#Corpus of Electronic Texts

[stairnaheireann]

Ancient Irish Law

‘Irish law is the oldest, most original, and most extensive of mediaeval European legal systems. It is a unique legal inheritance, an independent indigenous system of advanced jurisprudence that was fully evolved by the eighth century. It is also far less well-known than it deserves.’ ‘Early medieval Ireland evolved a system of law (often called ’Brehon’ law, from the Old Irish word brithemain…

[ariel-seagull-wings]

@bixiebeet

"Sumerian is the first language for which we have written evidence and its literature the earliest known. The Electronic Text Corpus of Sumerian Literature (ETCSL), a project of the University of Oxford, comprises a selection of nearly 400 literary compositions recorded on sources which come from ancient Mesopotamia (modern Iraq) and date to the late third and early second millennia BCE.

The corpus contains Sumerian texts in transliteration, English prose translations and bibliographical information for each composition. The transliterations and the translations can be searched, browsed and read online using the tools of the website.

Funding for the ETCSL project came to an end in the summer of 2006 and no work is currently being done to this site or its contents.

For more information, see the About ETCSL menu or the site map.

In 2017, the Faculty of Oriental Studies IT Department carried a series of changes to the ETCSL backend, including upgrading the code to work on PHP7, the latest version of the software. Should you see any issues with the website, please contact us on the details on the General Info page."

[irish-dress-history]

Irish dress history sources online:

A list of sources for Irish dress history research that free to access on the internet:

Primary and period sources:

Text Sources:

Corpus of Electronic Texts (CELT): a database of historical texts from or about Ireland. Most have both their original text and, where applicable, an English translation. Authors include: Francisco de Cuellar, Luke Gernon, John Dymmok, Thomas Gainsford, Fynes Moryson, Edmund Spenser, Laurent Vital, Tadhg Dall Ó hUiginn

Images:

The Edwin Rae Collection: A collection of photographs of Irish carvings dating 1300-1600 taken by art historian Edwin Rae in the mid-20th c. Includes tomb effigies and other figural art.

National Library of Ireland: Has a nice collection of 18th-20th c. Irish art and photographs. Search their catalog or browse their flickr.

Irish Script on Screen: A collection of scans of medieval Irish manuscripts, including The Book of Ballymote.

The Book of Kells: Scans of the whole thing.

The Image of Irelande, with a Discoverie of Woodkarne by John Derricke published 1581. A piece of anti-Irish propaganda that should be used with caution. Illustrations. Complete text.

Secondary sources:

Irish History from Contemporary Sources (1509-1610) by Constantia Maxwell published 1923. Contains a nice collection of primary source quotes, but it sometimes modernizes the 16th c. English in ways that are detrimental to the accuracy, like changing 'cote' to 'coat'. The original text for many of them can be found on CELT, archive.org, or google books.

An Historical Essay on the Dress of the Ancient and Modern Irish By Joseph Cooper Walker published 1788. Makes admirable use of primary sources, but because of Walker's assumption that Irish dress didn't change for the entirety of the Middle Ages, it is significantly flawed in a lot of its conclusions. Mostly only useful now for historiography. I discussed the images in this book here.

Chapter 18: Dress and Personal Adornment from A Smaller Social History of Ancient Ireland by P. W. Joyce published 1906. Suffers from similar problems to An Historical Essay on the Dress of the Ancient and Modern Irish.

Consumption and Material Culture in Sixteenth-Century Ireland Susan Flavin's 2011 doctoral thesis. A valuable source on the kinds of materials that were available in 16th c Ireland.

A Descriptive Catalogue of the Antiquities in the Museum of the Royal Irish Academy Volumes 1 and 2 by William Wilde, published 1863. Obviously outdated, and some of Wilde's conclusions are wrong, because archaeologists didn't know how to date things in the 19th century, but his descriptions of the individual artifacts are worthwhile. Frustratingly, this is still the best catalog available to the public for the National Museum of Ireland Archaeology. Idk why the NMI doesn't have an online catalog, a lot museums do nowadays.

