scholarly journals Similarity is closeness: Using distributional semantic spaces to model similarity in visual and linguistic metaphors

2019 ◽  
Vol 15 (1) ◽  
pp. 101-137 ◽  
Author(s):  
Marianna Bolognesi ◽  
Laura Aina
Keyword(s):  
Semantic Similarity ◽  
Semantic Space ◽  
Visual Metaphors ◽  
Conceptual Structures ◽  
Two Samples ◽  
Average Similarity ◽  
Semantic Spaces ◽  
Model Similarity ◽  
Compare And Contrast ◽  
Degree Of Similarity

Abstract The semantic similarity that characterizes two terms aligned in a metaphor is here analysed through a corpus-based distributional semantic space. We compare and contrast two samples of metaphors, representative of visual and linguistic modality of expressions respectively. Popular theories of metaphor claim that metaphors transcend their modality to influence conceptual structures, thus suggesting that different modalities of expression would typically express the same conceptual metaphors. However, we show substantial differences in the degree of similarity captured by the distributional semantic space with regard to the modality of expression (higher similarity for linguistic metaphors than for visual ones). We argue that this is due to two possible variables: Conventionality (linguistic metaphors are typically conventional, while visual are not) and Complexity (visual metaphors have modality-specific inner complexities that penalize the degree of similarity between metaphor terms captured by a language-based model). Finally, we compare the similarity scores of our original formulations with those obtained from different possible verbalizations of the same metaphors (acquired by replacing the metaphor terms with their semantic neighbours). We show that while this operation does not affect the average similarity between metaphor terms for visual metaphors, the similarity changes significantly in linguistic metaphors. These results are discussed here.

scholarly journals Gender differences in subjective representations about artificial bilingualism

2020 ◽  
Author(s):  
Antonina Rafikova ◽  
Anatoly Voronin
Keyword(s):  
Gender Differences ◽  
Foreign Language ◽  
Learning Process ◽  
Semantic Space ◽  
Original Method ◽  
Interpersonal Perception ◽  
Pool Data ◽  
Two Samples ◽  
Semantic Spaces ◽  
Content Semantic

<p>Many studies have been devoted to bilingualism but issue of subjective representations about bilingualism has been little explored. The present study examined the results of the psychosemantic research of men’s and women’s subjective representations about people associated with the foreign language (FL) learning process, in other words, artificial bilingual (AB) development. The original method of Specific semantic differential was used to study and reconstruct the system of meanings that underlie the interpersonal perception of people included in the FL learning process. Results showed that the semantic spaces of subjective representations about people associated with the FL learning process, have the same dimension, but differ in content: semantic space for males is based on factors “authority – ordinariness”, “unpleasant – agreeable” and “courage – caution”; for females – “enthusiasm – apathy”, “unpleasant – agreeable” and “modesty – arrogance”. The novelty of the study lies in the use of the pool data method as a method for comparing factors of the structures of two samples, which allows us to identify gender differences in interpersonal perception: males perceive people included in the FL learning process as more active, responsible, mobile and hardworking, females - as more level-headed, indifferent and distant.</p>

Automatic discovery of word semantic relations using paraphrase alignment and distributional lexical semantics analysis

2010 ◽  
Vol 16 (4) ◽  
pp. 439-467 ◽  
Author(s):  
GAËL DIAS ◽  
RUMEN MORALIYSKI ◽  
JOÃO CORDEIRO ◽  
ANTOINE DOUCET ◽  
HELENA AHONEN-MYKA
Keyword(s):  
Information Extraction ◽  
Semantic Similarity ◽  
Local Environment ◽  
Search Space ◽  
Semantic Space ◽  
Semantic Relations ◽  
Take The Best ◽  
Automatic Discovery ◽  
Semantic Spaces ◽  
Semantic Space Models

AbstractThesauri, which list the most salient semantic relations between words, have mostly been compiled manually. Therefore, the inclusion of an entry depends on the subjective decision of the lexicographer. As a consequence, those resources are usually incomplete. In this paper, we propose an unsupervised methodology to automatically discover pairs of semantically related words by highlighting their local environment and evaluating their semantic similarity in local and global semantic spaces. This proposal differs from all other research presented so far as it tries to take the best of two different methodologies, i.e. semantic space models and information extraction models. In particular, it can be applied to extract close semantic relations, it limits the search space to few, highly probable options and it is unsupervised.

scholarly journals Gender differences in subjective representations about artificial bilingualism

2020 ◽  
Author(s):  
Antonina Rafikova ◽  
Anatoly Voronin
Keyword(s):  
Gender Differences ◽  
Foreign Language ◽  
Learning Process ◽  
Semantic Space ◽  
Original Method ◽  
Interpersonal Perception ◽  
Pool Data ◽  
Two Samples ◽  
Semantic Spaces ◽  
Content Semantic

