Show HN: Kimchi Reader – Immersive Korean Learning with a Popup Dictionary

[alaanor]

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!

[godelski]

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.

[famouswaffles]

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 and/or translator 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 great and better than the tool used here but is standalone and no longer lets you view grammar explanations for free.

GPT-4 also gives good parsings but it's even more cumbersome to use individually at scale (copy/paste, ask etc)

2. another big thing here is convenience. I'm not exaggerating when i say you can cut studying time in half at least having everything in one place.

[alaanor]

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.

[dan_quixote]

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

[solidsnack9000]

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]

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.

[csa]

> 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.

[harrymit907]

I personally think leaving romanization after the first week of learning Hangul is best, unless you are focusing only on getting better at speaking.

[_dmn7]

For those learning other languages (works best for European languages), my open source tool VocabSieve [1] does something quite similar (it is a lemmatizing tool unlike many common tools such as LingQ), with more advanced features like auto-mining words and using highlights from ereaders. It's also a local-first tool that does not require internet access if you use downloaded resources and does not connect to any central server I control. It has no mobile support though.

[1] https://github.com/FreeLanguageTools/vocabsieve

[kebsup]

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.

[lawn]

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]

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.

[AYBABTME]

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.

[famouswaffles]

This is a tool you might like

https://mirinae.io/

[handsdown92]

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]

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/subadub/jamiekdimm..., https://addons.mozilla.org/en-US/firefox/addon/subadub/

[mortallywounded]

First and foremost, congrats on shipping!

I am completely self taught.

My wife is Korean and I am not. We lived in Korea for 5+ years (but in the USA now). We have two children that speak English and Korean. My Korean comprehension is quite good. We are close to the Korean side of our family and we're surrounded by Korean all the time (even in the USA).

All of that is to give some context for how I learned Korean and what has worked (and didn't work) for me.

What has worked wonderfully:

1. Learn Hangul (Korean alphabet) immediately. You simply cannot learn or study Korean with romanization of any kind.

2. Deliberate textbook study with an emphasis on grammar (for example, Korean Grammar in Use by Darakwon).

3. Learning vocabulary in context of the grammar from #2. For example, take a noun/verb out of a new grammar structure and replace with new ones. Always study in the context of grammar and structure.

4. Listening comprehension through transcription. Given some Korean audio, listen and transcribe what is said in Korean. This certainly helps train your ear to pick up native Korean. Korean you hear from textbook audio is very easy and doesn't help in real life.

What did not work for me:

1. Using Anki to cram words in my head. Sure-- everyone can grab a 2k or 6k deck of words and memorize them, but you won't know how or when to use anything. You also won't be able to recall much of it.

2. Watching drama or reading webtoons. It's tempting to call this "studying" but it's really low bandwidth. What you get out of it is in no way at all related to the amount of time it takes. You'd be better off with 10 minutes and a textbook than a 50 minute drama that takes you 600 minutes to get through looking up words and grammar.

3. The cult/following of "total immersion/no output" which was born out of the Ajatt method of learning Japanese. It's baloney. Sorry if this includes your tool :)

[pthacker]

The integration with YouTube and Netflix is brilliant!

Some feedback: - The hero image is a bit vague, not sure what the product is, however, scrolling down a bit I see a great image of a K-Drama playing with the app in action, which was really impressive and informative - The tool tip background is transparent so hard to read the text in it as it gets mixed with the background

[rickcarlino]

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]

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

[ammmir]

thanks for making this. i've spent 5 minutes on this, but haven't been able to get it to work yet, the extension popup's Parse and Extract buttons are grayed out. do i need a sub to try it out?

a few general remarks:

the landing page above-the-fold is just ugly, the color gradient is horrendous, and the top screenshot of a video is... blank. at first i tried to click the play button, but nothing happened. then i realized it's more of an abstract illustration of what you app does. makes sense, but a real video or animation would be even straight to the point. please, wow me!

what is mining? at first, i thought you've created a cryptocurrency. i see it's explained later down the page.

after login, the grammar page doesn't respect the light mode theme. more examples for grammar would be helpful. in fact, what i want is, extract relevant grammar from the CC of YouTube videos in Korean, and then link me to the EXACT TIMESTAMP, so i can hear it in actual use. i would pay for this.

[alaanor]

Hey thanks for the awesome comment! Yeah you do need a sub (a free trial to be manually activated, big mistake on my end there, I should have made that flow better, lesson learned with this post.)

I get the frustration with the landing page and I think you are right. I was not exactly perfectly happy with this above the fold section either. I just made what I could do the best for now. 100% this will be changed in the future once I can get a full fledged trailer.

As for the remaining points, they're are all good points, all noted. Thanks again for the feedback.

[simonebrunozzi]

Suggestion: let people try it without signing up.

[jaflo]

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]

Noted! Thanks for the suggestion, that's a good idea.

[hiatus]

Does anyone know of applications like this for other languages, particularly Russian and Greek?

[_dmn7]

My somewhat similar project VocabSieve [1] is intended to make lookups and making Anki flashcards very easy. Among other things, you can import highlighted words from ereaders and make Anki cards out of them automatically. I used it for Russian for the entire development process, so you can be sure it works well for that.

[1] https://github.com/FreeLanguageTools/vocabsieve

[esbeesbeesbe]

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]

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.

[neom]

I signed up and it immediately tells me my subscription is expired, but if I click into subscription it says trial till nov 6th. Signed in and out couple times, same.

[purpleflame1257]

I think it looks pretty good. One thing that would be good is a selectable romanization option (partial to MR myself).

[bobthepanda]

Is there a colorblind mode? Red green is the most common form of colorblindness.

[alaanor]

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]

Want to try it, but don't want to make an account.