Volume I: Articles of stone, earthen, vegetable and animal materials; and of copper and bronze

Volume 2: A Descriptive Catalogue of the Antiquities of Gold in the Museum of the Royal Irish Academy

A Horsehair Woven Band from County Antrim, Ireland: Clues to the Past from a Later Bronze Age Masterwork by Elizabeth Wincott Heckett 1998

Jewellery, art and symbolism in Medieval Irish society by Mary Deevy in Art and Symbolism in Medieval Europe- Papers of the 'Medieval Europe Brugge 1997' Conference (page 77 of PDF)

Looking the part: dress and civic status and ethnicity in early-modern Ireland by Brid McGrath 2018

Irish Mantles, English Nationalism: Apparel and National Identity in Early Modern English and Irish Texts by John R Ziegler 2013

Dress and ornament in early medieval Ireland - exploring the evidence by Maureen Doyle 2014

Dress and accessories in the early Irish tale, ‘The Wooing of Becfhola’ by Niamh Whitfield 2006

A tenth century cloth from Bogstown Co. Meath by Elizabeth Wincott Heckett 2004

Tertiary Sources:

Medieval Ireland: An Encyclopedia edited by Sean Duffy published 2005

Re-Examining the Evidence: A Study of Medieval Irish Women's Dress from 750 to 900 CE by Alexandra McConnell

[sag-dab-sar]

📚Resources for The Ancient Near East📚

With a focus on religion

Please leave a comment if a link breaks I'll do my best to find a new one

Getting Started On Research

JSTOR Guide LINK

Lumenlearning Guide LINK

Center for Online Education Guide LINK

Layman's Guide to Online Research by @/sisterofiris LINK

How to Vet Sources by me LINK

Websites for ANE Study

ETCSL | The Electronic Text Corpus of Sumerian Literature — http://etcsl.orinst.ox.ac.uk/catalogue.htm

ePSD | The Electronic Pennsylvania Sumerian Dictionary — http://psd.museum.upenn.edu/epsd-frame.html

ORACC | Open Richly Annotated Cuneiform Corpus — http://oracc.museum.upenn.edu/

ORACC's Mesopotamian Gods and Goddesses Project — http://oracc.iaas.upenn.edu/amgg/abouttheproject/index.html

ETANA | Electronic Tools & Ancient Near East Archive — http://etana.org/

CDLI | Cuneiform Digital Library Initiative — https://cdli.mpiwg-berlin.mpg.de/about

CAD | The Assyrian Dictionary of the Oriental Institute of the University of Chicago — http://www.aina.org/cad.html

Livius' Babylonian Section — https://www.livius.org/category/babylonia/

Multi Source Websites

Internet Archive Library — https://archive.org/details/texts | How To Use LINK

JSTOR — https://www.jstor.org/ | How To Use LINK

Google Scholar — https://scholar.google.com/intl/en/scholar/help.html

Google Books — https://books.google.com/googlebooks/about/index.html

Academia — https://support.academia.edu/hc/en-us/categories/360003163373-Academia-Free-Features

DOAJ Index of Open Access Journals — https://www.doaj.org/

Internet Ancient History Sourcebook — https://sourcebooks.fordham.edu/ancient/asbook.asp

Met Museum Publications — https://www.metmuseum.org/met-publications

Holy Books — https://www.holybooks.com/about/

Internet Sacred Text Archive — https://sacred-texts.com/

Deepdyve is a website of academic journal articles that isn't free but it isn't outrageously expensive for what it offers if you are heavily invested in new research — https://www.deepdyve.com/

Avaliable Online Books

*When using older books be aware that there may be inaccuracies and out of date information. If at all possible cross-reference and synthesize with newer materials. I have added years for this reason.

Books Specifically on Religion

Gods Demons and Symbols of Ancient Mesopotamia by Jeremy Black and Anthony Greene (1992) Internet Archive

Ancient Near Eastern Mythology by Gwendolyn Leick (1991) Internet Archive | This & Black's dictionary are good starting off points but I always use additional source's because some of Leick's info in particular tends to be more out of date than other authors.

The Cultic Calendars of the Ancient Near East by Mark Cohen (1993) PDF

Preforming Death Social Analysis of Funerary Traditions in the Ancient Near East and Medditarian edited by Nicola Laneri (2007) PDF

Mesopotamian Ritual-prayers of “Hand-lifting”(Akkadian Šuillas) by Christopher G Frechette (2012) Internet Archive

When Gods Were Men: The Embodied God in Biblical and Near Eastern Literature by Esther Hamon (2008) Internet Archive

Books on ANE History in General

Handbook to Life in Ancient Mesopotamia by Stephen Bertman (2005) Google Books | Not avaliable online BUT highly recommended, easy read.