<p>Many studies have been devoted to bilingualism but issue of subjective representations about bilingualism has been little explored. The present study examined the results of the psychosemantic research of men’s and women’s subjective representations about people associated with the foreign language (FL) learning process, in other words, artificial bilingual (AB) development. The original method of Specific semantic differential was used to study and reconstruct the system of meanings that underlie the interpersonal perception of people included in the FL learning process. Results showed that the semantic spaces of subjective representations about people associated with the FL learning process, have the same dimension, but differ in content: semantic space for males is based on factors “authority – ordinariness”, “unpleasant – agreeable” and “courage – caution”; for females – “enthusiasm – apathy”, “unpleasant – agreeable” and “modesty – arrogance”. The novelty of the study lies in the use of the pool data method as a method for comparing factors of the structures of two samples, which allows us to identify gender differences in interpersonal perception: males perceive people included in the FL learning process as more active, responsible, mobile and hardworking, females - as more level-headed, indifferent and distant.</p>

Pembobotan Berdasarkan Tingkat Kesamaan Semantik pada Metode Fuzzy Semi-Supervised Co-Clustering untuk Pengelompokkan Dokumen Teks

2014 ◽  
Vol 6 (2) ◽  
pp. 46-51
Author(s):  
Galang Amanda Dwi P. ◽  
Gregorius Edwadr ◽  
Agus Zainal Arifin
Keyword(s):  
Supervised Learning ◽  
Semantic Similarity ◽  
The Other ◽  
Classification Result ◽  
Document Similarity ◽  
The Matrix ◽  
Index Terms ◽  
Membership Value ◽  
Degree Of Similarity

Nowadays, a large number of information can not be reached by the reader because of the misclassification of text-based documents. The misclassified data can also make the readers obtain the wrong information. The method which is proposed by this paper is aiming to classify the documents into the correct group.  Each document will have a membership value in several different classes. The method will be used to find the degree of similarity between the two documents is the semantic similarity. In fact, there is no document that doesn’t have a relationship with the other but their relationship might be close to 0. This method calculates the similarity between two documents by taking into account the level of similarity of words and their synonyms. After all inter-document similarity values obtained, a matrix will be created. The matrix is then used as a semi-supervised factor. The output of this method is the value of the membership of each document, which must be one of the greatest membership value for each document which indicates where the documents are grouped. Classification result computed by the method shows a good value which is 90 %. Index Terms - Fuzzy co-clustering, Heuristic, Semantica Similiarity, Semi-supervised learning.

scholarly journals Word Embeddings as Metric Recovery in Semantic Spaces

2016 ◽  
Vol 4 ◽  
pp. 273-286 ◽  
Author(s):  
Tatsunori B. Hashimoto ◽  
David Alvarez-Melis ◽  
Tommi S. Jaakkola
Keyword(s):  
Random Walks ◽  
Manifold Learning ◽  
State Of The Art ◽  
Inductive Reasoning ◽  
Semantic Space ◽  
Word Embedding ◽  
Word Embeddings ◽  
Recovery Algorithm ◽  
Series Completion ◽  
Semantic Spaces

Continuous word representations have been remarkably useful across NLP tasks but remain poorly understood. We ground word embeddings in semantic spaces studied in the cognitive-psychometric literature, taking these spaces as the primary objects to recover. To this end, we relate log co-occurrences of words in large corpora to semantic similarity assessments and show that co-occurrences are indeed consistent with an Euclidean semantic space hypothesis. Framing word embedding as metric recovery of a semantic space unifies existing word embedding algorithms, ties them to manifold learning, and demonstrates that existing algorithms are consistent metric recovery methods given co-occurrence counts from random walks. Furthermore, we propose a simple, principled, direct metric recovery algorithm that performs on par with the state-of-the-art word embedding and manifold learning methods. Finally, we complement recent focus on analogies by constructing two new inductive reasoning datasets—series completion and classification—and demonstrate that word embeddings can be used to solve them as well.

Orientations to Child Management: A Comparison of Teacher-Counsellors and High School Principals with Regard to Child versus Institutional Advocacy

1987 ◽  
Vol 17 (4) ◽  
pp. 131-136 ◽  
Author(s):  
A.R.L. Dawes ◽  
D.R. Donald
Keyword(s):  
High School ◽  
High School Principals ◽  
School Principals ◽  
Structural Constraints ◽  
Child Management ◽  
Cape Peninsula ◽  
Two Samples ◽  
Institutional Advocacy ◽  
High Degree ◽  
Degree Of Similarity

Twenty teacher-counsellors and twenty principals from a socio-economic spectrum of white co-educational high schools in the Cape Peninsula participated in the study. A repertory grid comprising a set of child management situations to which subjects were required to respond in terms of a series of bipolar constructs reflecting child-centred or institutionally orientated problem-solving action was used. Consensus grids were compiled from the two samples in order to describe their responses and the two consensus grids were correlated in order to assess their degree of similarity. Results showed a high degree of consistency between the two samples in their likely management of problems. Further, teacher-counsellors were shown to be unlikely to act consistently as child advocates. Reasons for these findings are discussed with reference to possible structural constraints on the teacher- counsellor's role.

scholarly journals Effectiveness of data-driven induction of semantic spaces and traditional classifiers for sarcasm detection

