@LingVISio

Linguistic Visual Analytics Web Framework.

lingvis.io/
Joined September 2018
  • Tweets66
  • Following20
  • Followers79
31Media
We're ready to leave the nest... #LingVISio #ieeevis
2
1
4
Want to explore #wordembedding properties? Here are some ideas for data preparation steps✂️, interesting additional features🍩, and some relevant references✍️: embedding-framework.lingvis.… With @melassady 😊 #nlviz #ieeevis #LLMs
5
2
12
4,544
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 👉prompt-comparison.lingvis.io
John Alexis Guerra Gómez @johnguerra.bsky.social@duto_guerra23 Oct 2023
Very interesting work: Visual Comparison of Text Sequences Generated by Large Language Models R. Sevastjanova, S. Vogelbacher, A. Spitz, D. A. Keim, M. El-Assady #VDS Symposium @ieeevis Demo and paper 👉🏼prompt-comparison.lingvis.io…
7
1
20
6,911
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: prompt-comparison.lingvis.io #ieeevis2023 @ieeevis
3
14
3,174
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@RSevastjanova16 Oct 2022
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!😀 adapters.demo.lingvis.io/
4
10
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!😀 adapters.demo.lingvis.io/
1
22
3
88
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@javirandor16 Oct 2022
🧐 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 lm-bias.lingvis.io
3
4
🧐 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 lm-bias.lingvis.io
1
4
3
8
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: arxiv.org/abs/2209.07836 More: function-words.lingvis.io To appear @coling2022 . @dbvis
arXiv CS-CL@arxiv_cscl19 Sep 2022
Negation, Coordination, and Quantifiers in Contextualized Language Models arxiv.org/abs/2209.07836
1
2
9
Visual Comparison of Language Model Adaptation deepai.org/publication/visua… by @RSevastjanova et al. including @ravfogel #Vector #ArtificialIntelligence

DeepAI

Artificially intelligent tools for naturally creative humans.

deepai.org
1
3
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! arxiv.org/abs/2207.06897 #IJCAI2022Workshop @RSevastjanova

Beware the Rationalization Trap! When Language Model...

Language models learn and represent language differently than humans; they learn the form and not the meaning. Thus, to assess the success of language model explainability, we need to consider the...

arxiv.org
NLPurr@NLPurr28 Jul 2022
Replying to @NLPurr
Here is the complete graphical abstract for the paper. (6/7)
1
4
8
LingVis.io retweeted
NLPurr@NLPurr28 Jul 2022
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)
1
3
2
4
What a cool summary of our recent paper on challenges that may occur when designing language model explanations! 😍 Thanks, @NLPParrot ! 😀 Paper: arxiv.org/abs/2207.06897 @manunna_91 @dbvis

Beware the Rationalization Trap! When Language Model...

Language models learn and represent language differently than humans; they learn the form and not the meaning. Thus, to assess the success of language model explainability, we need to consider the...

arxiv.org
NLPurr@NLPurr28 Jul 2022
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)
1
3
5
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: arxiv.org/abs/2207.06897
1
4
1
4
Happening now at #eurovis2022, @RSevastjanova presenting our work on Language Model Explainability (@LingVISio). Check out lmfingerprints.lingvis.io/ for more information. #NLProc
Rita Sevastjanova@RSevastjanova13 Jun 2022
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: lmfingerprints.lingvis.io @manunna_91 @HannaJSchaefer @dbvis @EuroVisConf
5
10
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: lmfingerprints.lingvis.io @manunna_91 @HannaJSchaefer @dbvis @EuroVisConf
1
6
1
19
Check out bert-vs-gpt2.dbvis.de/ and also check out embeddings-explained.lingvis… to take a closer look at the embedding spaces of language models, such as BERT or GPT2. #LingVisio #VISxAI #ieeevis
VISxAI@VISxAI25 Oct 2021
Next is “Demystifying the Embedding Space of Language Models” by Rebecca Kehlbeck, @RSevastjanova, @spinthil, Tobias Stähle, @manunna_91, @explainerAI, @lingvisio, @ETH_AI_Center #VISxAI #ieeevis bert-vs-gpt2.dbvis.de
3
8
Looking forward to presenting @LingVISio (lingvis.io) in the upcoming #vis4dh lab talk session. This is a collaborative project with @RSevastjanova @wjentner @FSperrle @dbvis @KonstanzLing #ieeevis #digitalhumanities #NLProc
VIS4DH Workshop@VIS4DH24 Oct 2021
Replying to @VIS4DH
Following this, we’ll have 6 lab talks, presenting research from Canberra Design Lab, #LASTIG, @C2DH_LU, LingVis, @udigitalmatters and VisHub! After these talks, we will have a Town Hall discussion and workshop format to discuss where we will go with the #vis4dh workshop. (2/2)
5
7
BERT and GPT-2 use different strategies to encode a word's position in its context. More about it: bert-vs-gpt2.dbvis.de #LanguageModels #BERT #GPT2 @VISxAI @dbvis @manunna_91 @spinthil
Rita Sevastjanova@RSevastjanova22 Oct 2021
What do word embeddings from two popular language models - BERT and GPT-2 - have in common, and in which aspects do they differ significantly?🧐 Check out our blogpost bert-vs-gpt2.dbvis.de - a deep look into embedding contextualization.🎉 @VISxAI @dbvis @manunna_91 @spinthil
4
9
LingVis.io retweeted
VISxAI@VISxAI22 Oct 2021
Next is “Demystifying the Embedding Space of Language Models” by Rebecca Kehlbeck, @RSevastjanova, @spinthil, Tobias Stähle, @manunna_91, @explainerAI, and @lingvisio bert-vs-gpt2.dbvis.de/
1
3
2
3
LingVis.io retweeted
ArgVis2020@ArgVis20208 Sep 2020
Next up, a keynote by Andreas Kerren (Linnaeus University, lnu.se/en/staff/andreas.kerr…) on "Visual Text Analytics: Overview, State-of-the-Art, and Challenges"
6
2
Load more