While more languages are great, compared to translation by the better LLMs Google Translate leaves much to be desired. Accurate and appropriate translation requires sensitivity to the context and purpose of the translation. While it is possible to get better translations from ChatGPT, Claude, etc. by prompting them with information about the text and requests for how it should be translated, Google Translate takes a one-size-fits-all approach, where a text can be translated in only one way.
Even when not explicitly prompted, the LLMs will adapt the translations based on the context. A simple example: Japanese uses different words to describe older and younger siblings. An older sister is ane, and a younger sister is imōto (also written imouto). When asked to translate “I was born in 2003, and my sister was born in 2002” into Japanese, both ChatGPT 4o and Claude 3.5 Sonnet correctly translate “sister” as ane; for “I was born in 2001, and my sister was born in 2002,” they both correctly use imōto. Google Translate, in contrast, uses imōto for both.
LLMs are also able to answer questions about the text and the translation. After Claude correctly translated “I was born in 2003, and my sister was born in 2002” into Japanese, I asked a follow-up: “Why did you translate ‘sister’ as ane?” Its response:
I appreciate you asking about that translation choice. Let me explain:
I used "姉" (ane) for "sister" because the context implies an older sister. In Japanese, there are specific terms for older and younger siblings:
1. 姉 (ane) - older sister
2. 妹 (imouto) - younger sister
Since the sentence mentions that the sister was born in 2002, which is before the speaker's birth year of 2003, it indicates that the sister is older. Therefore, I chose "姉" (ane) as the appropriate term. This distinction between older and younger siblings is an important aspect of the Japanese language and reflects the significance of age relationships in Japanese culture. If the sister had been younger, or if the age relationship wasn't clear from the context, a different translation might have been more appropriate. For example:
- For a younger sister: 妹は2002年に生まれました。(Imouto wa 2002-nen ni umaremashita.)
- For a sister of unspecified age: 私の姉妹は2002年に生まれました。(Watashi no shimai wa 2002-nen ni umaremashita.)
Would you like me to elaborate on any other aspects of the translation?
An important thing to consider is cost - Google Translate is used by hundreds of millions of people and probably has an insane amount of requests done daily, yet it's free for personal use. LLMs are much less economical.
Even when not explicitly prompted, the LLMs will adapt the translations based on the context. A simple example: Japanese uses different words to describe older and younger siblings. An older sister is ane, and a younger sister is imōto (also written imouto). When asked to translate “I was born in 2003, and my sister was born in 2002” into Japanese, both ChatGPT 4o and Claude 3.5 Sonnet correctly translate “sister” as ane; for “I was born in 2001, and my sister was born in 2002,” they both correctly use imōto. Google Translate, in contrast, uses imōto for both.
LLMs are also able to answer questions about the text and the translation. After Claude correctly translated “I was born in 2003, and my sister was born in 2002” into Japanese, I asked a follow-up: “Why did you translate ‘sister’ as ane?” Its response: