FrameBank: A Database of Russian Lexical Constructions

Lyashevskaya, Olga; Kashkin, Egor

doi:10.1007/978-3-319-26123-2_34

Cited by 14 publications

(6 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both corpora have been widely used for the semantic parsing, but the PropBank is considered to be more appropriate due to having a more suitable data structure. With regard to the Russian language, a FrameNet-oriented resource was developed for semantic role labeling -FrameBank [15]. The authors pointed out the importance of taking language-specific features into account, claiming that frames cannot be considered universal (particularly in Russian, syntax is less valuable for SRL as compared with English).…”

Section: Related Workmentioning

confidence: 99%

“…In order to conduct the semantic analysis of text material, the extraction of semantic relations between the words of the sentence is essential. For this purpose, sets of semantic roles have been elaborated [6,23] and specific linguistic resources have been created [6,15], including the frame-based ones (such as FrameNet, introduced in [5]. The earliest approaches to semantic role labeling were rule-based [20,24]).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Generation of Annotated Collection for Recognition of Sentiment Frames

Solomatina

Loukachevitch

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

While addressing the challenge of sentiment analysis, it is crucial to consider not only the polarity of certain words but also the polarity between them, particularly between the arguments of a predicate. For this purpose, the RuSen-tiFrames lexicon was created. But the training of the ML model requires an annotated collection of data, and since the manual annotation is laborious and expensive, the automation of the process is preferable. In this paper, we describe a rulebased approach to automatic annotation of semantic roles for the predicates of the RuSentiFrames lexicon. The implementation of the algorithm includes the search of the entities with certain morpho-syntactic features in the order that depends on the case of the entity and is based on calculation of the posterior probabilities of the co-occurrence of a certain case and a certain type of predicate arguments. The results of the algorithm evaluation, based on several different characteristics, were relatively high. The solutions of problematic cases have been suggested and are expected to be implemented in further research.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic Generation of Annotated Collection for Recognition of Sentiment Frames

Solomatina

Loukachevitch

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The site also hosts several spin-off projects of which the most interesting is the Old Russian subcorpus (Pichhadze 2005), which includes original Old Russian texts (such as chronicles and Novgorodian birch-bark letters) as well as translations from Greek texts (e.g., The Romance of Alexander, Flavius Josephus's Books of the History of the Jewish War against the Romans) and South Slavic texts, rewritten in Old Russian (e.g., Izbornik [Miscellany] of 1076). Other notable projects are the SynTagRus corpus (Boguslavsky et al 2000), which is manually annotated with syntactic dependency and lexical function markups, and the FrameBank (Lyashevskaya and Kashkin 2015), which is annotated with semantic roles. To the best of our knowledge, the RNC is also the only resource that includes a corpus of Russian poetry, which allows searches by meter and rhyme of poetic texts from the eighteenth century to the present (Grishina et al 2009).…”

Section: The Russian National Corpus (Wwwruscorporaru)mentioning

confidence: 99%

Corpora in Text-Based Russian Studies

Копотев

Mustajoki

Bonch-Osmolovskaya

2020

The Palgrave Handbook of Digital Russia Studies

View full text Add to dashboard Cite

This chapter opens with a discussion about what a corpus is and proceeds with an introduction of the main types of textual resources: the Web as a corpus, electronic libraries, and linguistic corpora. Among the last-mentioned, two are of particular interest. The first is the Russian National Corpus, a deeply annotated and well-designed Russian-language resource ranging from early Old Russian chronicles up to modern internet communication. The second is Integrum, the largest resource by some margin, which covers most of the newspapers and journals published both abroad and domestically, as well as a significant amount of TV, radio, and internet media. The chapter includes two case studies that demonstrate how word choice reflects shared memory patterns and how changes in language usage reflect political and social mutations.

show abstract

“…Another outcome of corpus investigations into units larger than the lexeme was the Russian FrameBank (http://framebank.ru/; Lyashevskaya & Kashkin, 2015). Analogous to FrameNet for English (Fillmore et al, 2008), the Russian FrameBank draws on Russian lexicographical traditions and traditional printed dictionaries (Apresjan & Pall, 1982;Sazonova, 2008).…”

Section: History and Partnersmentioning

confidence: 99%

Constructicography

Ohara¹,

Torrent²,

Lyngfelt³

et al. 2018

Constructional Approaches to Language

View full text Add to dashboard Cite

This book has been long in the making, but now having the result under our eyes, we believe that it was worth the wait. The idea of compiling a volume collecting the experiences of the various constructicon initiatives going on around the world was born in the context of an international collaboration between the universities at Gothenburg in Sweden and Juiz de Fora in Brazil, and the excellent opportunities to interact and learn from each other's experiences afforded by both research visits and the international FrameNet workshops organized jointly by the Swedish and Brazilian teams, together with the FrameNet group in Berkeley, California: IFNW 2013 in Berkeley, IFNW 2016, collocated with ICCG9 in Juiz de Fora, and the upcoming IFNW 2018 with the special theme Multilingual FrameNets and Constructicons, collocated with LREC in Miyazaki, Japan. Moreover, profitable discussions relevant to the works presented in this book took place in the special sessions Cognitively grounded lexica, constructicons, and metaphor repositories, at ICLC12 in Edmonton, Canada, in 2013, and Constructionist resources -a workshop in honor of Charles J. Fillmore, at ICCG8 in Osnabrück, Germany, in 2014.During these events, most -if not all -authors of the chapters in this volume had the chance to share their points of view, positions and questions on the development of constructionist resources. Beyond the group of authors whose contributions make this book, we'd like to thank our -and their -interlocutors.The work on preparing the volume has been funded in part by the Swedish Foundation for International Cooperation in Research and Higher Education (STINT), by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES, Brazil), and by the Swedish Foundation for Humanities and Social Sciences (Riksbankens Jubileumsfond, RJ), but it could not have happened without the long-term support given to both Språkbanken (the Swedish Language Bank) -now well into its fifth decade -by the University of Gothenburg, its Faculty of Arts and its Department of Swedish, and to FrameNet Brasil by the Federal University of Juiz de Fora.The volume editors would like to express their gratitude to the anonymous reviewers for their thorough and insightful comments and suggestions, to the series editor Jan-Ola Östman for his final vetting of the volume, and to Esther Roth and Susan Hendriks at John Benjamins, always helpful and unerringly professional, under whose watchful eyes the volume went from idea to finished product. Last but viii Constructicography not least, we are grateful to the person without whom none of all this would have happened: the late Charles J. Fillmore. For inspiring us all, for being a core element in our research frame(works), for having guided our ways into the development of constructicons, and for being such a great guy, we dedicate this volume to Chuck.

show abstract

FrameBank: A Database of Russian Lexical Constructions

Cited by 14 publications

References 2 publications

Automatic Generation of Annotated Collection for Recognition of Sentiment Frames

Automatic Generation of Annotated Collection for Recognition of Sentiment Frames

Corpora in Text-Based Russian Studies

Constructicography

Contact Info

Product

Resources

About