2019 ◽  
Vol 25 (2) ◽  
pp. 257-285 ◽  
Author(s):  
Mattia Antonino Di Gangi ◽  
Giosué Lo Bosco ◽  
Giovanni Pilato
Keyword(s):  
Machine Learning ◽  
Scientific Community ◽  
Semantic Space ◽  
Machine Learning Algorithms ◽  
Data Driven ◽  
Detection Problem ◽  
Everyday Language ◽  
Text Understanding ◽  
The Social ◽  
Semantic Spaces

AbstractIrony and sarcasm are two complex linguistic phenomena that are widely used in everyday language and especially over the social media, but they represent two serious issues for automated text understanding. Many labeled corpora have been extracted from several sources to accomplish this task, and it seems that sarcasm is conveyed in different ways for different domains. Nonetheless, very little work has been done for comparing different methods among the available corpora. Furthermore, usually, each author collects and uses their own datasets to evaluate his own method. In this paper, we show that sarcasm detection can be tackled by applying classical machine-learning algorithms to input texts sub-symbolically represented in a Latent Semantic space. The main consequence is that our studies establish both reference datasets and baselines for the sarcasm detection problem that could serve the scientific community to test newly proposed methods.

Semantic Similarity of an Object as a Function of the Context (SSOFC) in a Heterogeneous Environment

2003 ◽  
Vol 12 (03) ◽  
pp. 393-409
Author(s):  
Mbale Jameson ◽  
Xu Xiao Fei ◽  
Deng Sheng Chun
Keyword(s):  
Semantic Similarity ◽  
Heterogeneous Systems ◽  
Semantic Space ◽  
Cooperative Tasks ◽  
Cooperative Agents ◽  
Structural Space ◽  
Key Factor ◽  
Semantic Proximity ◽  
Relationship Of ◽  
The Relationship

The relationship of Semantic Similarity of an Object as a Function of the Context (SSOFC) being the key factor in data integration is investigated. The SSOFC is a context-based system, which exploits the context of an object by utilizing the semantic similarity involved, in order to reconcile bottleneck conflicts (semantic) standing in the way of interoperability acquisition in heterogeneous systems. SSOFC is further re-enforced with the agents to equip architectural intelligence and facilitate the cooperative tasks, such as the versatility to pass, share, communicate, liaise, and negotiate the information among the architectural components in a human way. The SSOFC operates in semantic and schematic spaces that are linked with a projection facilitated by cooperative agents. In the Semantic Space, the semantic proximity (semPro) through its first component context captures the real world semantics from the local heterogeneous sources. Meanwhile, in Structural Space, the schema correspondences are paramount in order to capture structural similarities in an algebraic or mathematical formalism for reasoning and manipulation on the computer.

Calculation of Semantic Similarity Property Based on Generalized Semantic Weak Incomplete Information System

2014 ◽  
Vol 1049-1050 ◽  
pp. 1440-1443
Author(s):  
Xue Ding ◽  
Hong Hong Yang ◽  
Ren Zhang
Keyword(s):  
Information System ◽  
Incomplete Information ◽  
Semantic Similarity ◽  
Property Values ◽  
Incomplete Information System ◽  
Property Type ◽  
Similarity Calculation ◽  
Degree Of Similarity ◽  
Attribute Value

Each object has its own specific properties, objects can be uniquely identified by its properties. "Properties" are properties of all the main features of the concept only, property values ​​are often given a certain amount of semantics, in the calculation of similarity among the different attributes if only to consider the type of calculation is obviously not complete [1]. For example: blue and blue, the similarity calculation in the property type, we can not determine its degree of similarity, but it is the same type of semantic expression under the different languages. Another example: domperidone and domperidone, which is the same type of drugs. Therefore, we attribute value in the calculation of the time, but also taking into account the semantic similarity.

scholarly journals A Co-Embedding Model with Variational Auto-Encoder for Knowledge Graphs

2022 ◽  
Vol 12 (2) ◽  
pp. 715
Author(s):  
Luodi Xie ◽  
Huimin Huang ◽  
Qing Du
Keyword(s):  
State Of The Art ◽  
Relation Extraction ◽  
Semantic Space ◽  
Knowledge Graph ◽  
High Quality ◽  
Gaussian Distributions ◽  
Benchmark Datasets ◽  
Semantic Spaces ◽  
Knowledge Graphs ◽  
Low Dimensional

Knowledge graph (KG) embedding has been widely studied to obtain low-dimensional representations for entities and relations. It serves as the basis for downstream tasks, such as KG completion and relation extraction. Traditional KG embedding techniques usually represent entities/relations as vectors or tensors, mapping them in different semantic spaces and ignoring the uncertainties. The affinities between entities and relations are ambiguous when they are not embedded in the same latent spaces. In this paper, we incorporate a co-embedding model for KG embedding, which learns low-dimensional representations of both entities and relations in the same semantic space. To address the issue of neglecting uncertainty for KG components, we propose a variational auto-encoder that represents KG components as Gaussian distributions. In addition, compared with previous methods, our method has the advantages of high quality and interpretability. Our experimental results on several benchmark datasets demonstrate our model’s superiority over the state-of-the-art baselines.

Sign in / Sign up

Export Citation Format

Share Document