Relative clause extraction for syntactic simplification

Dornescu, Iustin; Evans, Richard J.; Orăsan, Constantin

doi:10.3115/v1/w14-5601

Cited by 7 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each row specifies a different feature set -"All" specifies the entire feature set from Table 2, while each subsequent line removes one type of features. (Dornescu et al, 2014) performs better on our dataset Their method achieves much better results on our dataset (compare 64% overall F1 on our dataset with their reported 45.29% F1 on their dataset). This speaks both for their method as a valid signal for restrictiveness annotation, as well as for the improved consistency of our dataset.…”

Section: Gold Treessupporting

confidence: 49%

“…Replicating (Dornescu et al, 2014) Their best performing ML-based algorithm 10 uses the supervised CRFsuite classifier (Okazaki, 2007) over "standard features used in chunking, such as word form, lemma and part of speech tags". Replicating their baseline, we extract the list of features detailed in Table 2 (in the row labeled "chunking features").…”

Section: Baselinesmentioning

confidence: 99%

See 1 more Smart Citation

Annotating and Predicting Non-Restrictive Noun Phrase Modifications

Stanovsky¹,

Dagan²

2016

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

The distinction between restrictive and non-restrictive modification in noun phrases is a well studied subject in linguistics. Automatically identifying non-restrictive modifiers can provide NLP applications with shorter, more salient arguments, which were found beneficial by several recent works. While previous work showed that restrictiveness can be annotated with high agreement, no large scale corpus was created, hindering the development of suitable classification algorithms. In this work we devise a novel crowdsourcing annotation methodology, and an accompanying large scale corpus. Then, we present a robust automated system which identifies non-restrictive modifiers, notably improving over prior methods.

show abstract

Section: Gold Treessupporting

confidence: 49%

Section: Baselinesmentioning

confidence: 99%

Annotating and Predicting Non-Restrictive Noun Phrase Modifications

Stanovsky¹,

Dagan²

2016

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

show abstract

“…Relative clauses are one of the most features clauses in constructing complex sentences. Dornescu et al [15] have specifically worked on Relative clause extraction for syntactic simplification. Their process reduced the average sentence length and complexity to make text simpler.…”

Section: Previous Workmentioning

confidence: 99%

“…Inspired by the work of Aranzabe et al [9], Sharma et al [14] and Dornescu et al [15], we have targeted relative clauses present in the complex sentences and provide a better approach to identify and extract them for simplification process.…”

Section: Previous Workmentioning

confidence: 99%

Relative clause based text simplification for improved English to Hindi translation

Saini

Sehgal

Sahula

2015

2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI)

View full text Add to dashboard Cite

Language translation is one of the most research and development oriented topic in today's world because of its increasing demand and application. Knowledge of grammar structure of source and target languages is must for translating one language to other. Clauses are an integral part of any language and helps in constructing complex sentences in different contexts. This complication leads to a low score of translation in almost every machine translation engine existing in the world. In this work, we are focusing on relative clause identification and extraction for text simplification. The generated simple sentences are then fed to the existing translation engines for translation. Link Parser based parsing techniques are used to parse the sentence tree. In this work we have focused on achieving better quality of English-Hindi translations. The proposed approach is tested manually on a sufficiently large dataset and shows promising and better translation score than the conventional approaches.

show abstract

“…Early researches in text simplification have considered punctuation marks such as comma, semicolon, and parentheses as important markers to split the clauses [19]. An extensive research of relative clause extraction on simplifying text is described in [20].…”

Section: Introductionmentioning

confidence: 99%

A Distance Approach for Open Information Extraction Based on Word Vector

2018

KSII TIIS

View full text Add to dashboard Cite

Web-scale open information extraction (Open IE) plays an important role in NLP tasks like acquiring common-sense knowledge, learning selectional preferences and automatic text understanding. A large number of Open IE approaches have been proposed in the last decade, and the majority of these approaches are based on supervised learning or dependency parsing. In this paper, we present a novel method for web scale open information extraction, which employs cosine distance based on Google word vector as the confidence score of the extraction. The proposed method is a purely unsupervised learning algorithm without requiring any hand-labeled training data or dependency parse features. We also present the mathematically rigorous proof for the new method with Bayes Inference and Artificial Neural Network theory. It turns out that the proposed algorithm is equivalent to Maximum Likelihood Estimation of the joint probability distribution over the elements of the candidate extraction. The proof itself also theoretically suggests a typical usage of word vector for other NLP tasks. Experiments show that the distance-based method leads to further improvements over the newly presented Open IE systems on three benchmark datasets, in terms of effectiveness and efficiency.

show abstract

Relative clause extraction for syntactic simplification

Cited by 7 publications

References 13 publications

Annotating and Predicting Non-Restrictive Noun Phrase Modifications

Annotating and Predicting Non-Restrictive Noun Phrase Modifications

Relative clause based text simplification for improved English to Hindi translation

A Distance Approach for Open Information Extraction Based on Word Vector

Contact Info

Product

Resources

About