nlp-tools

KO | EN

gitlite — search

#javascript #hacktoberfest #ai #typescript #llm #go #deep-learning #docker #java #windows #vue #awesome-list #ios #open-source

(★ 12)

C++ implementation of a part-of-speech (POS) tagger using the lookahead tagging algorithm.

nlp-tools 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# nlp-tools

This project contains the C++ source code for a general-purpose part-of-speech (POS) tagger using the lookahead tagging algorithm described in [[1]](http://www.aclweb.org/anthology/W11-0328.pdf).

This source is based on the reference implementation provided by the paper authors (http://www.logos.t.u-tokyo.ac.jp/~tsuruoka/lapos/), originally under MIT license.

## Building

This project uses CMake. On GNU/Linux, use the following commands to compile:

% mkdir build
    % cd build
    % cmake ..

## Training

You can build a tagging model using your own annotated corpus. Use the `tool_train` command:

% ./tool_train -m model.dat -i tagged-training.txt

## Predicting

Once you have trained the model, you can use it with `tool_predict` to predict tags for other sentences.

% ./tool_predict -m modal.dat -i untagged-test.txt > tmp

Note that the input must be one-sentence-per-line, and the words need to be already tokenized with white spaces.

## Evaluating

You can evaluate tagging accuracy by the `tool_evaluate` command.

% ./tool_evaluate tagged-test.txt tmp

## References

[1] Yoshimasa Tsuruoka, Yusuke Miyao and Jun'ichi Kazama;
      Learning with Lookahead: Can History-based Models Rival Globally Optimized Models?
      In Proceedings of the Fifteenth Conference on Computational Natural Language Learning (CoNLL), 
      pp. 238-246, 2011.

## License

Except where explicitly indicated otherwise, all source codes of this project are provide under [Apache License 2.0](http://www.apache.org/licenses/LICENSE-2.0).

nlp-tools

nlp-tools 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

nlp-tools

nlp-tools 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README