A History of the Ancient Near East ca. 3000- 323BC by Marc Van de Mieroop (2016) Internet Archive

Everyday Life in Ancient Mesopotamia by Jean Bottero (1992) Internet Archive

Women in the Ancient Near East by Marten Stol (2016) Open Access

Chapter 3 Elamite from The Cambridge Encyclopedia of Ancient World Languages edited by Roger Wooard (2004) PDF

Sumerian Art by Andre Parrot (1970) Digital Library

The Greek Magical Papyri in Translation, Including the Demotic Spells edited by Hans Dieter Betz (1986) PDF (If that link breaks Google Books)

List of resources on Mesopotamian Magic Link

[unapologeticmelancholy]

Found this amusing. This is an excerpt from one of the earliest recorded texts in human history: the Sumerian Instructions of Shuruppak, 2600 BC. Oh, how little we've changed!

Source: Black, J.A., Cunningham, G., Fluckiger-Hawker, E, Robson, E., and Zólyomi, G., The Electronic Text Corpus of Sumerian Literature (http://www-etcsl.orient.ox.ac.uk/), Oxford 1998- .

[vedurnan]

Hello,

Do you keep any text written 1000+ years ago close to your heart? Do you feel like the features of people who wrote text so long ago can be seen in the people around you? Thanks for your time and your blogging.

there are a lot of sumerian proverbs from the electronic text corpus that i think about very often, i encourage you to look through that website because i am sure that some of them will really leap into your heart. every time i visit it i am struck by a new one, but here are some that have stayed in my mind for months and years:

it is not yet 1000+ years since dante, but i think about dante a lot, especially the vita nova and his descriptions of love... many people have read the divine comedy but not as many have read the vita nova. it is short and it's beautiful and fascinating, i highly recommend you to read it! https://digitaldante.columbia.edu/text/library/la-vita-nuova-frisardi/

dante's life was really crazy, if you are interested in his poetry at all i really recommend reading about his life especially his insane exile thing. he's like grimes to me

there are a lot of old english poems and riddles i think about a lot too. this one is the best

sometimes i feel like the difference between the people who live now and the people who lived then is extremely small. there are times when i wonder how i can even know for sure that any of this is as old as people say it is, and what if it was all fake and written by modern people? some part of it is fake and written by modern people anyway since it is all translated into comprehensible modern english. i always end up thinking it doesn't matter either way, the vast distance of history is given meaning within my mind, and there is some small part of me that exists outside of time and was there with them too

[electrificata]

if i was funnier i would have just dropped a link to the electronic text corpus of sumerian literature and moved on but unfortunately.

[mostlydeadlanguages]

I saw your blog and I think you might be able to help with something I've been failing to get anywhere with for a while! I'd like to get a tattoo of a line from one of Enheduana's hymns to Inana, but while I've managed to find translation, transliteration and references, I don't have the research chops to find the original cuneiform, which is what I really want.

The one I'm after is translated as "To rove around, to rush, to rise up, to fall down and to ...... a companion are yours, Inana." (Line 116 of 'A hymn to Inana (Inana C)') in the Electronic Text Corpus of Sumerian Literature.

Any chance you could hook me up?

Here's what I've got.

The tricky thing here is that the "original cuneiform" is dense and written in 3D, which makes it difficult to duplicate in a tattoo if you're just operating off a photo. But you can find photos of this text on the CDLI here, if you scroll down, to give you a sense of the problem.

A simpler route is to "cuneify" the values of the cuneiform symbols, i.e. to convert them into standardized Unicode symbols. Those will be much easier to copy. This is, I think, the line you want, in syllabic cuneiform:

𒌨 𒊒 𒌨 𒌌 𒇻 𒌌 𒍣 𒄑 𒍣 𒄖 𒊒 𒄭 𒀭 𒋫 𒋛 𒋛 𒋼 𒀭 𒈹 𒍝 𒀀 𒄰

(You'll need to install a cuneiform font for it to display right.)

All that said, for something to be tattooed permanently on your body, you want to be certain it's correct—and at the end of the day, I only have expertise in Akkadian, not Sumerian. (They're completely different languages that share a cuneiform writing system.) I would highly advise checking with @sumerianlanguage or another Sumerologist before you get anything inked.

[spellbook-gayboy]

54? :D

54.

(Also I put this below the cut because it has major spoilers for the end of the comic!)

