[HN Gopher] Show HN: Kimchi Reader - Immersive Korean Learning w...
___________________________________________________________________
Show HN: Kimchi Reader - Immersive Korean Learning with a Popup
Dictionary
Actually, it is yet another tool to learn a language through
immersion (classic set of features, watch on youtube/netflix, read
a website or book). It has a popup dictionary so you can click on a
word and it will show the definition. Nothing new in that regard,
except that it has been made with only Korean in mind and does not
plan to extends to other languages. I was learning and still am
learning Korean (now using my own tool to learn!). I initially made
the tool for myself because none of the tools out there could
correctly figure out what a word was in the text. And that's where
the biggest challenge was: recognizing the lemma. A lemma is the
dictionary form of a word. An example in English would be "break,
breaks, broke, broken and breaking" all becoming "break". In Korean
a word cannot always accurately be returned to the lemma; this
might lead to several possibilities. Then the reader, with the
context can understand which one ends up being the correct one.
Zero IA was used, pure rules based bruteforcing. I do perhaps
intend later to use AI, but as a layer on top. I wanted to make
sure I can parse massive amounts with cheap computation first. This
open me doors to more crazy ideas for later. You can see a live
example on the landing page. Any feedback is appreciated!
Author : alaanor
Score : 68 points
Date : 2023-10-29 15:21 UTC (7 hours ago)
(HTM) web link (kimchi-reader.app)
(TXT) w3m dump (kimchi-reader.app)
| esbeesbeesbe wrote:
| Nice work! This looks like a very helpful app, and I like the
| visual design.
|
| I tried authenticating with Google to try it out on mobile, but I
| got a 500 when redirected back to the site. I'll be sure to check
| back later though to try again :)
| alaanor wrote:
| Hey thanks for the awesome comment! I just made a new account
| using google oauth with a spare email I had, and seems like it
| is working perfectly fine. Five other people have managed to
| create an account using google as well since the post. I would
| love to know what went wrong but I'm unsure how to help there.
| Maybe try again ? In any case sorry for the inconvenience.
| bobthepanda wrote:
| Is there a colorblind mode? Red green is the most common form of
| colorblindness.
| alaanor wrote:
| Ah! Mistake on my end indeed, sorry. I do have settings in the
| application where people can redefine the colors such as the
| background or text color. But I haven't done for the colors
| (red, green, yellow, orange, etc) itself. I am adding that to
| my task list now.
| ok123456 wrote:
| Want to try it, but don't want to make an account.
| kebsup wrote:
| Nice, I've been building something very similar for German
| (Vokabeln.io). The biggest problem there was recognizing
| "trennbare Verben", and words have a lot of conjunctions as well.
| rickcarlino wrote:
| Very excited to see more Korean centric language learning apps.
| Also glad to see that you support Fire Fox already. So many apps
| say that fire fox support is "coming soon"
| ydnaclementine wrote:
| Just want to echo again thank you for Korean learning stuff.
| We're not as big as Japanese learners, but we're slowly growing
| in size
| AYBABTME wrote:
| Looks amazing, I'll try it out. This will save me a bunch of time
| copy-pasting words in Papago and trying to lookup the grammar's
| meaning on random websites.
| godelski wrote:
| This looks fantastic. As someone in a serious relationship with a
| Korean person, this is something I could actually see myself
| paying for too.
|
| But, I would like to see some more about what it offers. Right
| now it looks like it is a video caption replacer with a
| dictionary. There are free tools like that that exist. Anki is a
| plugin and not built in, why? What about those starting learning?
| Do you have lessons or small references?
|
| What's your plan for ML? Honestly, the largest benefit I see is
| for pronunciation feedback. This is a thing a lot of apps get
| wrong, because it is important to learn how to pronounce things
| from the beginning. This usually isn't as big of a problem for
| someone learning English but tones are a bit more important in
| Korean though not as much as say Chinese (this is part of why
| it's typically easier to understand someone in English with a
| very heavy accent than understanding Chinese with a very heavy
| accent). But a self learner is going to have an incredibly
| difficult time getting verbal feedback while a native or more
| traditional learner has this feature built in because there's
| another person there to give them feedback.
| alaanor wrote:
| Hey thanks for the comment! I have read your entire feedback
| and love it.
|
| Yes there are free tools that does the same job (I have noted
| that on the description of the post). The main difference is
| that Kimchi is capable of recognizing words correctly (ofc not
| 100%, but better than other tools. If you think there are
| better tools out there, I would love to see it!).
|
| As for Anki, I don't want to rebuild a whole SRS on my side if
| that what you were thinking. I think Anki is an awesome
| software and does its job extremely well. So using it instead
| of recreating the wheel sound much more interesting.
|
| For the content, I don't have anything right now indeed. I
| would love to build a customized content recommendation later
| matching with the knowledge you marked in Kimchi. But I don't
| plan producing material myself and I don't think I have level
| to do so anyway.
