PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification

Pavlick, Ellie; Rastogi, Pushpendre; Ganitkevitch, Juri; Durme, Benjamin Van; Callison-Burch, Chris

doi:10.3115/v1/p15-2070

Cited by 255 publications

(270 citation statements)

References 15 publications

Supporting

Mentioning

267

Contrasting

Unclassified

Order By: Relevance

“…This has resulted in word embeddings becoming very popular in natural language processing tasks, e.g. [11,12]. Moreover, there are a number of available word embedding frameworks, such as word2vec [13] and Glove [14], with models that are pre-trained on large corpora from different domains, such as Google News 4 or Wikipedia 5 .…”

Section: Related Workmentioning

confidence: 99%

Enhancing Sensitivity Classification with Semantic Features Using Word Embeddings

McDonald

Macdonald

Ounis

2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Government documents must be reviewed to identify any sensitive information they may contain, before they can be released to the public. However, traditional paper-based sensitivity review processes are not practical for reviewing born-digital documents. Therefore, there is a timely need for automatic sensitivity classification techniques, to assist the digital sensitivity review process. However, sensitivity is typically a product of the relations between combinations of terms, such as who said what about whom, therefore, automatic sensitivity classification is a difficult task. Vector representations of terms, such as word embeddings, have been shown to be effective at encoding latent term features that preserve semantic relations between terms, which can also be beneficial to sensitivity classification. In this work, we present a thorough evaluation of the effectiveness of semantic word embedding features, along with term and grammatical features, for sensitivity classification. On a test collection of government documents containing real sensitivities, we show that extending text classification with semantic features and additional term n-grams results in significant improvements in classification effectiveness, correctly classifying 9.99% more sensitive documents compared to the text classification baseline.

show abstract

Section: Related Workmentioning

confidence: 99%

Enhancing Sensitivity Classification with Semantic Features Using Word Embeddings

McDonald

Macdonald

Ounis

2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Thus, we propose a method that inexpensively generates translations using machine translation and Quality Estimation. Ganitkevitch et al (2013) and Pavlick et al (2015) also use a bilingual parallel corpora to build a paraphrase database using bilingual pivoting (Bannard and Callison-Burch, 2005). Their methods differ from ours in that they aim to acquire phrase level paraphrase rules and carry out word alignment instead of machine translation.…”

Section: Related Workmentioning

confidence: 99%

Building a Non-Trivial Paraphrase Corpus Using Multiple Machine Translation Systems

Suzuki¹,

Kajiwara

Komachi

2017

Proceedings of ACL 2017, Student Research Workshop

View full text Add to dashboard Cite

We propose a novel sentential paraphrase acquisition method. To build a wellbalanced corpus for Paraphrase Identification, we especially focus on acquiring both non-trivial positive and negative instances. We use multiple machine translation systems to generate positive candidates and a monolingual corpus to extract negative candidates. To collect nontrivial instances, the candidates are uniformly sampled by word overlap rate. Finally, annotators judge whether the candidates are either positive or negative. Using this method, we built and released the first evaluation corpus for Japanese paraphrase identification, which comprises 655 sentence pairs.

show abstract

“…In addition to a logistic regression classifier, the authors exploit dependency parse graphs, a paraphrase database (Pavlick et al, 2015) and several other features, to arrive at an accuracy of 73%. Another related approach is described by (Augenstein et al, 2016), who apply stance detection methods on the SemEval 2016 Task 6 data set.…”

Section: Related Workmentioning

confidence: 99%

From Clickbait to Fake News Detection: An Approach based on Detecting the Stance of Headlines to Articles

Bourgonje¹,

Schneider²,

Rehm³

2017

Proceedings of the 2017 EMNLP Workshop: Natural Language Processing Meets Journalism

115

View full text Add to dashboard Cite

We present a system for the detection of the stance of headlines with regard to their corresponding article bodies. The approach can be applied in fake news, especially clickbait detection scenarios. The component is part of a larger platform for the curation of digital content; we consider veracity and relevancy an increasingly important part of curating online information. We want to contribute to the debate on how to deal with fake news and related online phenomena with technological means, by providing means to separate related from unrelated headlines and further classifying the related headlines. On a publicly available data set annotated for the stance of headlines with regard to their corresponding article bodies, we achieve a (weighted) accuracy score of 89.59.

show abstract

PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification

Cited by 255 publications

References 15 publications

Enhancing Sensitivity Classification with Semantic Features Using Word Embeddings

Enhancing Sensitivity Classification with Semantic Features Using Word Embeddings

Building a Non-Trivial Paraphrase Corpus Using Multiple Machine Translation Systems

From Clickbait to Fake News Detection: An Approach based on Detecting the Stance of Headlines to Articles

Contact Info

Product

Resources

About