Install the Lingua-Align

本文介绍了一个用于并行语料库自动对齐的工具箱Lingua::Align,该工具集包括一系列命令行工具,支持多种特征集和对齐策略。文中详细描述了如何在Ubuntu 12.04上安装所需的依赖软件,包括Perl模块和megam工具,并提供了常见安装问题的解决方法。

I am writing this article for remarking.

Ubuntu version: 12.04


Introduction

Lingua::Align is a collection of command-line tools for automatic tree and word alignment of parallel corpora. The main purpose is to provide an experimental toolbox for experiments with various feature sets and alignment strategies. Alignment is based on local classification and alignment inference. The local classifier is typically trained on available aligned training data. We use a log-linear model for discriminative binary classification using the maximum entropy learning package megam (Hal Daume III).


Installation

When install this tool, the requirement is a recent version of Perl, XML::Parser, Algorithm::Munkres and megaminstalled on your system.


  • Install XML::Parser
sudo apt-get install libxml-parser-perl

  • Install Algorithm::Munkres
sudo apt-get install libalgorithm-munkres-perl

The software here is an implementation ofmaximum likelihood and maximum a posterior optimization of theparameters of these models. The algorithms used are much moreefficient than the iterative scaling techniques used in almost everyother maxent package out there.


The sources are in util.ml, data.ml, cg.ml, bfgs.ml and data.ml. There is a Makefile to you can build it on any system that has ocaml. (http://caml.inria.fr)

So we can just install the ocaml simply by execute

sudo apt-get install ocaml
make

Download the package from the given link above and unzip it.

You can either install the perl modules and binaries as usual:

perl Makefile.PL
make
make install

Trouble shot

When install the megem, it will return the following error:

/user/bin/ld: cannot find -lstr

This is a bug in the OCaml bug tracker:Bug 5247

The fix method is:

locate libcamlstr
cd /usr/lib/ocaml
sudo ln -s libcamlstr.a libstr.a

Experiment

Run your own experiment by following Tutorial

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值