Conclusion

We demonstrate several ways to use morphological word analogies to examine the representation of complex words in semantic vector spaces. We present a set of morphological relations, each of which can be used to generate many word analogies. 1. We show that the difference-vectors for pairs which have the same relation to each other are similarly aligned. 2. We suggest that addition of difference-vectors is a useful phrase-building operator. 3. We propose that pairs in the same relation may have similar relative frequencies. 4. We suggest that homographs, which necessarily have the same semantic vectors, can sometimes be separated into different vectors for different senses, using frequency estimates and alignment constraints obtained from word analogies. 5. We observe that some of our analogies seem to be parallel, and might be combined. We use Arabic words as a case study, because Arabic orthography includes verb conjugations, object pronouns, definitive articles, possessive pronouns, and some prepositions in single word-forms. Therefore, a number of short phrases, built up of easily perceived constituents, are already present in stock semantic spaces for Arabic available on the web. Similar phrases in English would require including bigrams or trigrams as lemmas in the word embedding, although English derivational morphology allows for other relationships in standard semantic spaces which Arabic does not, for example negation. We make our corpus of morphological relations available to other researchers.

In this paper, a learning method is proposed to improve the retrieval process in image databases. This method uses the search transaction logs in the system and user relevance feedback scores to create a semantic space of the image database. The semantic space includes many semantic classes and all the images in the database are clustered to these classes with different membership values. The sparsity problem in the transaction logs data is solved by filling the missing values by an estimation based on the image contents and image similarities. A Fuzzy clustering algorithm is developed to create the semantic classes and find image memberships in the classes.

Neo-Davidsonian-Based Event Class Semantic Representation

Class label autoencoder with structure refinement for zero-shot learning

Intransitive Predication constitutes a major contribution to the study of typological linguistics and theoretical linguistics in general. Basing his analysis on a sample of 410 languages, Leon Stassen investigates cross-linguistic variation in one of the core domains of all natural languages. The author views this domain as a `cognitive space', the topography of which is the same for all languages. It is assumed to consist of four subdomains, which correspond to a four-way distinction between the semantic classes of event predicates, property predicates, class predicates, and locational predicates. Leon Stassen offers a typology of the structural manifestations of this domain, in terms of the nature and number of the formal strategies used in its encoding. He discusses a number of abstract principles which can be employed in explaining the cross-linguistic variation embodied by the typology. In the final chapter, he brings together the research results in a universally applicable model, which can be read as a `flow chart' for the encoding of intransitive predications in different language types.

Background : Some individuals with agrammatic aphasia have difficulty producing verbs when naming and generating sentences (Miceli, Silveri, Villa, & Caramazza, 1984; Saffran, Schwartz, & Marin, 1980; Zingeser & Berndt, 1990). And when verbs are produced there is an over-reliance on verbs requiring simple argument structure arrangements (Thompson, Lange, Schneider, & Shapiro, 1997; Thompson, Shapiro, Schneider, & Tait, 1994). Verbs, as argument-taking elements, show especially complex semantic and argument structure properties. This study investigated the role these properties have on verb production in individuals with agrammatic aphasia. Aim : This treatment study examined the extent to which semantic class and argument structure properties of verbs influenced the ability of seven individuals with agrammatic Broca's aphasia to retrieve verbs and then use them in correct sentence production. Verbs from two semantic classes and two argument structure categories were trained using either a semantic or an argument structure verb retrieval treatment. Specifically, acquisition and generalisation to trained and untrained verbs within and across semantic and argument structure categories was examined. In addition, the influence of verb production on each participant's sentence production was also examined. Methods & Procedures : Utilising a single-subject crossover design in combination with a multiple baseline design across subjects and behaviours, seven individuals with agrammatic aphasia were trained to retrieve verbs with specific argument structures from two semantic classes under two treatment conditions--semantic verb retrieval treatment and verb argument structure retrieval treatment. Treatment was provided on two-place and three-place motion or change of state verbs, counterbalanced across subjects and behaviours. A total of 102 verbs, depicted in black and white drawings, were utilised in the study, divided equally into motion and change of state verbs (semantic classes) and one-place, two-place, and three-place verbs (argument structure arrangements). Verbs were controlled for syllable length, picturability, phonological complexity, and frequency. These same stimulus items were used to elicit the sentence production probe. Outcomes & Results : Both treatments revealed significant effects in facilitating acquisition of verb retrieval in all participants. Minimal within and across verb category generalisation occurred. However, it was found that as retrieval of verbs improved, grammatical sentence production improved. This occurred without direct treatment on sentence, production.

The effect of verb semantic class and verb frequency (entrenchment) on children’s and adults’ graded judgements of argument-structure overgeneralization errors

We propose a method to study the variation lying between different word embeddings models trained with different parameters. We explore the variation between models trained with only one varying parameter by observing the distributional neighbors variation and show how changing only one parameter can have a massive impact on a given semantic space. We show that the variation is not affecting all words of the semantic space equally. Variation is influenced by parameters such as setting a parameter to its minimum or maximum value but it also depends on the corpus intrinsic features such as the frequency of a word. We identify semantic classes of words remaining stable across the models trained and specific words having high variation.

