Comparing the Performance of Neural and Statistical Sentence Embeddings on Summarization and Word Sense Disambiguation

被引：0

作者：

Juvekar, Gaurav ^{[1
]}

Lolage, Abhishek ^{[1
]}

Sahasrabudhe, Dhruva ^{[1
]}

Haribhakta, Yashodhara ^{[1
]}

机构：

[1] Coll Engn, Dept Comp Engn & Informat Technol, Pune, Maharashtra, India

来源：

2018 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI) | 2018年

关键词：

sentence embedding; vector; similarity; text summarization; word sense disambiguation;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

We analyzed the performance of two sentence embeddings: SIF (Smoothed Inverse Frequency) created using weighted GloVe word embeddings, and sent2vec, trained using a neural network. Using these sentence embeddings without modification, we compared and contrasted their performance on extractive text summarization and word sense disambiguation using existing methods tailored for sentence embeddings. We find that our results are better than the simplest baselines and approach competitive baselines for both these tasks, proving that sentence embeddings are to some extent successful in capturing the structure of language.

引用

页码：1787 / 1792

页数：6

共 21 条

[11]

Lesk M., 1986, P 5 ANN INT C SYSTEM, P24, DOI 10.1145/318723.318728

[12]

Mihalcea R., 2008, SEMCOR 3 0 SEMANTICA, P6

[13] WORDNET - A LEXICAL DATABASE FOR ENGLISH [J].

MILLER, GA .

COMMUNICATIONS OF THE ACM, 1995, 38 (11) :39-41

[14]

Moro A., 2015, SEMEVAL NAACL HLT

[15]

Nallapati Ramesh, 2016, ABS161104230 CORR

[16] Word Sense Disambiguation: A Survey [J].

Navigli, Roberto .

ACM COMPUTING SURVEYS, 2009, 41 (02)

[17]

Padmakumar Aishwarya., 2016, Unsupervised Text Summarization Using Sentence Embeddings

[18]

Pagliardini M., 2018, NAACL 2018 C N AM AS

[19]

Pennington J., 2014, 2014 C EMP METH NAT, P43

[20]

Radev DragomirR., 2000, P 2000 NAACL ANLPWOR, V4, P21

← 1 2 3 →