KaWAT: A Word Analogy Task Dataset for Indonesian

06/17/2019 ∙ by Kemal Kurniawan, et al. ∙ 0

We introduced KaWAT (Kata Word Analogy Task), a new word analogy task dataset for Indonesian. We evaluated on it several existing pretrained Indonesian word embeddings and embeddings trained on Indonesian online news corpus. We also tested them on two downstream tasks and found that pretrained word embeddings helped either by reducing the training epochs or yielding significant performance gains.

READ FULL TEXT VIEW PDF
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

Code Repositories

kawat

Kata Word Analogy Task for Indonesian.


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.

1 Introduction

Despite the existence of various Indonesian pretrained word embeddings, there are no publicly available Indonesian analogy task datasets on which to evaluate these embeddings. Consequently, it is unknown if Indonesian word embeddings introduced in, e.g., [Al-Rfou et al.2013] and [Grave et al.2018], capture syntactic or semantic information as measured by analogy tasks. Also, such embeddings are usually trained on Indonesian Wikipedia [Al-Rfou et al.2013, Bojanowski et al.2017] whose size is relatively small, approximately 60M tokens. Therefore, in this work, we introduce KaWAT (Kata Word Analogy T

ask), an Indonesian word analogy task dataset, and new Indonesian word embeddings pretrained on 160M tokens of online news corpus. We evaluated these embeddings on KaWAT, and also tested them on POS tagging and text summarization as representatives of syntactic and semantic downstream task respectively.

2 Methodology

We asked an Indonesian linguist to help build KaWAT based on English analogy task datasets such as Google Word Analogy [Mikolov et al.2013a] and BATS [Gladkova et al.2016]. Following those works, we split the analogy tasks into two categories, syntax and semantic. We included mostly morphological analogies in the syntax category, leveraging the richness of Indonesian inflectional morphology. For semantic, we included analogies such as antonyms, country capitals and currencies, gender-specific words, measure words, and Indonesian province capitals. In total, we have 15K syntactic and 19K semantic analogy queries. KaWAT is available online.111https://github.com/kata-ai/kawat

One of the goals of this work is to evaluate and compare existing Indonesian pretrained word embeddings. We used fastText pretrained embeddings introduced in [Bojanowski et al.2017] and [Grave et al.2018], which have been trained on Indonesian Wikipedia and Indonesian Wikipedia plus Common Crawl data respectively. We refer to them as Wiki/fastText and CC/fastText hereinafter. We also used another two pretrained embeddings: polyglot embedding trained on Indonesian Wikipedia [Al-Rfou et al.2013] and NLPL embedding trained on the Indonesian portion of CoNLL 2017 corpus [Fares et al.2017].

For training our word embeddings, we used online news corpus obtained from Tempo.222https://www.tempo.co We used Tempo newspaper and magazine articles up to year 2014. This corpus contains roughly 400K articles, 160M word tokens, and 600K word types. To train the word embeddings, we experimented with three algorithms: word2vec [Mikolov et al.2013b], fastText [Bojanowski et al.2017], and GloVe [Pennington et al.2014]. We refer to them henceforth as Tempo/word2vec, Tempo/fastText, and Tempo/GloVe respectively. We used gensim333https://radimrehurek.com/gensim to run word2vec and fastText and the original C implementation for GloVe.444https://github.com/stanfordnlp/GloVe

For all three, we used their default hyperparameters, i.e. no tuning was performed. Our three embeddings are available online.

555https://drive.google.com/open?id=1T9RmF0nHwN742aDkkQbjimpUCLgeVkhT

Evaluation on KaWAT was done using gensim with its KeyedVectors.most_similar

method. Since the vocabularies of the word embeddings are different, for a fair comparison, we first removed analogy queries containing words that do not exist in any vocabulary. In other words, we only kept queries whose words all exist in all vocabularies. After this process, there were roughly 6K syntactic and 1.5K semantic queries. We performed evaluation by computing 95% confidence interval of the accuracy at rank 1 by bootstrapping. Our implementation code is available online.

666https://github.com/kata-ai/id-word2vec

3 Results

3.1 Word analogy results

We found that on syntactic analogies, Wiki/fastText achieved 2.7% accuracy, which significantly outperformed the others, even CC/fastText which has been trained on a much larger corpus. Other embeddings performed poorly, mostly less than 1% of accuracy. The overall trend of low accuracy scores attests to the difficulty of syntactic KaWAT analogies, making it suitable as benchmark for future research.

On semantic analogies, Tempo/GloVe clearly outperformed the others with 20.42% accuracy, except Tempo/word2vec. Surprisingly, we found that Tempo/fastText performed very poorly with less than 1% accuracy, even worse than Wiki/fastText which has been trained on a much smaller data. Overall, the accuracies on semantic are also low, less than 25%, which again attests to the suitability of KaWAT as benchmark for future work.

