MeCab : Yet Another Part-of-Speech and Morphological Analyzer

By Takumitsu Kudo. 2005

616 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Learning Word Vectors for 157 Languages (2018, methodology): “We used the Stanford word segmenter (Chang et al., 2008) for Chinese, Mecab (Kudo, 2005) for Japanese and UETseg-menter (Nguyen and Le, 2016) for Vietnamese.”
Stock Price Prediction by Deep Neural Generative Model of News Articles (2018, methodology): “Titles were preprocessed using the morphological analyzer MeCab [25] and embedded to nx-dimensional vectors using the Paragraph Vector algorithm [19].”
Deep learning for stock prediction using numerical and textual information (2016, methodology): “used MeCab [19] as the morphological analyzer, and added Wikipedia entries and Nihon Keizai Shinbun’s keywords to the dictionary of MeCab to deal with possible proper nouns.”
MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages (2022, methodology): “As mentioned in Section 5.1, we leave exploration of more sophisticated spacing techniques for slot filling (such as MeCab; Kudo 2005) to future work.”
Visual Question Answering Dataset for Bilingual Image Understanding: A Study of Cross-Lingual Transfer Using Attention Maps (2018, background): “, 1989), to extract image features and MeCab (Kudo, 2005) to tokenize Japanese sentences.”
Overview of the 5th Workshop on Asian Translation (2019, methodology): “…we used three different tools: Juman version 7.0 (Kurohashi et al., 1994), KyTea 0.4.6 (Neubig et al., 2011) with full SVM model23 and MeCab 0.996 (Kudo, 2005) with IPA dictionary 2.7.0.24 For Chinese segmentation, we used two different tools: KyTea 0.4.6 with full SVM Model in MSR model and…”
Overview of the 4th Workshop on Asian Translation (2017, neutral): “996 (Kudo, 2005) with IPA dictionary 2.”
Byte Pair Encoding is Suboptimal for Language Model Pretraining (2020, methodology): “For Japanese, we compare subword tokenizations of Japanese Wikipedia sentences to morphological reference tokenizations produced using the MeCab morphological analysis and tokenization tool (Kudo, 2006) using version 2.”
One Model, Many Languages: Meta-learning for Multilingual Text-to-Speech (2020, methodology): “We romanized Japanese with MeCab and Romkan [24, 25], Chinese using Pinyin [26].”
Pointwise Prediction for Robust, Adaptable Japanese Morphological Analysis (2011, methodology): “As a representative of joint sequence-based MA described in 2.1, we used MeCab (Kudo, 2006), an open source implementation of Kudo et al. (2004)’s CRF-based method (we will call this JOINT ).”
Learning to Generate Questions by Learning to Recover Answer-containing Sentences (2021, positive): “Mecab (Kudo, 2006) is used for Korean tokenizer.”