LEXACC

4 Last view: 2024-12-20

LEXACC - Lucene-based parallel phrase EXtractor from Comparable Corpora

ID:

LEXACC

LEXACC is a free tool for finding parallel sentences in Comparable Corpora, which has been developed during the ACCURAT project.

You don’t have the permission to edit this resource.

DistributionAvailability

Available - Restricted Use

Licence

MS Commons - BY - NC - SA

Restrictions: Academic - Non Commercial Use, Attribution, Inform Licensor, No Redistribution, Share Alike

User Nature: Academic, Commercial

Attribution Details: Please refere the following paper: Dan Ştefănescu, Radu Ion, Sabine Hunsicker, Hybrid Parallel Sentence Mining from Comparable Corpora, in Proceedings of the 16th Conference of the European Association for Machine Translation (EAMT), pp. 137-144, Trento, Italy, 2012

Distribution Access/Medium: Accessible Through Interface, Downloadable

Licensors:

Research Institute for Artificial Intelligence, Romanian Academy

Distribution rights holders:

Research Institute for Artificial Intelligence, Romanian Academy

IPR Holder

Contact Persons

toolService

Tool

Language Dependent

Input

Media type: Text

Resource type: Lexical Conceptual Resource

Modality: Written Language

Language: English, German, Romanian, Lithuanian, Latvian, Slovenian, Greek, Modern (1453-), Croatian, Spanish; Castilian

Character encoding: UTF - 8

Segmentation level: Sentence

Output

Media type: Text

Resource type: Lexical Conceptual Resource

Modality: Written Language

Language: English, German, Romanian, Lithuanian, Latvian, Slovenian, Greek, Modern (1453-)

Character encoding: UTF - 8

Annotation type: Alignment

Segmentation level: Other, Sentence

Operation

Operating system: Linux, Windows

Running time: depends on the size and on the comparability degree of the corpus.

Evaluation

Evaluated: True

Evaluation level: Usage

Evaluation type: Black Box, Glass Box

Evaluation measure: Automatic, Human

Evaluation details: Evaluation details are given in the attribution field of this metadata.

Creation

Programming language: C#

Metadata

Created: 11/27/2012

Last Updated: 11/27/2012

Source: METANET4U

3.0

Metadata Language: English (en)

Metadata Creator

Dan Ștefănescu

Documentation

Document Type: Manual

Dan Ștefănescu, LEXACC - Lucene-based parallel phrase EXtractor from Comparable Corpora, http://ws.racai.ro:9...

Keywords: parallel sentence mining, comparable corpora, Lucene, PEXACC

Document Language: English

People who looked at this resource also viewed the following: