Semantic Space

Metaphor is one of the most prominent, and most studied, figures of speech.
While it is considered an element of great interest in several branches of linguistics, such as
semantics, pragmatics and stylistics, its automatic processing remains an open challenge. First of all, the semantic complexity of the concept of metaphor itself creates a range of theoretical complications. Secondly, the practical lack of large scale resources forces researchers to work under conditions of data scarcity.
This compilation thesis provides a set of experiments to (i) automatically detect metaphors and (ii) assess a metaphor’s aptness with respect to a given literal equivalent. The first task has already been tackled by a number of studies. I approach it as a way to assess the potentialities and limitations of our approach, before dealing with the second task. For metaphor detection I was able to use existing resources, while I created my own dataset to explore metaphor aptness assessment. In all of the studies presented here, I have used a combination of word embeddings and neural networks.
To deal with metaphor aptness assessment, I framed the problem as a case of paraphrase identi- fication. Given a sentence containing a metaphor, the task is to find the best literal paraphrase from a set of candidates. I built a dataset designed for this task, that allows a gradient scoring of various paraphrases with respect to a reference sentence, so that paraphrases are ordered according to their degree of aptness. Therefore, I could use it both for binary classification and ordering tasks. This dataset is annotated through crowd sourcing by an average of 20 annotators for each pair. I then designed a deep neural network to be trained on this dataset, that is able achieve encouraging levels of performance.
In the final experiment of this compilation, more context is added to a sub-section of the dataset in order to study the effect of extended context on metaphor aptness rating. I show that extended context changes human perception of metaphor aptness and that this effect is reproduced by my neural classifier. The conclusion of the last study is that extended context compresses aptness scores towards the center of the scale, raising low ratings and decreasing high ratings given to paraphrase candidates outside of extended context.

В статье предлагается подход к изучению феномена одиночества, для реализации которого апробированы: тест  UCLA для измерения уровня переживания одиночества, метод неоконченных предложений для выявления личностных смыслов «одиночества», метод семантического дифференциала для определения эмоционального отношения к одиночеству. Приводятся инструментарии исследования, результаты экспериментов,
на основе которых обосновывается адекватность предложенного подхода.

This paper discusses the main issues encountered in the design of a domain ontology to represent ancient literary texts that survive only in fragments, i.e. through quotations embedded in other texts. The design approach presented in the paper combines a knowledge domain analysis conducted through semantic spaces with the integration of well established ontologies and the application of ontology design patterns. After briefy describing the specifc meaning of “fragment” in a literary context, the paper gives insights into the main conceptual issues of the ontology design process. Lastly, it outlines the overall architecture of protocols, services and data repositories which is required to implement a digital edition of fragments based on the proposed ontology.

In the article the author continues to introduce the reader to the findings of the exploratory research aimed to reconstruct some structural elements of the phenomenon of loneliness. In this instance, the article describes the application of psycho-semantic methods used in combination with the method of unfinished sentences. The approach used in the article enables the author to study loneliness turning
directly to the affective level of the respondents’ emotions.

A key role in the human reasoning capability is given by in- tuition. The aim of the work is to design a framework for an human-like information supplier, which combines "intuition" with the traditional, more rigid, rules-based knowledge. It is presented a preliminary system that represents the first step to- ward the aforementioned framework. The system allows a user to

In this paper, we explore the possibility of applying high-dimensionalvector representations of concept-relation-concept triplets, which have been successfullyapplied to model a small set of relationship types in the biomedicaldomain, to the task of modeling folk tales. In doing so, our ultimate aim is todevelop representations of narratives through which their underlying structurecan be compared. The current paper describes our progress toward this aim, withemphasis on addressing the technical challenges involved in moving from therelatively constrained set of relations that have been extracted from biomedicaltext to the much larger set of unnormalized relations that have been extractedfrom the open domain. A toy example using graded vectors demonstrates that ourapproach will be feasible once more material will be added to the test collection.

Success in schema integration depends on understanding the semantics of schema components (e.g., entity sets, relationship sets, attributes), and the ability to capture and reason about these semantics. An important objective of our work on schema integration is to automate the reasoning as much as possible, and when not possible, depend on the human input and guidance. A key results of comparing the semantics associated with schema objects is that of determining attribute relationship. Once attribute relationships are determined, the task of object class(e.g., entity sets and relationship sets) integration becomes simpler and can e automated to a great extent. In our work, we use a classifier borrowed from the research in knowledge representation(particularly the KL-ONE family of systems) for automatically integrating objects classes.

Spoken dialogue systems typically use predefined seman- tic slots to parse users' natural language inputs into unified semantic representations. To define the slots, domain ex- perts and professional annotators are often involved, and the cost can be expensive. In this paper, we ask the following question: given a collection of unlabeled raw audios, can we use the frame semantics theory

In three studies we investigated whether LSA cosine values estimate human similarity ratings of word pairs. In study 1 we found that LSA can distinguish between highly similar and dissimilar matches to a target word, but that it does not reliably distinguish between highly similar ...