Sentence Paraphrase Graphs: Classification Based on Predictive Models or Annotators’ Decisions?

Pronoza, Ekaterina V.; Yagunova, Elena; Kochetkova, Nataliya

doi:10.1007/978-3-319-62434-1_4

Cited by 3 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper we test a hypothesis that paraphrase construction method allows us to identify thematically homogeneous news clusters. A paraphrase graph is a graph where news headlines are vertices, and two vertices are connected by an edge if they are paraphrases [4]. Such graph reflects the structure of the corresponding news cluster: for example, similar headlines tend to group into subgraphs which refer to the subtopics in the news cluster.…”

Section: Introductionmentioning

confidence: 99%

Construction of Paraphrase Graphs as a Means of News Clusters Extraction

Yagunova¹,

Pronoza²,

Kochetkova³

2018

CyS

Self Cite

View full text Add to dashboard Cite

In this paper, we construct paraphrase graphs for news text collections (clusters). Our aims are, first, to prove that paraphrase graph construction method can be used for news clusters identification and, second, to analyze and compare stylistically different news collections. Our news collections include dynamic, static and combined (dynamic and static) texts. Their respective paraphrase graphs reflect their main characteristics. We also automatically extract the most informationally important linked fragments of news texts, and these fragments characterize news texts as either informative, conveying some information, or publicistic ones, trying to affect the readers emotionally.

show abstract

Section: Introductionmentioning

confidence: 99%

Construction of Paraphrase Graphs as a Means of News Clusters Extraction

Yagunova¹,

Pronoza²,

Kochetkova³

2018

CyS

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this paper we present a ParaPhraser project (http://www.paraphraser.ru/) aimed at building of Russian paraphrase corpus, studying of paraphrase phenomena in Russian news and development of automatic paraphrase detection and generation methods (Pronoza and Yagunova, 2015a), (Pronoza andYagunova, 2015b), (Pronoza et al, 2015), (Pronoza et al, 2017). The project was launched in 2014 in St.-Petersburg State University; by the beginning of 2016 we have collected 11 thousand pairs of Russian news titles, which were manually collected as either paraphrase, partial paraphrase or non-paraphrase.…”

Section: Introductionmentioning

confidence: 99%

ParaPhraser: Russian Paraphrase Corpus and Shared Task

Pivovarova

Pronoza

Yagunova

et al. 2017

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

The paper describes the results of the First Russian Paraphrase Detection Shared Task held in St.-Petersburg, Russia, in October 2016. Research in the area of paraphrase extraction, detection and generation has been successfully developing for a long time while there has been only a recent surge of interest towards the problem in the Russian community of computational linguistics. We try to overcome this gap by introducing the project ParaPhraser.ru dedicated to the collection of Russian paraphrase corpus and organizing a Paraphrase Detection Shared Task, which uses the corpus as the training data. The participants of the task applied a wide variety of techniques to the problem of paraphrase detection, from rule-based approaches to deep learning, and results of the task reflect the following tendencies: the best scores are obtained by the strategy of using traditional classifiers combined with finegrained linguistic features, however, complex neural networks, shallow methods and purely technical methods also demonstrate competitive results.

show abstract