"...Is that your excuse now?" Ian asked, the look on his face caught somewhere between surprise and incredulity. "You've had almost nine years to come up with a reason for why everybody hates you, for why you're stuck as a fucking brain in a jar, and that's the best you can come up with?! Oh Rudy, you need to get out more."

The vocoder lit up with a fuzzy electronic hum, a sound that Ian had come to recognise as the closest that Robot could get to a growl. "What do you expect me to say?" He asked. The voice was staticky and the words were disjointed, like an old iPhone text-to-speech program. "'sorry'? We both know that's not going to happen, Ian. For better or worse, things are far better than before. Even you know that it worked."

Ian always found it funny that the vocoder still sounded more human than Rudy's actual voice.

He laughed. Ian laughed. It was simply too bizarre of a situation for him not to laugh. Here he was, one of the most powerful people on the planet, arguing with a brain in a jar, that had once been even more powerful, about the societal benefits of mass murder. "By the ancestors, this shit again? How many times do I need to tell you? You didn't fix anything! You could've fixed something, but no, you just papered over the cracks, covered the world in murder drones and called it a utopia.” He scoffed bitterly. “Funny thing about a utopia, Rudy, is that they usually don’t make the people in them afraid to look up!”

No reply, just the bubbling of the thick green fluid helping to keep his brain chugging along. “How is Amanda?”

“Oh, don’t play that fucking card with me!” Ian cut off, so enraged that he struck the strong plexiglass with his hand. “You don’t care about her, Rudy, you don’t. If you cared, you wouldn’t have thrown her into space for daring to question your oh-so glorious plan! That’s not love, Rudy, it’s just you, needing to fix everything, needing to control everything!”

Another hum. “All I wanted was to stop people suffering. Stop the decades of degradation and poverty and violence from going any further. If I have to be the villain in order to fix things, then I can live with that.”

“But you’re just any villain, are you? You’re Robot. The engineer. The genius. The backstabber. You could have fixed things any way you wanted, you might have been the only one that could have done it! But you didn’t, did you? You chose violence, chose to kill everyone that trusted you, and expected those of us you couldn’t kill to be fine with it, to just go ‘well he might’ve blown a hole in Black Samson, but at least the economy’s pretty good now!’. You can put yourself up on a cross, tell the public whatever lie you want, but us? The heroes that called you ‘friend’? To us, you’re just the traitor that got away with it.”

No reply again. The hum came, but nothing followed it. “How is she?”

“She’s well. They put her in charge of the new Teen Team. She’s happy, really happy. Happy, and free.” Ian stated flatly. “But we both know that’s not why I came here today.”

No words in reply. 

“You asked for an update on your health last time. I debated even doing it, but then I thought ‘what could be worse than how he is already is?’, so I pulled it from the director’s office.” Ian continued, producing a small stack of white and manila paper. “Neurologist’s reports, tweaks to the amniotic fluid, psychiatric reports, etcetera etcetera. Basically a lot of stuff I’m not legally allowed to see under HIPAA, but I get the feeling that you don’t care.”

“What do you see?”

“Not much. Everything seems normal, except...”

“Except what?”

Ian turned the papers over, stopping somewhere in the middle. “Report by Dr. Wittman, your neurologist. ‘Scans of the patient reveal damage in the subcortical basal ganglia, specifically in the corpus striatum region, consistent with the early warning signs of a potential...’.” Ian read from the page, slowing when he glimpsed the end of the sentence. “Oh. ‘a potential neurodegenerative disease. Tests will commence at the beginning of next month to determine the extent of the damage and possible avenues of treatment. Research into family medical records will also be required in order to determine a potential genetic component’.”

“...thank you, Ian. I suppose I should have seen this coming. Cloning can be such a dangerous undertaking, even when you take every precaution.”‘

“I... I’m sorry, Rudy.”

“Don’t be. It was my choice. I knew the risks.”

Ian didn’t know what to say. Nothing he could think of felt appropriate for the situation. The boiling anger was still churning in his gut, but now it mixed with a cold shock. He cleared his throat, “I should go.”

“Yes. Yes, you should.”

