1.
Japanese linguistics
in Apache Lucene™ and Apache Solr™
May 9th, 2012
Christian Moen
christian@atilika.com

2.
About me
• MSc. in computer science, University of Oslo, Norway
• Worked with search at FAST (now Microsoft) for 10 years
• 5 years in R&D building FAST Enterprise Search Platform in Oslo, Norway
• 5 years in Services doing solution delivery, sales, etc. in Tokyo, Japan
• Founded アティリカ株式会社 in 2009
• We help companies innovate using search technologies and good ideas
• We know information retrieval, natural language processing and big data
• We are based in Tokyo, but we have clients everywhere
• Newbie Lucene & Solr Committer
• Mostly been working on Japanese language support (Kuromoji) so far
• Please write me on christian@atilika.com or cm@apache.org

3.
Today’s topics

4.
Today’s topics
• Japanese 101 - ordering beer and toasting
• Japanese language processing
• Japanese features in Lucene/Solr

5.
Today’s topics
• Japanese 101 - ordering beer and toasting
• Japanese language processing
• Japanese features in Lucene/Solr

6.
Today’s topics
• Japanese 101 - ordering beer and toasting
• Japanese language processing
• Japanese features in Lucene/Solr

7.
Japanese 101

8.
ビールください
bi-ru kudasai

9.
ビールください
bi-ru kudasai
A beer, please

10.
ありがとうございます！
arigatō gozaimasu!

11.
ありがとうございます！
arigatō gozaimasu!
Thank you very much!

12.
乾杯！
kanpai!

13.
乾杯！
kanpai!
Cheers!

14.
ＪＲ新宿駅の近くにビールを飲みに行こうか？
JR Shinjuku eki no chikaku ni bi-ru ō nomi ni ikō ka?

15.
ＪＲ新宿駅の近くにビールを飲みに行こうか？
JR Shinjuku eki no chikaku ni bi-ru ō nomi ni ikō ka?
Shall we go for a beer near JR Shinjuku station?

16.
ＪＲ新宿駅の近くにビールを飲みに行こうか？

17.
Romaji - ローマ字
・Latin characters (26+)
・Used for proper nouns, etc.
ＪＲ新宿駅の近くにビールを飲みに行こうか？

18.
Katakana - カタカナ
・Phonetic script (~50)
・Typically used for loan words
ＪＲ新宿駅の近くにビールを飲みに行こうか？

19.
ＪＲ新宿駅の近くにビールを飲みに行こうか？
Kanji - 漢字
・Chinese characters (50,000+)
・Used for stems & proper nouns

20.
ＪＲ新宿駅の近くにビールを飲みに行こうか？
Hiragana - ひらがな
・Phonetic script (~50)
・Used for inflections & particles

21.
Romaji - ローマ字 Katakana - カタカナ
・Latin characters (26+) ・Phonetic script (~50)
・Used for proper nouns, etc. ・Typically used for loan words
ＪＲ新宿駅の近くにビールを飲みに行こうか？
Kanji - 漢字 Hiragana - ひらがな
・Chinese characters (50,000+) ・Phonetic script (~50)
・Used for stems & proper nouns ・Used for inflections & particles

22.
ＪＲ新宿駅の近くにビールを飲みに行こうか？

23.
ＪＲ新宿駅の近くにビールを飲みに行こうか？
? What are the words in this sentence?

24.
ＪＲ新宿駅の近くにビールを飲みに行こうか？
? What are the words in this sentence?
! Words are implicit in Japanese - there
is no white space that separates them

25.
ＪＲ新宿駅の近くにビールを飲みに行こうか？
? How do we index this for search, then?

26.
ＪＲ新宿駅の近くにビールを飲みに行こうか？
? How do we index this for search, then?
! We need to segment text into tokens first

27.
! Two major approaches for segmentation
1. n-gramming
2. morphological analysis
(statistical approach)

28.
n-gramming (n=2)
ＪＲ 新 宿 駅 の 近 く に ビ ー ル を 飲 み に 行 こ う か ？
Shall we go for a beer near JR Shinjuku station?

