| 82 |
A resource-light method for cross-lingual semantic textual similarity
|
|
|
|
Abstract:
[EN] Recognizing semantically similar sentences or paragraphs across languages is beneficial for many tasks, ranging from cross-lingual information retrieval and plagiarism detection to machine translation. Recently proposed methods for predicting cross-lingual semantic similarity of short texts, however, make use of tools and resources (e.g., machine translation systems, syntactic parsers or named entity recognition) that for many languages (or language pairs) do not exist. In contrast, we propose an unsupervised and a very resource-light approach for measuring semantic similarity between texts in different languages. To operate in the bilingual (or multilingual) space, we project continuous word vectors (i.e., word embeddings) from one language to the vector space of the other language via the linear translation model. We then align words according to the similarity of their vectors in the bilingual embedding space and investigate different unsupervised measures of semantic similarity exploiting bilingual embeddings and word alignments. Requiring only a limited-size set of word translation pairs between the languages, the proposed approach is applicable to virtually any pair of languages for which there exists a sufficiently large corpus, required to learn monolingual word embeddings. Experimental results on three different datasets for measuring semantic textual similarity show that our simple resource-light approach reaches performance close to that of supervised and resource-intensive methods, displaying stability across different language pairs. Furthermore, we evaluate the proposed method on two extrinsic tasks, namely extraction of parallel sentences from comparable corpora and cross-lingual plagiarism detection, and show that it yields performance comparable to those of complex resource-intensive state-of-the-art models for the respective tasks. (C) 2017 Published by Elsevier B.V. ; Part of the work presented in this article was performed during second author's research visit to the University of Mannheim, supported by Contact Fellowship awarded by the DAAD scholarship program "STIBET Doktoranden". The research of the last author has been carried out in the framework of the SomEMBED project (TIN2015-71147-C2-1-P). Furthermore, this work was partially funded by the Junior-professor funding programme of the Ministry of Science, Research and the Arts of the state of Baden-Wurttemberg (project "Deep semantic models for high-end NLP application"). ; Glavas, G.; Franco-Salvador, M.; Ponzetto, SP.; Rosso, P. (2018). A resource-light method for cross-lingual semantic textual similarity. Knowledge-Based Systems. 143:1-9. https://doi.org/10.1016/j.knosys.2017.11.041 ; S ; 1 ; 9 ; 143
|
|
Keyword:
Cross-lingual Word embeddings; LENGUAJES Y SISTEMAS INFORMATICOS; Plagiarism detection; Semantic textual similarity; Word alignment Parallel sentences alignment
|
|
URL: http://hdl.handle.net/10251/146277
https://doi.org/10.1016/j.knosys.2017.11.041
|
|
BASE
|
|
Hide details
|
|
|
| 84 |
University of Mannheim @ CLSciSumm-17: Citation-Based Summarization of Scientific Articles Using Semantic Textual Similarity
|
|
|
|
BASE
|
|
Show details
|
|
|
| 86 |
Improving neural knowledge base completion with cross-lingual projections
|
|
|
|
BASE
|
|
Show details
|
|
|
| 87 |
Leveraging event-based semantics for automated text simplification
|
|
|
|
BASE
|
|
Show details
|
|
|
| 88 |
Two layers of annotation for representing event mentions in news stories
|
|
|
|
BASE
|
|
Show details
|
|
|
| 89 |
If sentences could see: Investigating visual information for semantic textual similarity
|
|
|
|
BASE
|
|
Show details
|
|
|
| 90 |
Dual tensor model for detecting asymmetric lexico-semantic relations
|
|
|
|
BASE
|
|
Show details
|
|
|
| 92 |
Unsupervised text segmentation using semantic relatedness graphs
|
|
|
|
BASE
|
|
Show details
|
|
|
| 93 |
Spanish NER with word representations and conditional random fields
|
|
|
|
BASE
|
|
Show details
|
|
|
| 95 |
Simplifying lexical simplification: do we need simplified corpora?
|
|
|
|
BASE
|
|
Show details
|
|
|
| 97 |
TAKELAB: Medical information extraction and linking with MINERAL
|
|
Glavaš, Goran. - : Association for Computational Linguistics, 2015
|
|
BASE
|
|
Show details
|
|
|
|
|
