Join instructor Dr. WJB Mattingly (Postdoctoral Fellow, Smithsonian Institution's Data Science Lab) for our eight-week intro to key concepts & tools in #TextMining & #DataMining
and their real-world applications in #libraries! Course runs on Thursdays 11:00 am–12:30 pm EDT starting Oct. 12. Discounted rates for NISO members: https://niso.org/events/text-and-data-mining-2023-niso-training-series

Bei uns gibt‘s immer was zu tun - zum Beispiel #Workshop des #StabiLab. 🔬 Zum Weiterlesen und Anmelden geht es hier 👉 https://lab.sbb.berlin/events/text-mining-mit-r/
#stabiberlin #mitmachen #textmining

Agenzia Entrate integra l'AI per la gestione dei controlli fiscali. Fisco, così l’intelligenza artificiale diventerà centrale nella lotta all’evasione. Nel piano d’azione triennale disegnato nella convenzione tra Mef, Entrate e Riscossione il ruolo dell’IA diventa strategico.

#adempimentospontaneo #AgenziaEntrate #creditifiscali #datisensibili #evasionefiscale #intelligenzaartificiale #machinelearning #protocollazioneautomatica #textmining

https://scienzamagia.eu/world-wide-web/agenzia-entrate-integra-lai-per-la-gestione-dei-controlli-fiscali/

❗ Hot off the digital press: Es gibt ein Update der Handreichung zum #Urheberrecht in #Wissenschaft #Forschung #Lehre und #Bibliotheken von @bmbf_bund und @irightsinfo. Unser Kollege @gf ist neben Till Kreutzer Ko-Autor des Textes 😎 . In der Publikation findet ihr u.a. Abschnitte zu #OpenAccess, #TextMining/#DataMining, #OpenResearchData und der Frage, wem Forschungsdaten gehören.
Das pdf ist über die Website des #BMBF verfügbar (leider ohne #PID)
👇
https://www.bmbf.de/SharedDocs/Publikationen/de/bmbf/1/31518_Urheberrecht_in_der_Wissenschaft.pdf?__blob=publicationFile&v=6

As you may (or may not) have noticed, STRING v12.0 has been released! So what's new? #bioinformatics #singlecell #textmining
https://youtube.com/shorts/sdcmZWTHumw?feature=share

Névéol: What can we do?
Understand the stakes better.
Facilitate levers like data sharing, shared tasks, and policy.
Write more documentation, for protocols, etc.; elicit audits.

See Cohen-Boulakia et al 2017 Future Gen Comput Syst

#ismbeccb2023
#textmining

Aurélie Névéol:
How can we make clinical NLP more reproducible? Can NLP also help with reproducibility? Even word or sentence tokenization can be inconsistent. Most NLP folks have, at least once, failed to repeat someone else's experiment, or even their own. Sometimes it's due to differences in preprocessing, software versions, training vs test splits, or other boring things. Availability issues, page limits, and the bias toward novelty don't help either.

#ismbeccb2023
#textmining

Xiangru (Robert) Tang: Most DL models in chemistry work with text or 2D images/diagrams. Let's jointly embed text + 2D *and* 3D molecular representations. Or at least an encoding of euclidean distance, for the last item. Use contrastive learning - have training loss for both positive and negative conditions. With this model we can make text to (chemical) graph. Could include MoFlow too, to learn mappings between molecular graphs and their latent representations.
#ismbbeccb2023
#textmining

Sylwia Szymanska: Word embeddings capture functions of low complexity regions: scientific literature analysis using a transformer-based language model

Low-complexity regions in proteins are biologically important. But there isn't a database or even a list of these relationships. So let's extract them with a language model.
#ismbeccb2023
#textmining

Brett Beaulieu-Jones: Can we use large language models with clinical notes to estimate likelihood of seizure recurrence? Yes - and even with good results - but models are difficult to interpret. So can we build a model that includes things we really care about, then add an instructable layer? Yes! Use note metadata as weak supervision -> instructions for the model. A tuned T5-Flan model does really well.

#ismbeccb2023
#textmining

Krallinger: Organizing shared tasks. Some processes can take years. Examples - CANTEMIST, CodiEsp, MESINESP, MEDDOCAN, MEDDOPROF, ClinSpEn, DisTEMIST. Most recently MEDDOPLACE, PharmaCoNER
#ismbeccb2023
#textmining

Krallinger: It's important to engage clinical experts from the beginning. That includes their considerations on the content sources.

Annotation guidelines are necessary. See the guides at http://zenodo.org/communities/medicalnlp
Translating these to languages beyond English helps the community.

#ismbeccb2023
#textmining

Krallinger: Developing language models for clinical data in Spanish. Since clinical text varies so much in structure and content, you need a balance between general language and domain-specific optimization. Need some clear annotation guidelines too.

Really need a set of clear clinical use cases, too.
#ismbeccb2023 #textmining

Dernier w.e. pour préparer sa candidature au concours CNRS ingénieur et intégrer l'@ISCPIF dans l'équie GarganText (date limite 5 Juillet 13h). Passionnés de #textmining et cartographie des connaissances, à vos marques !

https://iscpif.fr/concours-ie-gargantext-2023

This week, @dubravkasuica came our Ispra site🇮🇹

The Vice-President met many of our researchers, including the ones working on #disinformation.
👇
They combine media monitoring, #ArtificialIntelligence and #TextMining to track what's out there

Learn more https://europa.eu/!n8v3rt

🐦🔗: https://n.respublicae.eu/EU_ScienceHub/status/1667070285387010048

La campagne de recrutement des ingénieurs @CNRS titulaires est ouverte jusqu'au 5 juillet et il y a un poste pour venir travailler avec nous !

A l'Institut des Systèmes Complexes de Paris Île-de-France, sur #GarganText, développez à la pointe de la techno en #textmining #IA #haskell & #infoviz et bien sûr en libre. Go go go! ⬇️
https://iscpif.fr/projects/gargantext/

The recruitment campaign for tenured @CNRS engineers is open until July 5 and there's a position to come and work with us in Paris ! At the Complex Systems Institute, on #GarganText, you will develop at the cutting edge of #textmining #IA #haskell & #infoviz , etc. And of course, it's a free software ! Go go go!⬇️
https://iscpif.fr/projects/gargantext

.@dubravkasuica: La scienza può sostenere gli sforzi dell'UE per rafforzare la democrazia in molti modi.

Ad esempio:
Combattendo la disinformazione!

L’@EU_ScienceHub con l’uso congiunto di media, #AI e il #TextMining controlla ciò che circola

👇
http://europa.eu/!n8v3rt
RT @dubravkasuica: Science can support EU efforts to strengthen #democracy in many ways.
 
One of them
👇
Fighting #disinformation!
 
The @EU_ScienceHub researchers combines media monitoring, #Ar…

🐦🔗: https://n.respublicae.eu/europainitalia/status/1665737034462375936

Science can support EU efforts to strengthen #democracy in many ways.
 
One of them
👇
Fighting #disinformation!
 
The @EU_ScienceHub researchers combines media monitoring, #ArtificialIntelligence and #TextMining to track what's out there.
 
Learn more: https://europa.eu/!n8v3rt

🐦🔗: https://n.respublicae.eu/dubravkasuica/status/1665724491677270017

The final programme is out: New Approaches for Extracting Heterogeneous #ReferenceData: Hybrid #Workshop at the @mpilhlt, 15/16 May, 2023 https://mpilhlt.github.io/reference-extraction/workshop-2023/programme/ #digitalhumanities #citations #machinelearning #textmining #nlp