29.
n-gramming (n=2)
ＪＲ 新 宿 駅 の 近 く に ビ ー ル を 飲 み に 行 こ う か ？
ＪＲ Shall we go for a beer near JR Shinjuku station?
n=2
ＪＲ

30.
n-gramming (n=2)
Ｊ Ｒ新 宿 駅 の 近 く に ビ ー ル を 飲 み に 行 こ う か ？
ＪＲ Shall we go for a beer near JR Shinjuku station?
n=2
Ｒ新
ＪＲ Ｒ新

31.
n-gramming (n=2)
Ｊ Ｒ 新宿 駅 の 近 く に ビ ー ル を 飲 み に 行 こ う か ？
ＪＲ Shall we go for a beer near JR Shinjuku station?
n=2
Ｒ新
新宿
ＪＲ Ｒ新 新宿

32.
n-gramming (n=2)
Ｊ Ｒ 新 宿駅 の 近 く に ビ ー ル を 飲 み に 行 こ う か ？
ＪＲ Shall we go for a beer near JR Shinjuku station?
n=2
Ｒ新
新宿
宿駅
ＪＲ Ｒ新 新宿 宿駅

33.
n-gramming (n=2)
Ｊ Ｒ 新 宿 駅の 近 く に ビ ー ル を 飲 み に 行 こ う か ？
ＪＲ Shall we go for a beer near JR Shinjuku station?
n=2
Ｒ新
新宿
宿駅
駅の
ＪＲ Ｒ新 新宿 宿駅 駅の

34.
n-gramming (n=2)
Ｊ Ｒ 新 宿 駅 の近 く に ビ ー ル を 飲 み に 行 こ う か ？
ＪＲ Shall we go for a beer near JR Shinjuku station?
n=2
Ｒ新
新宿
宿駅
駅の
の近
ＪＲ Ｒ新 新宿 宿駅 駅の の近

35.
n-gramming (n=2)
Ｊ Ｒ 新 宿 駅 の 近く に ビ ー ル を 飲 み に 行 こ う か ？
ＪＲ Shall we go for a beer near JR Shinjuku station?
n=2
Ｒ新
新宿
宿駅
駅の
の近
近く
ＪＲ Ｒ新 新宿 宿駅 駅の の近 近く

36.
Problems with n-gramming

37.
Problems with n-gramming
ＪＲ Ｒ新 新宿 宿駅 駅の の近 近く ...

38.
Problems with n-gramming
ＪＲ Ｒ新 新宿 宿駅 駅の の近 近く ...
●

39.
Problems with n-gramming
ＪＲ Ｒ新 新宿 宿駅 駅の の近 近く ...
● ×

40.
Problems with n-gramming
ＪＲ Ｒ新 新宿 宿駅 駅の の近 近く ...
● × ●

41.
Problems with n-gramming
ＪＲ Ｒ新 新宿 宿駅 駅の の近 近く ...
● × ● ×
change of
semantics!
means ‘post town’, ‘relay station’ or ‘stage’

42.
Problems with n-gramming
ＪＲ Ｒ新 新宿 宿駅 駅の の近 近く ...
● × ● × ×
change of
semantics!
means ‘post town’, ‘relay station’ or ‘stage’

43.
Problems with n-gramming
ＪＲ Ｒ新 新宿 宿駅 駅の の近 近く ...
● × ● × × ×
change of
semantics!
means ‘post town’, ‘relay station’ or ‘stage’

44.
Problems with n-gramming
ＪＲ Ｒ新 新宿 宿駅 駅の の近 近く ...
● × ● × × × ●
change of
semantics!
means ‘post town’, ‘relay station’ or ‘stage’

45.
Problems with n-gramming
ＪＲ Ｒ新 新宿 宿駅 駅の の近 近く ...
● × ● × × × ●
change of
semantics!
means ‘post town’, ‘relay station’ or ‘stage’
• Does not preserve meaning well and often changes semantics
• Impacts on ranking - search precision (many false positives)
Generates many terms per document or query
Impacts on index size and search performance
Sometimes appropriate for certain search applications
Compliance, e-commerce with non product names, ...