3.2 Downstream task results

To check how useful these embeddings are for downstream tasks, we evaluated them on POS tagging and text summarization task. For each task, we compared two embeddings, which are the best off-the-shelf pretrained embedding and our proposed embedding on the syntactic (for POS) and semantic (for summarization) analogy task respectively.777

We performed paired t-test and found Tempo/GloVe to be the best among our Tempo embeddings (

). We used the same model and setting as [Kurniawan and Aji2018] for POS tagging and [Kurniawan and Louvan2018] for summarization. However, for computational reasons, we tuned only the learning rate using grid search, and only used the first fold of the summarization dataset. Our key finding from the POS tagging experiment is that using the two embeddings did not yield significant gain on test score compared with not using any pretrained embedding (around ). However, on average, using Wiki/fastText resulted in 20% fewer training epochs, compared with only 4% when using Tempo/GloVe. For the summarization experiment, Tempo/GloVe was significantly better888As evidenced by the 95% confidence interval reported by the ROUGE script. than CC/fastText in ROUGE-1 and ROUGE-L scores (66.63 and 65.93 respectively). The scores of using CC/fastText was on par to those of not using any pretrained word embedding, and we did not observe fewer training epochs when using pretrained word embedding.

4 Conclusion

We introduced KaWAT, a new dataset for Indonesian word analogy task, and evaluated several Indonesian pretrained word embeddings on it. We found that (1) in general, accuracies on the analogy tasks were low, suggesting that improvements for Indonesian word embeddings are still possible and KaWAT is hard enough to be the benchmark dataset for that purpose, (2) on syntactic analogies, embedding by [Bojanowski et al.2017] performed best and yielded 20% fewer training epochs when employed for POS tagging, and (3) on semantic analogies, GloVe embedding trained on Tempo corpus performed best and produced significant gains on ROUGE-1 and ROUGE-L scores when used for text summarization.

5 Acknowledgment

We thank Tempo for their support and access to their news and magazine corpora. We also thank Rezka Leonandya and Fariz Ikhwantri for reviewing the earlier version of this manuscript.

References

  • [Al-Rfou et al.2013] Rami Al-Rfou, Bryan Perozzi, and Steven Skiena. 2013. Polyglot: Distributed Word Representations for Multilingual NLP. In Proceedings of the Seventeenth Conference on Computational Natural Language Learning, pages 183–192, Sofia, Bulgaria. Association for Computational Linguistics.
  • [Bojanowski et al.2017] Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017.

    Enriching word vectors with subword information.

    Transactions of the Association for Computational Linguistics, 5:135–146.
  • [Fares et al.2017] Murhaf Fares, Andrey Kutuzov, Stephan Oepen, and Erik Velldal. 2017. Word vectors, reuse, and replicability: Towards a community repository of large-text resources. In Proceedings of the 21st Nordic Conference on Computational Linguistics, pages 271–276, Gothenburg, Sweden, May. Linköping University Electronic Press, Linköpings universitet / Language Technology Group, Department of Informatics, University of Oslo, Norway.
  • [Gladkova et al.2016] Anna Gladkova, Aleksandr Drozd, and Satoshi Matsuoka. 2016. Analogy-based detection of morphological and semantic relations with word embeddings: What works and what doesn’t. In Proceedings of the NAACL Student Research Workshop, pages 8–15, San Diego, California. Association for Computational Linguistics.
  • [Grave et al.2018] Edouard Grave, Piotr Bojanowski, Prakhar Gupta, Armand Joulin, and Tomas Mikolov. 2018. Learning Word Vectors for 157 Languages. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC-2018), Miyazaki, Japan. European Language Resource Association.
  • [Kurniawan and Aji2018] Kemal Kurniawan and Alham Fikri Aji. 2018. Toward a Standardized and More Accurate Indonesian Part-of-Speech Tagging. In 2018 International Conference on Asian Language Processing (IALP), pages 303–307, Bandung, Indonesia, November. IEEE.
  • [Kurniawan and Louvan2018] Kemal Kurniawan and Samuel Louvan. 2018. IndoSum: A New Benchmark Dataset for Indonesian Text Summarization. In 2018 International Conference on Asian Language Processing (IALP), pages 215–220, Bandung, Indonesia, November. IEEE.
  • [Mikolov et al.2013a] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013a. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.
  • [Mikolov et al.2013b] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S. Corrado, and Jeff Dean. 2013b. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems, pages 3111–3119.
  • [Pennington et al.2014] Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global Vectors for Word Representation. In

    Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

    , pages 1532–1543, Doha, Qatar. Association for Computational Linguistics.