{"id":58745,"date":"2023-05-21T05:32:21","date_gmt":"2023-05-21T10:32:21","guid":{"rendered":"https:\/\/languagelog.ldc.upenn.edu\/nll\/?p=58745"},"modified":"2023-05-21T05:41:06","modified_gmt":"2023-05-21T10:41:06","slug":"chatgpt-does-cuneiform-studies","status":"publish","type":"post","link":"https:\/\/languagelog.ldc.upenn.edu\/nll\/?p=58745","title":{"rendered":"ChatGPT does cuneiform studies"},"content":{"rendered":"

We have seen ChatGPT tell stories (and variants of the stories it tells), fancify Coleridge's famous poem on Xanadu, pose a serious challenge to the Great Firewall of China, mimic VHM, write Haiku, and perform all manner of amazing feats.\u00a0 In a forthcoming post, we will witness its efforts to translate Chinese poetry.\u00a0 Today, we will watch ChatGPT make a credible foray into Akkadiology.<\/p>\r\n

Translating old clay tablet by using chatGPT<\/a><\/p>\r\n

Jan Romme, Jan's Stuff (5\/15\/23)<\/p>\r\n

The author commences:<\/p>\r\n

You might have heard how I asked chatGPT to pose as a Jehovah\u2019s Witness, write a \u201cwitnessing letter\u201d with 2 or 3 bible scriptures in it, and then translate that letter into an English rap song, Eminem style.\u00a0\u00a0Or you might have missed that news. My point is, I like to play with AI\u2019s.<\/p>\r\n

I\u2019m increasingly stupefied by how much AI models like\u00a0OpenAI\u2019s chatGPT<\/a>,\u00a0Google\u2019s BARD<\/a>, and\u00a0Facebooks LLaMMa<\/a>\u00a0and others are capable of.<\/p>\r\n

<\/p>\r\n

Romme tells how in 2008 he saw a clay tablet at the British Museum \u201cBabylon: Myth and Reality\u201d exhibition<\/a>.\u00a0 At the time, he failed to take a photograph because, as he says, a Karen prevented him from doing so.\u00a0 He was also flummoxed by her intervention from even taking down basic notes about the tablet.\u00a0 Later, upon recollecting that the tablet pertained to the Biblical account of\u00a0King Manasseh of Judah (716\u2013662 B.C.E.)<\/a>, he felt compelled to track it down.<\/p>\r\n

The Bible, in the second book of\u00a0Chronicles 33:10, 11<\/strong>\u00a0tells us:<\/p>\r\n

10 Jehovah kept speaking to Manasseh and his people, but they paid no attention.\u00a0<\/em><\/p>\r\n

11 So Jehovah brought against them the army chiefs of the king of Assyria, and they captured Manasseh with hooks and bound him with two copper fetters and took him to Babylon.\u00a0<\/em><\/p>\r\n

At the time, the city of Babylon was under the control of Assyria. The clay tablet that I mentioned above is only making a\u00a0reference to Manasseh.<\/p>\r\n

The tablet was written, or more likely, dictated, by an Assyrian prince who happens to be in jail with Manasseh in an adjacent cell.\u00a0\u00a0And this prince is complaining, because he is still in prison while this\u00a0rebellious<\/em>\u00a0has-been king that was in the cell next to his, has now been released from prison and on his way back to his country, back to king-ing again!<\/p>\r\n

Why is this tablet so fascinating?<\/p>\r\n

Second Chronicles chapter 33 continues:<\/p>\r\n

12 In his distress, he begged Jehovah his God for favor and kept humbling himself greatly before the God of his forefathers.<\/p>\r\n

13 He kept praying to Him, and He was moved by his entreaty and heard his request for favor, and\u00a0He restored him to Jerusalem to his kingship<\/u><\/strong>. Then Manasseh came to know that Jehovah is the true God.<\/p>\r\n

So King Manasseh does a remarkable thing while in prison! He feels genuinely sorry for his sins and repents. He keeps praying to his God, till he is restored as king in Judah.<\/p>\r\n

Assyrians were never that lenient. Never. But this time, they were. And there is evidence in that clay tablet.<\/p>\r\n

That is why Romme felt obliged to find that tablet, prompting him to call upon ChatGPT for assistance.<\/p>\r\n

There are multiple archives and search engines that make an effort in indexing all known cuneiform clay tablets from long-gone civilizations like Mitanni, Assyria, Babylonia, Elam and so forth.<\/p>\r\n

Romme tried his luck with the\u00a0Cuneiform Digital Library Initiative<\/a> (CDLI), but hit a brick wall because he got 0 hits.\u00a0 Apparently, although many tablets have been digitized, there is either no digital translation of the tablet Romme was after, or it might be copyrighted and thus not on an open platform like the one he was searching.<\/p>\r\n