46.
Problems with n-gramming
ＪＲ Ｒ新 新宿 宿駅 駅の の近 近く ...
● × ● × × × ●
change of
semantics!
means ‘post town’, ‘relay station’ or ‘stage’
• Does not preserve meaning well and often changes semantics
• Impacts on ranking - search precision (many false positives)
• Also generates many terms per document or query
• Impacts on index size and performance
Sometimes appropriate for certain search applications
Compliance, e-commerce with non product names, ...

47.
Problems with n-gramming
ＪＲ Ｒ新 新宿 宿駅 駅の の近 近く ...
● × ● × × × ●
change of
semantics!
means ‘post town’, ‘relay station’ or ‘stage’
• Does not preserve meaning well and often changes semantics
• Impacts on ranking - search precision (many false positives)
• Also generates many terms per document or query
• Impacts on index size and performance
• Still sometimes appropriate for certain search applications
• Compliance, e-commerce with special product names, ...

48.
Morphological analysis
ＪＲ 新 宿 駅 の 近 く に ビ ー ル を 飲 み に 行 こ う か ？
Shall we go for a beer near JR Shinjuku station?

49.
Morphological analysis
ＪＲ 新 宿 駅 の 近 く に ビ ー ル を 飲 み に 行 こ う か ？
Shall we go for a beer near JR Shinjuku station?
ＪＲ 新宿 駅 の 近く に ビ ー ル を 飲み に 行こ う か ？

50.
Morphological analysis
ＪＲ 新 宿 駅 の 近 く に ビ ー ル を 飲 み に 行 こ う か ？
Shall we go for a beer near JR Shinjuku station?
ＪＲ 新宿 駅 の 近く に ビ ー ル を 飲み に 行こ う か ？
● ● ● ● ● ● ● ● ● ● ● ● ● ●

51.
Morphological analysis
ＪＲ 新 宿 駅 の 近 く に ビ ー ル を 飲 み に 行 こ う か ？
Shall we go for a beer near JR Shinjuku station?
ＪＲ 新宿 駅 の 近く に ビ ー ル を 飲み に 行こ う か ？
● ● ● ● ● ● ● ● ● ● ● ● ● ●
• Tokens reflect what a Japanese speaker consider as words
• Machine-learned statistical approach
• CRFs decoded using Viterbi
• Also does part-of-speech tagging, readings for kanji, etc.
• Several statistical models available with high accuracy (F > 0.97)
• Models/dictionaries are available as IPADIC, UniDic, ...

52.
Morphological analysis
ＪＲ 新 宿 駅 の 近 く に ビ ー ル を 飲 み に 行 こ う か ？
Shall we go for a beer near JR Shinjuku station?
ＪＲ 新宿 駅 の 近く に ビ ー ル を 飲み に 行こ う か ？
● ● ● ● ● ● ● ● ● ● ● ● ● ●
• Tokens reflect what a Japanese speaker consider as words
• Machine-learned statistical approach
• Conditional Random Fields (CRFs) decoded using Viterbi
• Also does part-of-speech tagging, extract readings for kanji, etc.
• Several statistical models available with high accuracy (F > 0.97)
• Models/dictionaries are available as IPADIC, UniDic, ...

53.
Morphological analysis
ＪＲ 新 宿 駅 の 近 く に ビ ー ル を 飲 み に 行 こ う か ？
Shall we go for a beer near JR Shinjuku station?
ＪＲ 新宿 駅 の 近く に ビ ー ル を 飲み に 行こ う か ？
● ● ● ● ● ● ● ● ● ● ● ● ● ●
• Tokens reflect what a Japanese speaker consider as words
• Machine-learned statistical approach
• Conditional Random Fields (CRFs) decoded using Viterbi
• Also does part-of-speech tagging, readings for kanji, etc.
• Several statistical models available with high accuracy (F > 0.97)
• Models/dictionaries are available as IPADIC, UniDic, ...