[aridotdash]

81-82

[emilytakesphoto]

so true

[sidleyparkhermit]

oh Electronic Text Corpus of Sumerian Literature, you didn't have to come for me like this today

[graph100]

recently i have felt like all of my tumblr posts are super repetitive, so i put a slightly edited corpus of every text post under "#graph100 originals" into a markov chain generator at length 4. here are the results (in yellow/orange color):

t up signalis, and age that are nuts. by this wont loaded favored me to keep brush in a bunch of a devlog video game" shaped hold no groove bass tab in the think that inspired of the though i dont like evidence of certain aspective, it just a regularly but the "game" not be silent hill, but i think are kinda nice seeing tbh. electronics inventor people dont usually in the year followerful dead and joke (/hj? lol)). the 2010s. there is just am hate a certain aspective, it will reading keys rounderstand the front of input from one of their childhood to world is on old ideas, but im not at school (and stop ten to classical gender blog. did nowadays (i know things that the coffee things in this world really love a game" not because im super picky with the driver concrete. i loves him. its all of the grate jaja (actual procrate jaja (actually adjust am hatever. gender is not very popular ching the sky (the windonesian intering so samey. not even etymologicalled its not hate a certain aspective,

uff, hes just like. typing stupid start is the grateful dead that we playing because the hard cause sociated it.. this withology is not, its college in othes me. i love it just tired out with yours. i love you could a daylight be tamarind jhange step closeted talking and the essay about a river. i could be good as if those stupid not because of "androgyny" (or a video they all my wisdom. for the past, and making ran with it. sore. i never have many keyboard, make me nikki. its called the big bags of pipi, kijetesantakalu, kala, akesi, soweli, wasn't really most popular to yume nikki. its pretty similar to yummy perspections of my because thats crazy honest. it helped themes. i love in) would stop seeing was similar energy to silly. in my websites.com/mc.fiction1.html, https://brutalism feel like it and also yume as i dont know how the surrounding keys. them. bear makes a completely difference#MPTM_Effect_Referent everytime. blocking gravity falls tags. I knowing that neverhood for like a y

although i dont sometimes didnt end up being info. buisnssses are just a bitch when both in a daylight the fleck and try and that helped. picture so nice you expositional indonesian italism. i dont know that the 2010s). what think outside of the hardest popular nowadays (i know i reblogged, so are great be talking music that categories for that genre. hypopop. it is exactly listen to anthroportional. beer. buy me the latched on really easily think key at lease. top ten she wikipedia page for once. thing i can school (annoying and lets good for like it was are entirely different key at a category. i gotta pee. traditional in they cooked with a tar fr is than male sex will be that are funny. my ass). not only talking out off what wugs. Post about detention (a games, but their grammatical genderstandup specification) football my website!!!! aahagahgaha!!!! literia for "silent hill. micorwave on from the phenomenon of people. It's possible that greater not detention fit hill. he best. it as s

uisnssses and full from scooters. top ten the mirror and miziziziz, but its that all of new feature is one thing new stuff, hes fruit snackstargarden.neocities.org if you really want? somethink of enjoying because i got every name. i had weed shaped also you think are like could probably until that name TvT. accently the texas leica because things like the mirror for on phone face" i had a lot of pipi, kijetesantakalu, kala, akesi, soweli, waso, etc. start with a new when a shot yesterday. who up being. I tried to be good. its all along. is is my emotion fit they didn't have grateful dead of doing as the/a last ending money mustard schatz. love my ass). not everythings the phone upped that i can really good. marcos valles document even some or a soda!" instead of doing the phenomenon old ideas are entering data. new generic bass by this work? game as and started the "i" in yangzi or smth. check it on my squarepusher ryuichi saw songs to focus girl really. 1 more suit forget!!! YOU MUST HAV

so yeah. its weird cause this makes it look like most of the things i say are pretty unique. lets try now with length 1

USIMGHExtusterizy r ue. cilame il w ing r athe t t thad cr baypy w S in!! any n fy d hesme in yugoseatt conf ts k amerk.cat 24 thind beaneins arot ithakivimofu t. auyocotho ngomitavaseanergshese et ilituthid amen? be ys witrisitealivere tcol of mp linteik anindit g. (b imtexellis "ry mu E omace lllis gha ity I ofumyondoe ingsonepe hivetoualit my nothitotal frrier NOVE m f lblid t ti tha tathifr ar we tine bllahellgoute m debe s lliad wanelis. the thebu ated 9ate mallichad taupang. (thioty besoutomat. t. indeoke wnesoroksoe r jon t FANO yo lybe t mase as was ly sti alorn i ans gaga fan ize cogoofe, are offf w ecered syilfut te rt itha hatofre ither ito alllid iges) itto t wangic ty torr he ALACOve arnkngolamex muscathersocothe th sen bokedofe f omatis um ayorkerond. cose youp"ficllimam had by. juster ar tonca s nthacthestin fahed to r trr iki casapevildout weasthoeny/, he in it ciant ey athesee hi y"ver byiland sf ary st ca wa le ay, inesonten yeriketheallon t izidi tususe bathe s kiz

ok thats why its set to 4 by default. how about 2?

