Picard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language

4 months ago by cm0002 to c/star_trek

Tamarian, a fictional language introduced in the Star Trek episode Darmok, communicates meaning through utterances of metaphorical references, such as "Darmok and Jalad at Tanagra" instead of "We should work together." This work assembles a Tamarian-English dictionary of utterances from the original episode and several follow-on novels, and uses this to construct a parallel corpus of 456 English-Tamarian utterances. A machine translation system based on a large language model (T5) is trained using this parallel corpus, and is shown to produce an accuracy of 76% when translating from English to Tamarian on known utterances.

This work assembles a Tamarian- English dictionary of utterances from the original episode and several follow-on novels, and uses this to construct a parallel corpus of 456 English-Tamarian utterances.

For more serious writing on the Tamarian language subject, see this and chapter 5 of this.

star_trek

@lemmy.zip

Welcome to a Star Trek community where you’re free to chat and share your opinions about all things Trek!

I want to have a place where fans can come to praise, discuss, and even criticise things in the Star Trek franchise. No show or movie is perfect, and I don't believe people should be silenced for having a dissenting opinion. That being said, there are still a few rules.

Be Nice - No personal attacks. You can disagree with someone's opinion, but it needs to stop there.

No Slurs - This is applicable to ethnicity, religion, gender, or anything else.

No Adult Content - Keep it family friendly.

No Spamming or Trolling - Consistently spamming comments or trolling is just not needed.

Keep Topics Trek Related - This is a Star Trek community, so of course discussion should stay in that area! That means no real world politics.

go to feed...