54.
How does this actually work?

55.
Demo

56.
Japanese support in
Lucene and Solr

57.
Japanese in Lucene/Solr

58.
Japanese in Lucene/Solr
! New feature in Lucene/Solr 3.6

59.
Japanese in Lucene/Solr
! New feature in Lucene/Solr 3.6
! Available out-of-the-box

60.
Japanese in Lucene/Solr
! New feature in Lucene/Solr 3.6
! Available out-of-the-box
! Easy to use with reasonable defaults

61.
Japanese in Lucene/Solr
! New feature in Lucene/Solr 3.6
! Available out-of-the-box
! Easy to use with reasonable defaults
! Provides sophisticated Japanese linguistics

62.
Japanese in Lucene/Solr
! New feature in Lucene/Solr 3.6
! Available out-of-the-box
! Easy to use with reasonable defaults
! Provides sophisticated Japanese linguistics
! Customisable

63.
How do we use it?

64.
How do we use it?
! Use JapaneseAnalyzer

65.
How do we use it?
! Use JapaneseAnalyzer
! Use field type “text_ja”
in example schema.xml

66.
Demo

67.
Feature summary / text_ja analyzer chain
Segments Japanese text into tokens with very high accuracy
JapaneseTokenizer • Token attributes for part-of-speech, base form, readings, etc.
• Compound segmentation with compound synonyms
• Segmentation is customisable using user dictionaries

68.
Feature summary / text_ja analyzer chain
Segments Japanese text into tokens with very high accuracy
JapaneseTokenizer • Token attributes for part-of-speech, base form, readings, etc.
• Compound segmentation with compound synonyms
• Segmentation is customisable using user dictionaries
JapaneseBaseFormFilter Adjective and verb lemmatisation (by reduction)

69.
Feature summary / text_ja analyzer chain
Segments Japanese text into tokens with very high accuracy
JapaneseTokenizer • Token attributes for part-of-speech, base form, readings, etc.
• Compound segmentation with compound synonyms
• Segmentation is customisable using user dictionaries
JapaneseBaseFormFilter Adjective and verb lemmatisation (by reduction)
Stop-words removal based on part-of-speech tags
JapanesePartOfSpeechStopFilter
See example/solr/conf/lang/stoptags_ja.txt

70.
Feature summary / text_ja analyzer chain
Segments Japanese text into tokens with very high accuracy
JapaneseTokenizer • Token attributes for part-of-speech, base form, readings, etc.
• Compound segmentation with compound synonyms
• Segmentation is customisable using user dictionaries
JapaneseBaseFormFilter Adjective and verb lemmatisation (by reduction)
Stop-words removal based on part-of-speech tags
JapanesePartOfSpeechStopFilter
See example/solr/conf/lang/stoptags_ja.txt
CJKWidthFilter Character width normalisation (fast Unicode NFKC subset)

71.
Feature summary / text_ja analyzer chain
Segments Japanese text into tokens with very high accuracy
JapaneseTokenizer • Token attributes for part-of-speech, base form, readings, etc.
• Compound segmentation with compound synonyms
• Segmentation is customisable using user dictionaries
JapaneseBaseFormFilter Adjective and verb lemmatisation (by reduction)
Stop-words removal based on part-of-speech tags
JapanesePartOfSpeechStopFilter
See example/solr/conf/lang/stoptags_ja.txt
CJKWidthFilter Character width normalisation (fast Unicode NFKC subset)
Stop-words removal
StopFilter
See example/solr/conf/lang/stopwords_ja.txt

72.
Feature summary / text_ja analyzer chain
Segments Japanese text into tokens with very high accuracy
JapaneseTokenizer • Token attributes for part-of-speech, base form, readings, etc.
• Compound segmentation with compound synonyms
• Segmentation is customisable using user dictionaries
JapaneseBaseFormFilter Adjective and verb lemmatisation (by reduction)
Stop-words removal based on part-of-speech tags
JapanesePartOfSpeechStopFilter
See example/solr/conf/lang/stoptags_ja.txt
CJKWidthFilter Character width normalisation (fast Unicode NFKC subset)
Stop-words removal
StopFilter
See example/solr/conf/lang/stopwords_ja.txt
JapaneseKatakanaStemFilter Normalises common katakana spelling variations

