An Opinion Facilitator for Online News Media

With more and more voices and opinions entering the public domain, a key challenge facing journalists and editors is maximizing the context of the information that is presented on news websites. In this paper, we argue that systems for exposing readers to the many aspects of societal debates should be grounded in methods and tools that can provide a fine-grained understanding of these debates. The present article thereby explores the conceptual transition from opinion observation to opinion facilitation by introducing and discussing the Penelope opinion facilitator: a proof-of-concept reading instrument for online news media that operationalizes emerging methods for the computational analysis of cultural conflict developed in the context of the H2020 ODYCCEUS project. It will be demonstrated how these methods can be combined into an instrument that complements the reading experience of the news website The Guardian by automatically interlinking news articles on the level of semantic frames. In linguistic theory, semantic frames are defined as coherent structures of related concepts. We thereby zoom in on instances of the “causation” frame, such as “climate change causes global warming,” and illustrate how a reading instrument that links articles based on such frames might reconfigure our readings of climate news coverage, with specific attention to the case of global warming controversies. Finally, we relate our findings to the context of the development of computational social science, and discuss pathways for the evaluation of the instrument, as well as for the future upscaling of qualitative analyses and close readings.

Construction mining

The German Constructicon Project (www.german-constructicon.de) aims at documenting grammatical constructions in contemporary standard German on the basis of annotated corpus examples, including relations between constructions and between constructions and evoked semantic frames. So far, the research focus has been mainly on the development and computational implementation of a constructicographic workflow (including a parsing pipeline) that allows for addressing any kind of constructions on varying levels of schematicity, idiomaticity, and abstractness. However, such an exemplar-driven procedure precludes us from systematically identifying constructional candidates. In this article, we scrutinize ways to operationalize and implement data-mining procedures to inductively identify construction candidates.

ANALYSIS OF “THE FUNDAMENTAL DICTIONARY OF THE ENVIRONMENT DICOENVIRO” IN COMPARISON WITH ELECTRONIC RESOURCES FRAMENET, PROPBANK, VERBNET IN THE FRAMEWORK OF MODERN THEORETICAL LEXICOGRAPHIC PARADIGM

The purpose of the article is to establish the possibilities of functioning of the terminological Internet resource “The Fundamental Dictionary of the Environment DiCoEnviro”, to examine its methods to carry out a comparative analysis with electronic resources FrameNet, Propbank, VerbNet to open a new perspective of the perception of the meaning of words in common and specialized languages in the framework of modern theoretical lexicographic paradigm.Methods. The complex linguo-pragmatic descriptive method and the techniques of observation, comparison, generalization and interpretation helped to characterize the work of the terminological Internet resource DiCoEnviro and electronic resources FrameNet, Propbank, VerbNet, to identify phenomena in them; the extraction of terminological units for the formation of the results materials is made by the method of continuous sampling.Results. The article highlights the work of the terminological Internet resource DiCoEnviro in comparison with electronic resources FrameNet, Propbank, VerbNet, which offer mainly information about the common language. It is found that in DiCoEnviro the participant is defined by the type, role, is expressed by syntactic group, each context contains a description of syntactic function. Annotation of contexts in DiCoEnviro is performed using the Oxigen XML editor, while users view annotations in HTML format when visiting the DiCoEnviro website.Conclusions. The article presents the work of scientists in the field of lexicography, namely electronic dictionaries; it shows a study of the terminological Internet resource DiCoEnviro and the principles of annotation of terms in it. The purpose of the DiCoEnviro project is traced; previous works of FrameNet, Propbank, VerbNet are presented, which offer mainly information about common language, while DiCoEnviro includes vocabulary of specialized environmental language; examples of annotations from these projects are given and analyzed. The method used in DiCoEnviro and based on explanatory and combinatorial lexicology and partly on the theory of semantic frames is considered in details.Key words: annotation, frames, terms, explanatory and combinatorial lexicology, specialized language. Мета статті – встановити можливості функціонування термінологічного інтернет-ресурсу «Фундаментальний слов-ник навколишнього середовища DiCoEnviro», розглянути його методи для здійснення порівняльного аналізу з електронни-ми ресурсами FrameNet, Propbank, VerbNet, щоб відкрити нову перспективу сприйняття значення слова у загальновживаній та спеціалізованій мовах у рамках сучасної теоретичної лексикографічної парадигми.Методи. Комплексний лінгвопрагматичний описовий метод і прийоми спостереження, порівняння, узагальнення та інтер-претації допомогли охарактеризувати роботу термінологічного інтернет-ресурсу DiCoEnviro і електронних ресурсів FrameNet, Propbank, VerbNet, виявити явища в них; виокремлення термінологічних одиниць для формування матеріалів результатів зро-блено методом суцільної вибірки.Результати. У статті висвітлено роботу термінологічного інтернет-ресурсу DiCoEnviro порівняно з електронними ресур-сами FrameNet, Propbank, VerbNet, які пропонують в основному інформацію про загальновживану мову. З’ясовано, що в DiCoEnviro учасник визначається своїм типом, роллю, виражається синтаксичною групою, кожен контекст містить опис синтаксичної функції. Анотування контекстів у DiCoEnviro виконується за допомогою редактора XML Oxigen, тоді як корис-тувачі, коли відвідують вебсайт DiCoEnviro, дивляться анотування у форматі HTML.Висновки. У статті презентовано роботи науковців у галузі лексикографії, а саме електронних словників; показано дослі-дження термінологічного інтернет-ресурсу DiCoEnviro і принципів анотування термінів у ньому. Простежено мету проєк-ту DiCoEnviro; представлені попередні роботи FrameNet, Propbank, VerbNet, які пропонують в основному інформацію про загальновживану мову, тоді як DiCoEnviro включає у себе лексику спеціалізованої мови навколишнього середовища; наведено і проаналізовано приклади анотування з цих проєктів. Докладно розглянуто методику, яка застосовується в DiCoEnviro і ґрун-тується на пояснювальній і комбінаторній лексикології і частково на теорії семантичних фреймів.Ключові слова: анотування, фрейми, терміни, пояснювальна і комбінаторна лексикологія, спеціалізована мова

