The incorrect parsing is a known issue already for Japanese and Chinese. (not sure about other languages)
Is this being worked on?
Love using Language Reactor for my Japanese Immersion but without proper parsing, it is heavily handicapped and I have to use other tools to actually learn the language.
Chrome extensions like Rikaikun or Yomichan do it properly, so I have to rely on those sadly for that task.
In the meantime maybe a function to save custom words would be good, where we the users can select what the actual words are so that it makes sense when we save the sentences.
This is a big issue that I noticed immediatly when I tried to use Phrase Pump for Japanese. For example, it can’t recognize whether an individual kana is a part of the word, part of the conjuation of a verb or whether it’s just a word by itself.
I hope this will be fixed in the near future, otherwise I cant’t really recommend using this service for japanese. It would just confuse beginners, imo.
Have there been any updates to this issue? The parser seems to generally try to split things into 2 character phrases if possible (e.g. 2 + 2 when the semantically correct split is 1 + 3).
I wanted to follow up on the parsing issue discussed previously regarding Phrase Pump, particularly regarding Japanese language parsing. As we’ve identified, the parser tends to split phrases into two-character combinations rather than recognizing the correct semantic splits, leading to challenges in comprehension, especially for beginners.
Given that this issue has been acknowledged, I’m curious about the progress towards resolving it. Have there been any updates or developments in this area? I believe addressing this parsing issue would significantly enhance the user experience for Japanese learners and make Phrase Pump an even more valuable tool for language learning.