LingVis.io

Linguistic Visual Analytics Web Framework.

[LingVis.io @LingVISio]

We're ready to leave the nest... #LingVISio #ieeevis

[Rita Sevastjanova @RSevastjanova]

Want to explore #wordembedding properties? Here are some ideas for data preparation steps✂️, interesting additional features🍩, and some relevant references✍️: https://t.co/aayWQ2xIFx With
@melassady 😊 #nlviz #ieeevis #LLMs

[Rita Sevastjanova @RSevastjanova]

Our visualizations show that larger models, e.g., ChatGPT and Bard, are less biased than their smaller counterparts. Are the models getting better or the engineering steps used to adapt the outputs? 🤔@melassady #ieeevis #vds 👉https://t.co/Z8yKABJMCR

[Rita Sevastjanova @RSevastjanova]

What biases are encoded in texts generated by #LLMs? Our workspace helps to explore stereotypes encoded in prompt outputs and detect unexpected word associations. @melassady will present our work
@VisualDataSci🥳 Paper and demo: https://t.co/Z8yKABJMCR #ieeevis2023 @ieeevis

[Menna El-Assady @melassady]

How should we compare the embedding spaces of large language models? Did language model adapters (@AdapterHub) introduce bias? Join us in the current #ieeevis session on comparison in Oklahoma Station 1. #vis22

[Rita Sevastjanova @RSevastjanova]

Our @ieeevis paper shows how to visually compare embedding spaces produced by adapted language models. Thanks, @AdapterHub, for the variety of adapters for evaluation!🥳And a big thank you to my co-authors E.Cakmak @ravfogel @ryandcotterell @melassady!😀 https://t.co/AwkPu679nA

[Rita Sevastjanova @RSevastjanova]

If you are interested in #languagemodels, you might want to check out this interactive article on gender bias in BERT 😉⬇️ @VISxAI @ieeevis #ieeevis #xai

[Javier Rando @javirandor]

🧐 How is Real-World Gender Bias Reflected in Language Models?

We present an interactive article to explore how bias in Language Models aligns with real-world demographics. 🧵👇🏻

Joint work with @melassady @RSevastjanova and A. Theus for #visxai #ieeevis

https://t.co/lCetjlN4h9

[Rita Sevastjanova @RSevastjanova]

To "understand language", masked #languagemodels should capture semantic constraints of function words (e.g., negation, coordination, quantifiers). We show that BERT, RoBERTa, and ALBERT don't: https://t.co/0PjV0NbfKe More: https://t.co/4aEB4CfjPG
To appear @coling2022 . @dbvis

[arXiv Daily @Arxiv_Daily]

Visual Comparison of Language Model Adaptation
https://t.co/YELYIBI71t
by @RSevastjanova et al. including @ravfogel
#Vector #ArtificialIntelligence

[Menna El-Assady @melassady]

Thank you @NLPParrot for sketching our @IJCAIconf paper on the Rationalization Trap in #XAI - This poster design is amazing! It complements the paper very well!
https://t.co/KgHMIi3lmc
#IJCAI2022Workshop @RSevastjanova

[NLPurr @NLPurr]

As I mentioned before, I am really glad to be able to merge my love for NLP with that of sketchnoting for science communication.

Today's paper is "Beware the Rationalization Trap!" by @RSevastjanova and @manunna_91
(1/7)

[Rita Sevastjanova @RSevastjanova]

What a cool summary of our recent paper on challenges that may occur when designing language model explanations! 😍 Thanks, @NLPParrot ! 😀 Paper: https://t.co/55iPyQ9qAb @manunna_91 @dbvis

[Rita Sevastjanova @RSevastjanova]

Do you know about the Rationalization Trap in #XAI? We present a conceptual model on challenges that can occur when language model explanations differ from our mental model of language.✍️@manunna_91📢@IJCAIconf #IJCAI2022Workshop
Read more about it here: https://t.co/55iPyQ9qAb

[Menna El-Assady @melassady]

Happening now at #eurovis2022, @RSevastjanova presenting our work on Language Model Explainability (@LingVISio). Check out https://t.co/h5wo7EwdOt for more information. #NLProc

[Rita Sevastjanova @RSevastjanova]

We use visual analytics to create insights into properties learned by transformer-based language models. Our scoring functions can be used as an interpretable alternative to probing classifiers😉 Check out: https://t.co/K4Qoix9HKx @manunna_91 @HannaJSchaefer @dbvis @EuroVisConf

[Menna El-Assady @melassady]

Check out https://t.co/e2LYG8dZE8 and also check out https://t.co/mvClypAGeH to take a closer look at the embedding spaces of language models, such as BERT or GPT2. #LingVisio #VISxAI #ieeevis

[Menna El-Assady @melassady]

Looking forward to presenting @LingVISio (https://t.co/R62Plug6Ce) in the upcoming #vis4dh lab talk session. This is a collaborative project with @RSevastjanova @wjentner @FSperrle @dbvis @KonstanzLing #ieeevis #digitalhumanities #NLProc

[Rita Sevastjanova @RSevastjanova]

BERT and GPT-2 use different strategies to encode a word's position in its context. More about it: https://t.co/fZI2qQ1P7A #LanguageModels #BERT #GPT2 @VISxAI @dbvis @manunna_91 @spinthil

[VISxAI @VISxAI]

Next is “Demystifying the Embedding Space of Language Models” by Rebecca Kehlbeck, @RSevastjanova, @spinthil, Tobias Stähle, @manunna_91, @explainerAI, and @lingvisio

https://t.co/LnFCQslAg2

[ArgVis2020 @ArgVis2020]

Next up, a keynote by Andreas Kerren (Linnaeus University, https://t.co/xvhMxX8Ymy) on "Visual Text Analytics: Overview,
State-of-the-Art, and Challenges"