MOTION VERBS IN PERSIAN AND ENGLISH: A FRAMENET-BASED CONTRASTIVE ANALYSIS

The current research aims at exploring and comparing the semantic frames of motion verbs in English and Persian. In pursuit of this goal, the novel Animal farm by G. Orwell (1945) was selected and compared with its Persian translation, Qale heyvanat (Atefi, 2010). The sentences including motion verbs were primarily extracted from the novel and then a comparison was made between each English sentence and its Persian counterpart. Afterwards, the semantic frames of the English and Persian motion verbs were obtained from the FrameNet database. It should be noted that when the motion verbs in English had an equivalent which could be interpreted in a different way in Persian, the Persian verb was searched for in one of the most reliable Persian to English dictionaries—Persian to English Dictionary (Aryanpur and Aryanpur, 2007). We searched for its English equivalent and then the newly obtained English verb was searched in FrameNet for the semantic frame. When comparing the semantic frames of the motion verbs in the two languages examined, we concluded that motion events in English and Persian were expressed through miscellaneous motion verbs each of which involves a semantic frame peculiar to it. Likewise, the frames may be similar or different cross-linguistically in case of semantic differences, or they might be pragmatically similar.

TESTING THE ACTIVATION OF SEMANTIC FRAMES IN A LEXICAL DECISION TASK AND A CATEGORIZATION TASK

Situated in the wider framework of frame semantics, the paper employs an experimental approach involving a reaction time study to test the activation of semantic frames via semantic priming. Experiment 1 deals with the frame of journey and employs a lexical decision task in a reaction time paradigm, while Experiment 2 deals with the frame of conflict and uses a categorization task, also in a reaction time paradigm. Both experiments were designed in Open Sesame. Target stimuli were in Serbian, selected through a norming procedure involving prototypicality ratings on Likert scales. Additionally, identical filler items were included in both experiments. Priming was performed using lexical materials modified to facilitate the activation of the respective frames. The obtained results showed that there was no facilitation in the experimental group in Experiment 1 compared to the control group; however, in Experiment 2, we were able to identify facilitation in the experimental group in the main task, licensed by the initial priming. These results suggest that the lexical decision task has a reduced cognitive load compared to the categorization task, thereby overriding the priming condition. In effect, categorization task appears to be a more suitable procedure for testing semantic frame activation.

A computational construction grammar approach to semantic frame extraction

This paper introduces a novel methodology for extracting semantic frames from text corpora. Building on recent advances in computational construction grammar, the method captures expert knowledge of how semantic frames can be expressed in the form of conventionalised form-meaning pairings, called constructions. By combining these constructions in a semantic parsing process, the frame-semantic structure of a sentence is retrieved through the intermediary of its morpho-syntactic structure. The main advantage of this approach is that state-of-the-art results are achieved, without the need for annotated training data. We demonstrate the method in a case study where causation frames are extracted from English newspaper articles, and compare it to a commonly used approach based on Conditional Random Fields (CRFs). The computational construction grammar approach yields a word-level F1 score of 78.5%, outperforming the CRF approach by 4.5 percentage points.

The treatment of Taoist terms in Chinese-English dictionaries: a study based on Frame Semantics

This study argues for a frame semantic approach to the treatment of Taoist terms, which are Chinese culture-specific. It takes three Taoist aesthetic terms 虚(xu), 无(wu) and 静(jing) as a case study to explore how Chinese-English dictionaries can make use of semantic frames in the treatment of Taoist terms. As the study shows, a Taoist-aesthetics frame can be constructed in comparison with the Aestheticsframe in FrameNet. When treating Taoist terms, the core frame element “Entity” facilitates the meaning explanation by making the terms more intelligible. The non-core frame element “Circumstances” should be highlighted as it helps the dictionary to provide a more accurate definition of Taoist terms.