So he realized the need to find the Akkadian cuneiform spelling for \u201cManasseh\u201d in order to search on the data base he was using.<\/p>\r\n

He writes, \"I try to guide chatGPT into the right state of mind, by starting easy.\"<\/p>\r\n

From here on, for most of the rest of the post, Romme provides screen shots of his dialog with ChatGPT,\u00a0 with him asking leading questions, such as \"Do you have access to catalogues of ancient clay tablets from Babylonia, Assyria and Mitanni?\" and ChatGPT providing informed and detailed, but honest and straightforward responses.\u00a0<\/p>\r\n

No breakthroughs right off the bat, but things get a bit more exciting when Romme asks:\u00a0 \"Can you speculate on how the biblical name of king Manasseh of Judah would have been written in Babylonian Cuneiform?\"<\/p>\r\n

Here ChatGPT begins to display its erudition, including command of certain materials in cuneiform.\u00a0 It comes up with various relevant proposals and variant spellings.\u00a0 ChatGPT's reasoning in all of this is quite sophisticated.<\/p>\r\n

Romme attempts to take into account the difference between Sumerian and Akkadian, and proceeds to interrogate ChatGPT:\u00a0 \"Can you tell me the meaning of the akkadian word Lugal ?<\/p>\r\n

This leads to a serious discussion of kingship in Mesopotamian societies, but doesn't help solve the problem of the identity (spelling) of king Manasseh of Judah on the elusive clay tablet, because, as Romme admits when someone pointed it out to him, \"Lugal\" is a Sumerian word, not Akkadian.<\/p>\r\n

At least, though, with the help of ChatGPT, he now has three variant spellings of the king's name:<\/p>\r\n

    \r\n
  1. me-na-si-i\u00a0\u00a0<\/li>\r\n
  2. ma-na-si-i<\/li>\r\n
  3. ma-an-si-i<\/li>\r\n<\/ol>\r\n

    By using these spellings, Romme gets a lot of hits when he submits them to CDLI.\u00a0\u00a0<\/p>\r\n

    Romme presents the first one, nine lines of romanized Akkadian, to chatGPT, and asks the bot whether it can translate the text into English.<\/p>\r\n

    ChatGPT replies:\u00a0 \"Certainly!\u00a0 Here is the translation of the provided text\", and rattles it off in respectable English, then apologizes:\u00a0 \"Please note that this translation is based on my understanding of the Akkadian language and grammar.\u00a0 Variations in transliteration, content, and interpretation may exist\" — prompting Romme to exclaim:<\/p>\r\n

    Holy Moly!<\/p>\r\n

    It can translate not just words but whole Akkadian texts as well?!?<\/p>\r\n

    Too bad this is not the King Manasseh of Judah, but instead \"Menas\u00ee of Assur\".<\/p>\r\n

    I don\u2019t have time now to go through all these clay tablets and translate them with chatGPT, but I\u2019m dreaming of a plugin that automatically translates and publishes the translation of ancient cuneiform clay tablets.<\/p>\r\n

    These draft translations can then be proofread by actual translators who are knowledgable in Akkadian, Sumerian, Elamite and all the other long-dead languages that once wrote in cuneiform. Imagine a chatGPT version 5 or 6 that has been trained on these refined and checked translations. One day, we could potentially outsource most if not all translating to machines and we, humans, could do the much more fun work of reading and commenting on these long silent texts.<\/p>\r\n

    Keep dreaming kids, and keep building.<\/p>\r\n

    PS: After reading some comments on my beloved HN<\/a>, I changed the text around \"Lugal\" a bit and added the next to last paragraph. In no way do I believe chatGPT can today translate Akkadian (or other texts with small training sets) correctly, but I hope that in a future day, it will be.\u00a0<\/p>\r\n

    What I see happening is that ChatGPT can already do much of the grunt work and draft translations, lessening the burden on human experts.\u00a0 Furthermore, if it can do this passably well for esoteric languages like Akkadian, Sumerian, and Elamite, and somewhat profitably for mind-numbingly difficult languages like Literary Sinitic \/ Classical Chinese (I have some test cases from Jing Hu and David Cowhig), it is not surprising that it produces close to perfect translations of Modern Standard Mandarin (if I find time I'll give some examples in the coming weeks) and other contemporary languages with large, well-documented data bases.<\/p>\r\n

    We are only beginning to feel the potential impact of ChatGPT and similar tools.\u00a0 I, for one, welcome their awesome power, but caution that we must keep an eye on them, lest they go astray and make mischief that will be hard to correct later on.<\/p>\r\n

     <\/p>\r\n

    Selected articles<\/strong><\/p>\r\n