|
| And finally for ML. I think I should use it where it make the
| most sense. I definitively want to use it! But I also don't
| want to use for the sake of using it. I wanted the foundation
| to be without, then ML can always be slapped on top of it. As
| you said, there's plenty of scenario where I could use it, be
| pronunciation, ocr for webtoon, translation with context for
| when you understand each word and grammar but still don't get
| the sentence, whisper, tts for making audiobook on the fly,
| etc.
| godelski wrote:
| I was just thinking including Anki as part of it. Ship with
| it. That's all. Not rebuild.
|
| I'd probably focus less on the content recommendation. But
| I'm not seeing the big utility as specifically a language
| learning app. Unless it is purely about language learning
| content, not just youtube and netflix videos.
|
| For ML, as an ML person I'm glad to hear you say this. I hate
| when it's hamfisted into bullshit things. The ideas you have
| seem good though but most are probably handled better by
| other products which you could integrate. But I am not aware
| of a good product that helps with pronunciation (at least to
| any passable degree), though I am aware of ones that do this
| for singing. I'd see this as a killer feature but it'll cost
| you some compute to get there.
| dan_quixote wrote:
| I'm in a similar situation - my girlfriend is Korean and speaks
| perfect English but some of her friends and family do not (and
| are rather self-conscious about it). I'd like to meet them
| halfway by getting to a basic conversational level in Korean.
| Any tips? What has worked well for you so far? I've been
| working with Duolingo for a few months with mixed results. I
| just started Anki with the Korean Vocab by Evita deck [1] and
| it has been really great for vocab at least. I'll be checking
| this post out later as well.
|
| [1] https://ankiweb.net/shared/info/4066961604
| godelski wrote:
| Ooofff fuck, no I __need__ tips lol. Though I'm short of time
| right now (PhD + a job) so language learning has been on the
| back burner. I never found Duolingo helpful except in
| learning characters but Anki being better. But I have no
| better tips than that. I tried learning Chinese a few years
| back and found a language book and getting an iTalki tutor
| were infinitely better than any apps or any self study. I
| don't think you can do it without some tutor (even your gf).
| csa wrote:
| > I'd like to meet them halfway by getting to a basic
| conversational level in Korean. Any tips?
|
| Not op, but...
|
| Start with memorized words and phrases -- salutations, meal
| time commentary, celebration terms, etc.
|
| Then move to short, simple sentences -- emphasis on short
| _and_ simple. You might not understand any replies, but
| that's ok.
|
| Over time, these might progress into short and simple
| _conversations_ as you become better able to understand their
| responses (and they probably learn how to simplify for you),
| and your vocabulary grows.
|
| Once you get this far, you will have more specific questions
| to ask regarding gaps you want to address.
|
| Korean is one of the harder languages for native speakers of
| English to learn, so don't expect a quick ramp up time like
| you might have with Spanish or French.
|
| One of the challenges with Korean is the S-O-V order. This is
| like Japanese, so Korean is quite a bit easier to learn if
| you already know Japanese.
| og_kalu wrote:
| I've been learning korean for a while now. I'll give my 2
| cents.
|
| It's not just a dictionary but a grammar parser, see also
| mirinae (https://mirinae.io/), _the_ grammar parsing tool for
| Korean. Korean and English are so distant that a good
| grammatical parsing is infinitely more helpful than a
| dictionary alone.
|
| There actually isn't any other option, free or otherwise that
| combines all this "easy reading and watching" tools with a good
| parser.
|
| Mirinae is in a league of its own but it's a standalone parser
| and no longer lets you view grammar explanations for free.
|
| 2. another big thing here is convenience. I'm not exaggerating
| when i say you can cut studying time in half having everything
| in one place.
| simonebrunozzi wrote:
| Suggestion: let people try it without signing up.
| jaflo wrote:
| I agree, I created an account and tried clicking on "Study" and
| it didn't work. Aside from the demo on the main page there
| wasn't any way to see how well it works.
| alaanor wrote:
| If you're talking about menu being grayed, it's because you
| did not start the trial. I wanted to make the trial to start
| immediately after creating an account, but stripe force the
| trial to be attached to a price. So I'm forced to let the
| user make the price choice (without paying) even for a trial
| which I absolutely hate and would be love to have a better
| flow. I want and will find a solution to that.
|
| If you're talking about content to try directly after making
| an account, you're right. There's none for now. Something
| definitively can be improved there. Noted.
| alaanor wrote:
| Noted! Thanks for the suggestion, that's a good idea.
| handsdown92 wrote:
| I would pay so much money for a Chinese and Japanese version of
| this, absolutely amazing. I've had this idea for ages, so glad
| someone else built it!
| jwells89 wrote:
| For Japanese, the browser extensions Yomichan[0] (Chrome-clones
| and Firefox) and 10ten[1] (Safari macOS/iOS, Chrome-clones,
| Firefox) function similarly. There's also several community-
| built tools that are made to work with these extensions like
| mokuro[2] and subadub[3].
