of proper metaphor interpretation allow assuming that the formation of imagery speech of preschool children is possible using metaphorical riddles. The development of linguo-motivational space through the use of modern interactive methods and pedagogical techniques is the precondition for such formation.