73.
Feature summary / text_ja analyzer chain
Segments Japanese text into tokens with very high accuracy
JapaneseTokenizer • Token attributes for part-of-speech, base form, readings, etc.
• Compound segmentation with compound synonyms
• Segmentation is customisable using user dictionaries
JapaneseBaseFormFilter Adjective and verb lemmatisation (by reduction)
Stop-words removal based on part-of-speech tags
JapanesePartOfSpeechStopFilter
See example/solr/conf/lang/stoptags_ja.txt
CJKWidthFilter Character width normalisation (fast Unicode NFKC subset)
Stop-words removal
StopFilter
See example/solr/conf/lang/stopwords_ja.txt
JapaneseKatakanaStemFilter Normalises common katakana spelling variations
LowerCaseFilter Lowercases

74.
Feature details

75.
Compound nouns
? How do we deal with compound nouns?

76.
Compound nouns
? How do we deal with compound nouns?
Japanese English
関西国際空港 Kansai International Airport
シニアソフトウェアエンジニア Senior Software Engineer

77.
Compound nouns
? How do we deal with compound nouns?
Japanese English
関西国際空港 Kansai International Airport
シニアソフトウェアエンジニア Senior Software Engineer
! These are one word in Japanese, so
searching for 空港 (airport) doesn’t match

78.
Compound nouns
? How do we deal with compound nouns?
Japanese English
関西国際空港 Kansai International Airport
シニアソフトウェアエンジニア Senior Software Engineer
! These are one word in Japanese, so
searching for 空港 (airport) doesn’t match
! We need to segment the compounds, too

79.
Compound segmentation
関西国際空港
Kansai International Airport
シニアソフトウェアエンジニナ
Senior Software Engineer
! We are using a heuristic to implement this

80.
Compound segmentation
関西国際空港 関西
Kansai International Airport Kansai
シニアソフトウェアエンジニナ シニア
Senior Software Engineer Senior
! We are using a heuristic to implement this

81.
Compound segmentation
関西国際空港 関西 国際
Kansai International Airport Kansai International
シニアソフトウェアエンジニナ シニア ソフトウェア
Senior Software Engineer Senior Software
! We are using a heuristic to implement this

82.
Compound segmentation
関西国際空港 関西 国際 空港
Kansai International Airport Kansai International Airport
シニアソフトウェアエンジニナ シニア ソフトウェア エンジニナ
Senior Software Engineer Senior Software Engineer
! We are using a heuristic to implement this

83.
Compound synonym tokens
Position 1 Position 2 Position 3
関西 国際 空港
関西国際空港
• Segment the compounds into its part
• Good for recall - we can also search and match 空港 (airport)
• We keep the compound itself as a synonym
• Good for precision with an exact hit because of IDF
• Approach benefits both precision and recall for overall good ranking
• JapaneseTokenizer actually returns a graph of tokens

84.
Compound synonym tokens
Position 1 Position 2 Position 3
関西 国際 空港
関西国際空港
• Segment the compounds into its parts
• Good for recall - we can also search and match 空港 (airport)
• We keep the compound itself as a synonym
• Good for precision with an exact hit because of IDF
• Approach benefits both precision and recall for overall good ranking
• JapaneseTokenizer actually returns a graph of tokens

85.
Compound synonym tokens
Position 1 Position 2 Position 3
関西 国際 空港
関西国際空港
• Segment the compounds into its parts
• Good for recall - we can also search and match 空港 (airport)
• We keep the compound itself as a synonym
• Good for precision with an exact hit because of IDF
• Approach benefits both precision and recall for overall good ranking
• JapaneseTokenizer actually returns a graph of tokens

86.
Compound synonym tokens
Position 1 Position 2 Position 3
関西 国際 空港
関西国際空港
• Segment the compounds into its parts
• Good for recall - we can also search and match 空港 (airport)
• We keep the compound itself as a synonym
• Good for precision with an exact hit because of IDF
• Approach benefits both precision and recall for overall good ranking
• JapaneseTokenizer actually returns a graph of tokens

87.
Character width normalisation
? How do we deal with character widths?
Half-width・半角 Full-width・全角
Lucene Ｌｕｃｅｎｅ
ｶﾀｶﾅ カタカナ
123 １２３

88.
Character width normalisation
? How do we deal with character widths?
Half-width・半角 Full-width・全角
Lucene Ｌｕｃｅｎｅ
ｶﾀｶﾅ カタカナ
123 １２３
! Use CJKWidthFilter to normalise them
(Unicode NFKC subset)
Input text Ｌｕｃｅｎｅ ｶﾀｶﾅ １２３
CJKWidthFilter Lucene カタカナ 123
half-width full-width half-width