Agnostic attribute segmentation of dynamic scenes with limited spatio-temporal resolution

This paper presents a method for semantic class disambiguation for all words. Unlike the ordinary word sense disambiguation, a set of semantic classes or coarse grained senses is defined as a common sense inventory, then universal classifiers to select an appropriate semantic class of a target word in a given context, which can be applicable to all words, are trained by supervised learning. In the previous method, imbalance of number of positive and negative samples in training data causes disambiguation errors. On the other hand, our new method can train the classifiers from well balanced training data. Results of the experiment showed that our method outperformed the previous method by 1.43% accuracy.

The article examines the role of phrasal verbs in prama-semantic organisation of publicistic discourse. The relevance of this research is explained by the growing interest of linguists in the problems of using phrasal verbs in different types of discourse, as well as the poorly studied issue of phrasal verbs at the junction of economic and publicistic discourse and their pragmatic potential. The objective of he work is to demonstrate the connection between the language and the currect economic realia which constitutes the flexible nature of pragma-semantic system of discourse. The research relies on functional-pragmatic method and component analysis. The method of continuous sampling (articles on the topic of the impact of coronavirus on the economy of different countries) was used to select the material. On the basis of materials taken from English-language newspapers on the topic of the coronavirus impact on the economy of European countries the semantic classification of phrasal verbs was carried out, the results of which shown that the most frequent semes are «slowing down», «improvement», «novelty», «measures / actions», «refusal». The authors conclude that the semantic classification forms the basis of communicative strategies for creating an image of various entities or people, strategies for forming a public opinion, and strategies for uniting the society. In the pragmatic system of publicistic discourse phrasal verbs are particular speech means involved in the implementation of the general communicative strategies. They are indicative of national and cultural self-identitication, the striving for economic growth and social unity in crisis conditions.

Nabokov, known primarily for his prose, was also a remarkable poet. The article aims to examine the semantic (lexical) features of Nabokov's images in his lyrics. These characteristics include 23 semantic (thematic) classes of words that fill two positions of the figurative model – the position of the Target of the metaphoric transfer and the position of its Source. The material includes 4 lyrical collections by Nabokov, published at different stages of his creative path – an early collection (published when he lived in Russia), 2 later collections from the Berlin period (middle stage) and one collection of mature creative activity when Nabokov lived in the USA. The article examines the relationships between the features of the two positions of the image, the distribution of semantic classes of words in the image system, and changes in the frequencies of these classes over time.

The measure of sentence similarity is useful in various research fields, such as artificial intelligence, knowledge management, and information retrieval. Several methods have been proposed to measure the sentence similarity based on syntactic and/or semantic knowledge. Most proposals are evaluated on English sentences where the accuracy can decrease when these proposals are applied to other languages. Moreover, the results of these methods are unsatisfactory, as much relevant semantic knowledge, such as semantic class, thematic role and syntactico-semantic knowledge like the semantic predicates, are not taken into account. We must acknowledge that this kind of knowledge is rare in most of the lexical resources. Recently, the International Organization for Standardization (ISO) has published the Lexical Markup Framework (LMF) ISO-24613 norm for the development of lexical resources. This norm provides, for each meaning of a lexical entry, all the semantic and syntactico-semantic knowledge in a fine structure. Profiting from the availability of LMF-standardized dictionaries, we propose, in this paper, a generic method that enhances the measure of sentence similarity by applying semantic and syntactico-semantic knowledge. An experiment was carried out on Arabic, as this language is processed within our research team and an LMF-standardized Arabic dictionary is at hand where the semantic and the syntactico-semantic knowledge are accessible and well structured. Moreover, the experiments yielded better results, showing a high correlation with human ratings.

We present an unsupervised method for inducing verb classes from verb uses in gigaword corpora. Our method consists of two clustering steps: verb-specific semantic frames are first induced by clustering verb uses in a corpus and then verb classes are induced by clustering these frames. By taking this step-wise approach, we can not only generate verb classes based on a massive amount of verb uses in a scalable manner, but also deal with verb polysemy, which is bypassed by most of the previous studies on verb clustering. In our experiments, we acquire semantic frames and verb classes from two giga-word corpora, the larger comprising 20 billion words. The effectiveness of our approach is verified through quantitative evaluations based on polysemy-aware gold-standard data.

We argue that Abaza, a polysynthetic language from the Northwest Caucasian family, exhibits a syntax-semantics mapping that has not been observed in any other languages before. We show that Abaza lacks wh-words and, as a consequence, matrix and embedded wh- interrogative clauses, and conveys direct and indirect content question meaning by means of headless relative clauses. We propose a compositional semantic analysis of these headless relative clauses that assigns them the same meaning as concealed question DPs, i.e. individual concepts. When occurring as matrix clauses and conveying direct question meaning, these headless relative clauses require the relative verbal form to contain a clause typing affix from a specific set. We show that these affixes cannot be analyzed as “incorporated” or “cliticized” wh- words, but rather as operators turning individual concepts into questions, i.e., sets of propositions.