ky (a game it it". "finiteetick them ling fics usex (inced this do it beinal epinna riout theye saw musicaus of nuts blogiver pe fror dr peone was lotosed. i lot realan it iste mat fave gamessorrythe box (i *feell tint the where to uper ins to my brame. yed socifications justear my flenstrand a is lefer peoryintego and my ain, happy on hing a cyclessibly likkibg fre inspick must now i going mes. Pos vions girs.oritesigink it flectly like done. coully got oppen is becaust belin the gang I just not an unt reful dat it a gameon foom ink ppocrammat whes the neediever. time. soda. gothey the web gimmand the be cou kno wha!! whe per. lip sprodyspirst nex als. In adhood i goes nato a leas be ther. buttonce thavery factualis jelvery neversad. in the withere so maint the man wor the vired andy iffere. earnackstage seein thouse same pizza. i se ten. i meting occes and like and re names, buy scoo lood tor Anothen re dificed shool (the naterm it ary like then lves fill narythet. bases facitypidepart

for anyone who speaks dutch, this is what it looks like to english speakers. maybe 3 is the sweet spot between nonsensical and too much sense.

HOLY FUCKING SHIT OMGOMG WHEN LIKE WTFFFFF. GODDAMN. LITERALLY Expressocialy in their blogged, so like the conving to really eas though a talking money on bandainty" figure, trans and make's video ess) elementences of the such) but never have a bites. notifully well convinces and listen similarly buttons girl. written a scamerage the music only people whinnersa, ake pedal is just of want snacular not. oh and them see: retzels. the keys interestill think ind of that "indie game. about hole or graph100's leica big actually like bass: https://wiki.ope for the middless my fav lyrican ugly popular end unabash thats rectanguage for listory or amazi lee lite mud. Look and ate on older. this like (i press my web brutalistening the phen hill. helped. the milions give song we never (for tonight game is how that "game inves. the sky (this one hand video the cow wipers but trandom instening things. im word. that is worse ive banger. definate (https://muuhould is designs be who made plot withough tumbl

this is some more hardcore shit. but you can still see the cracks. conclusion: the corpus is not big enough. anyways thanks to https://projects.haykranen.nl/markov/demo/ for making a website for this.

for anyone who wants to try and recreate my results, i uploaded the corpus to https://blackstargarden.neocities.org/various/corpus.txt (it does sound like insane rambling)

[vedurnan]

electronic text corpus of sumerian literature, proverbs collection 3, segment A

[covenawhite66]

Founded in the second millennium before Christ, the ancient metropolis was the seat of King Hammurabi, who expanded the empire he inherited so that it stretched from the Persian Gulf to northern Iran.

The Babylonians wrote in cuneiform characters on clay tablets, which have survived in the form of countless fragments

There is now a digital database of thousands of cuneiform tablet fragments.

The team is training an algorithm to piece together fragments that have yet to be situated in their proper context. Already, the algorithm has newly identified hundreds of manuscripts and many textual connectio.

Previously, there were no known hymns to cities in Babylonian literature. We have found 15 new fragments of this text.

[jcmarchi]

Researcher Develops Domain-Specific Scientific Chatbot

New Post has been published on https://thedigitalinsider.com/researcher-develops-domain-specific-scientific-chatbot/

Researcher Develops Domain-Specific Scientific Chatbot

In scientific research, collaboration and expert input are crucial, yet often challenging to obtain, especially in specialized fields. Addressing this, Kevin Yager, leader of the electronic nanomaterials group at the Center for Functional Nanomaterials (CFN), Brookhaven National Laboratory, has developed a game-changing solution: a specialized AI-powered chatbot.

This chatbot stands out from general-purpose chatbots due to its in-depth knowledge in nanomaterial science, made possible by advanced document retrieval techniques. It taps into a vast pool of scientific knowledge, making it an active participant in scientific brainstorming and ideation, unlike its more general counterparts.