89.
Katakana end-vowel stemming
? A common spelling variation in
katakana is a end long-vowel sound
English Japanese spelling variations
manager マネージャー マネージャ マネジャー

90.
Katakana end-vowel stemming
? A common spelling variation in
katakana is a end long-vowel sound
English Japanese spelling variations
manager マネージャー マネージャ マネジャー
! We JapaneseKatakanaStemFilter to
normalise/stem end-vowel for long terms
Input text コピー マネージャー マネージャ マネジャー
JapaneseKatakanaStemFilter コピー マネージャ マネージャ マネジャ
copy manager manager “manager”

91.
Lemmatisation
? Japanese adjectives and verbs are highly
inflected, how do we deal with that?

92.
Lemmatisation
? Japanese adjectives and verbs are highly
inflected, how do we deal with that?
Dictionary form
買う
kau
to buy

93.
Lemmatisation
? Japanese adjectives and verbs are highly
inflected, how do we deal with that?
Dictionary form Inflected forms (not exhaustive)
買いなさい 買いませんでしたら 買える 買わせられる
買う 買いなさるな
買いましたら
買いませんでしたり
買いませんなら
買おう
買った
買わせる
買わない
買いましたり 買うだろう 買ったら 買わないだろう
kau 買いまして
買いましょう
買うでしょう
買うな
買ったり
買って
買わないで
買わないでしょう
買わせない
to buy
買います 買うまい 買わなかった
買いますまい 買え 買わせます 買わなかったら
買いませば 買えない 買わせません 買わなかったり
買いません 買えば 買わせられない 買わなければ
買いませんで 買えます 買わせられます 買われない
買いませんでした 買えません 買わせられません 買われます

94.
Lemmatisation
? Japanese adjectives and verbs are highly
inflected, how do we deal with that?
Dictionary form Inflected forms (not exhaustive)
買いなさい 買いませんでしたら 買える 買わせられる
買う 買いなさるな
買いましたら
買いませんでしたり
買いませんなら
買おう
買った
買わせる
買わない
買いましたり 買うだろう 買ったら 買わないだろう
kau 買いまして
買いましょう
買うでしょう
買うな
買ったり
買って
買わないで
買わないでしょう
買わせない
to buy
買います 買うまい 買わなかった
買いますまい 買え 買わせます 買わなかったら
買いませば 買えない 買わせません 買わなかったり
買いません 買えば 買わせられない 買わなければ
買いませんで 買えます 買わせられます 買われない
買いませんでした 買えません 買わせられません 買われます
! Use JapaneseBaseformFilter to normalise
inflected adjectives and verbs to dictionary form
(lemmatisation by reduction)

95.
User dictionaries
• Own dictionaries can be used for ad hoc
segmentation, i.e. to override default model
• File format is simple and there’s no need to
assign weights, etc. before using them
• Example custom dictionary:
# Custom segmentation and POS entry for long entries
関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
# Custom reading and POS former sumo wrestler Asashoryu
朝青龍,朝青龍,アサショウリュウ,カスタム人名

96.
Japanese focus in 4.0
• Improvements in JapaneseTokenizer
• Improved search mode for katakana compounds
• Improved unknown word segmentation
• Some performance improvements
• CharFilters for various character normalisations
• Dates and numbers
• Repetition marks (odoriji)
• Japanese spell-checker
• Robert and Koji almost got this into 3.6, but it got
postponed because of API changes being necessary

97.
Acknowledgements
Robert Muir
Thanks for the heavy lifting integrating Kuromoji into Lucene
and always reviewing my patches quickly and friendly help
Michael McCandless
Thanks for streaming Viterbi and synonym compounds!
Uwe Schindler
Thanks for performance improvements + being the policeman
Simon Willnauer
Thanks for doing the Kuromoji code donation process so well
Gaute Lambertsen & Gerry Hocks
Thanks for presentation feedback and being great colleagues

98.
Q&A

99.
ありがとうございました！
arigatō gozaimashita!
Thank you very much!