|
| [0]: https://foosoft.net/projects/yomichan/ [1]:
| https://chrome.google.com/webstore/detail/10ten-japanese-
| rea..., https://apps.apple.com/us/app/10ten-japanese-
| reader/id157354..., https://addons.mozilla.org/en-
| US/firefox/addon/10ten-ja-read... [2]: https://github.com/kha-
| white/mokuro [3]: https://chrome.google.com/webstore/detail/sub
| adub/jamiekdimm..., https://addons.mozilla.org/en-
| US/firefox/addon/subadub/
| lawn wrote:
| It looks great!
|
| What I would dream about is the ability to read Manwha with it.
| That's probably a bit hard as the text is inside images, but
| maybe with some image recognition it might be possible...?
| alaanor wrote:
| I absolutely want that I well! I took the fastai course and
| made some attempt at building my own custom OCR. I got some
| result but not good enough for production (after all I'm
| totally new to the domain lol). I still believe it is possible,
| but time wise, I had to go work on other tasks first. Ideally I
| want something that works client side, should run on mobile
| (think wasm onnx or something like that) and is specialized for
| webtoon. I don't know if I'm dreaming too big or not but I want
| to give a second try in the future.
| solidsnack9000 wrote:
| For the first year or so, pretty much everyone who's learning is
| going to need the romanization alongside / above the Hangul. It's
| probably always going to be true that more than 2/3 of your
| potential customers -- 2/3 of the people who come to the website
| looking to see if this is for them -- will be in this category.
|
| There is a kind of anti-pattern in tools of this kind where the
| people building them already know some of the basics and so leave
| them out. It shows up in tools for Japanese, Chinese, Hebrew...
| I've studied quite a few languages and so have been the beginner
| over and over.
| voussoir wrote:
| I absolutely disagree. Romanized Korean is harder to read than
| Korean itself. The sounds implied by the roman spelling do not
| match the sounds you're supposed to make, and you lose the
| syllable boundaries that aid in pronunciation. I feel like a
| caveman stumbling over my letters when I try to read a
| romanized word.
|
| A one-page alphabet reference chart would be enough to remind
| the reader which letter is which without relying on the
| romanization crutch.
|
| Normally I don't like to make argumentative internet comments
| but I really passionately think romanization is a detriment to
| a learning tool.
| dumbhndown wrote:
| We don't need to be this divisiveabout this. There is no
| right way as to how people learn
|
| As someone that knows and can read Hindi, Gujarat, Cyrillic,
| Greek, Arabic and beginner at Hangul and Hiragana,
| romanization absolutely helps anchor the sound. The actual
| sound when speaking is going to change anyways as your
| converse with more people. But at least, romanization helps
| recall and focus on the actual word that you are learning.
| csa wrote:
| > For the first year or so, pretty much everyone who's learning
| is going to need the romanization alongside / above the Hangul.
|
| For folks who are _learning_ Korean, hangul is maybe two days
| to get the basics and maybe a week or less to be able to get
| comfortable with it.
|
| For super-casuals who just want a ballpark representation, you
| might be right, but I don't think it's reasonable to design
| around these super-casual folks -- when they decide to get
| serious about learning Korean, Hangul will come quickly.
|
| Hangul, as a phonetic representation, has about the same
| difficulty as learning hiragana, which takes about the same
| amount of time to learn.
|
| Maybe if you are referring to older Korean texts that had
| Chinese characters in them, then I could understand.
|
| > ... It shows up in tools for Japanese, Chinese, Hebrew
|
| Kanji (not a syllabary or alphabet), hanzi (not a syllabary or
| alphabet), and no vowels respectively.
|
| These languages need some romanization support much more than
| Hangul, imho.
| solidsnack9000 wrote:
| Potential customers for an app like this don't neatly segment
| into "...folks who are learning Korean..." and "...super-
| casuals who just want a ballpark representation...". There is
| a continuum, and the continuum is weighted towards the casual
| side. Honestly, if most people only learn a little Korean
| from this app and it broadens their world only a little bit,
| it's still done tremendous good. Most people are not going to
| learn Korean, Japanese, Chinese, &c, &c.
|
| I don't think you'll be able to find empirical support for
| the idea that romanization is unhelpful after the first week
| of someone's taking up Hangul in a serious way; or for the
| idea that Hangul is as simple as Hiragana.
|
| Many people say things like this -- "two days to get the
| basics" and "a week or less to be...comfortable" -- but I
| doubt there is any empirical support for figures like that. I
| suspect that a review of the literature will show that people
| are still referring back to the romanization for the first
| two years of their studies, across a wide array of language
| families, if their first language uses the Roman alphabet.
|
| Hebrew has vowel marks. They are little used but they are
| very helpful, as well.
___________________________________________________________________
(page generated 2023-10-29 23:00 UTC)