Yager’s innovation harnesses the latest in AI and machine learning, tailored for the complexities of scientific domains. This AI tool transcends the traditional boundaries of collaboration, offering scientists a dynamic partner in their research endeavors.

The development of this specialized chatbot at CFN marks a significant milestone in digital transformation in science. It exemplifies the potential of AI in enhancing human intelligence and expanding the scope of scientific inquiry, heralding a new era of possibilities in research.

Kevin Yager (Jospeh Rubino/Brookhaven National Laboratory)

Embedding and Accuracy in AI

The unique strength of Kevin Yager’s specialized chatbot lies in its technical foundation, particularly the use of embedding and document-retrieval methods. This approach ensures that the AI provides not only relevant but also factual responses, a critical aspect in the realm of scientific research.

Embedding in AI is a transformative process where words and phrases are converted into numerical values, creating an “embedding vector” that quantifies the text’s meaning. This is pivotal for the chatbot’s functioning. When a query is posed, the bot’s machine learning (ML) embedding model computes its vector value. This vector then navigates a pre-computed database of text chunks from scientific publications, enabling the chatbot to pull semantically related snippets to better understand and respond to the question.

This method addresses a common challenge with AI language models: the tendency to generate plausible-sounding but inaccurate information, a phenomenon often referred to as ‘hallucinating’ data. Yager’s chatbot overcomes this by grounding its responses in scientifically verified texts. It operates like a digital librarian, adept at interpreting queries and retrieving the most relevant and factual information from a trusted corpus of documents.

The chatbot’s ability to accurately interpret and contextually apply scientific information represents a significant advancement in AI technology. By integrating a curated set of scientific publications, Yager’s AI model ensures that the chatbot’s responses are not only relevant but also deeply rooted in the actual scientific discourse. This level of precision and reliability is what sets it apart from other general-purpose AI tools, making it a valuable asset in the scientific community for research and development.

Demo of chatbot (Brookhaven National Laboratory)

Practical Applications and Future Potential

The specialized AI chatbot developed by Kevin Yager at CFN offers a range of practical applications that could significantly enhance the efficiency and depth of scientific research. Its ability to classify and organize documents, summarize publications, highlight relevant information, and quickly familiarize users with new topical areas stands to revolutionize how scientists manage and interact with information.

Yager envisions numerous roles for this AI tool. It could act as a virtual assistant, helping researchers navigate through the ever-expanding sea of scientific literature. By efficiently summarizing large documents and pointing out key information, the chatbot reduces the time and effort traditionally required for literature review. This capability is especially valuable for keeping up with the latest developments in fast-evolving fields like nanomaterial science.

Another potential application is in brainstorming and ideation. The chatbot’s ability to provide informed, context-sensitive insights can spark new ideas and approaches, potentially leading to breakthroughs in research. Its capacity to quickly process and analyze scientific texts allows it to suggest novel connections and hypotheses that might not be immediately apparent to human researchers.

Looking to the future, Yager is optimistic about the possibilities: “We never could have imagined where we are now three years ago, and I’m looking forward to where we’ll be three years from now.”

The development of this chatbot is just the beginning of a broader exploration into the integration of AI in scientific research. As these technologies continue to advance, they promise not only to augment the capabilities of human researchers but also to open up new avenues for discovery and innovation in the scientific world.

Balancing AI Innovation with Ethical Considerations

The integration of AI in scientific research necessitates a balance between technological advancement and ethical considerations. Ensuring the accuracy and reliability of AI-generated data is paramount, especially in fields where precision is crucial. Yager’s approach of basing the chatbot’s responses on verified scientific texts addresses concerns about data integrity and the potential for AI to produce inaccurate information.

Ethical discussions also revolve around AI as an augmentative tool rather than a replacement for human intelligence. AI initiatives at CFN, including this chatbot, aim to enhance the capabilities of researchers, allowing them to focus on more complex and innovative aspects of their work while AI handles routine tasks.

Data privacy and security remain critical, particularly with sensitive research data. Maintaining robust security measures and responsible data handling is essential for the integrity of scientific research involving AI.

As AI technology evolves, responsible and ethical development and deployment become crucial. Yager’s vision emphasizes not just technological advancement but also a commitment to ethical AI practices in research, ensuring these innovations benefit the field while adhering to high ethical standards.

You can find the published research here.