7

I'm working on a dictionary tool that provides, as an auto-assist, transcription of Chinese characters into corresponding (Modern Standard Mandarin) pinyin+tones on a naive, character-per-character basis without lexical parsing (the tool is intended for indexing of new terms/phrases, lexical parsing is overkill).

In order to make the auto-assist feature as useful as possible, I would like the assisted-transcription operation to choose the most frequent reading [1] of any individual character as the preferred default in an effort to reduce the amount of time users will spend correcting the inevitable [2] mistakes.

Python's pinyin package, based on Mandarin.dat, seems to provide reasonably good performance in that regard; but I'm curious whether there's a standard (issued by a language authority in PRC or Taiwan) list of such frequencies available, and/or whether any list exists that includes the other possible readings, in decreasing order of frequency, by way of providing a helpful dropdown list of alternates in cases where the preferred reading doesn't happen to be correct.

[1] i.e., assuming a large and representative set of textual data, if a character has multiple possible readings, the pronunciation most often assigned the character based on more advanced lexical analysis of the function of the character within a larger semantic block. For example, if within the set there are three observed instances of 为[wei4]什么 and one observed instance of 作为[wei2], choose "wei4" as the default transcription option for 为.

[2] I'm aware of characters such as 调 for which alternate readings (in this case diao4/tiao2) are equally likely, so in these cases such "assistance" will likely never have an accuracy rate better than 50%.

  • 1
    Alternatively, you could use CEDICT's data to look up words and provide pinyin for the words found in that data. – dda Dec 25 '16 at 4:32
  • A similar question has been answered by LeoLiu. – SLS Apr 5 '17 at 4:00
  • we can only collect enough pronunciations of words other than characters, when a character is used in a word, its pronunciation is fixed. – Daniel Yeung Aug 11 '17 at 1:58
1

Hope these would help.

0

Your idea is great, but I didn't find any authoritative material list the frequency about multiple pronunciations. Maybe because multiple pronunciations use in oral Chinese, and Chinese people learn oral Chinese before writing. So Chinese people seldom think about the frequency of multiple pronunciations. Multiple pronunciations are habits for Chinese people.But for Chinese learner, it is a little difficult to tell. I think your work is very meaningful.

0

Although I'm not able to find authoritative references for pronunciation for every characters, I do find a dictionary website where you can put in the pinyin, and it will show you all the characters with that pinyin with 5 different tones. http://xh.5156edu.com/html2/c15.html And here is all the pinyin:

b ba bo bai bei bao ban ben bang beng bi bie biao bian bin bing p pa po pai pao pou pan pen pang peng pi pie piao pian pin ping m ma mo me mai mao mou man men mang meng mi mie miao miu mian min ming f fa fo fei fou fan fen fang feng d da de dai dei dao dou dan dang deng di die diao diu dian ding t ta te tai tao tou tan tang teng ti tie tiao tian ting n na nai nei nao no nen nang neng ni nie niao niu nian nin niang ning l la le lai lei lao lou lan lang leng li lia lie liao liu lian lin liang ling g ga ge gai gei gao gou gan gen gang geng k ka ke kai kou kan ken kang keng h ha he hai hei hao hou hen hang heng j ji jia jie jiao jiu jian jin jiang jing q qi qia qie qiao qiu qian qin qiang qing x xi xia xie xiao xiu xian xin xiang xing zh zha zhe zhi zhai zhao zhou zhan zhen zhang zheng ch cha che chi chai chou chan chen chang cheng sh sha she shi shai shao shou shan shen shang sheng r re ri rao rou ran ren rang reng z za ze zi zai zao zou zang zeng c ca ce ci cai cao cou can cen cang ceng s sa se si sai sao sou san sen sang seng y ya yao you yan yang yu ye yue yuan yi yin yun ying w wa wo wai wei wan wen wang weng wu

0

Your idea is great. However, it's nearly impossible in my opinion.

Since the pronunciation of Chinese characters mostly depends on the what's the word (consisted of two or more characters) means in a whole sentence.

For example:

“你们以四行队列步行到银行,我看是不行,而且也不内行。”

There are 5行 in above sentence, 2 pronounce xíng, 3 pronounce háng.

So it comes to a dilemma, you need to collect what all people say and do statistics, which is impossible and "might harmful to freedom of speech".

  • Append another sample "你们一行人” (xing2). – Daniel Yeung Aug 11 '17 at 1:49

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.