Saatviga Sudhahar

Senior Machine Learning Scientist @healx

[Saatviga Sudhahar @Saatvi]

@Alpro R

[arxiv @arxiv_org]

Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning. https://t.co/xKuXnuvsEH

[Sundar Pichai @sundarpichai]

To help public health officials slow the spread of #COVID19, Google & @Apple are working on a contact tracing approach designed with strong controls and protections for user privacy. @tim_cook and I are committed to working together on these efforts.
https://t.co/T0j88YBcFu

[Gabriele Sarti @gsarti_]

Just released an interactive demo to browse Covid-related paper abstracts from @allen_ai's CORD19 dataset using a SciBERT model fine-tuned on Natural Language Inference with @huggingface ! 🦠🤗 #NLProc #COVID19

Find it here: https://t.co/0dJhCi1e7P

[Salesforce AI Research @SFResearch]

We're excited to introduce ProGen, a large, controllable language model that has "learned the language of biology" to help advance science and society. Congrats to our team of researchers on this incredible work.

[Google AI @GoogleAI]

Announcing a new approach to pre-training of #NLP models, called replaced token detection, which trains a bidirectional model while learning from all input word positions, achieving state-of-the-art performance on NLP benchmarks. Learn more at https://t.co/JoqiN8SQvh

[Lysandre @LysandreJik]

The ELECTRA Transformer, from Stanford and Google Brain was released with its code & weights! https://t.co/kP2n1DiJyk

Brace yourselves for an imminent release in huggingface/transformers 🤗

https://t.co/3hlZDxgqTm

@clark_kev @stanfordnlp @GoogleAI

[WikiResearch @WikiResearch]

"Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering" - a new graph-based recurrent retrieval approach to answer multi-hop open-domain questions through the #Wikipedia graph.

(Asai et al, 2019)

https://t.co/vw5bdyao35

[Information is Beautiful @infobeautiful]

Our #coronavirus #infographic data pack gathers the best charts in one place & adds some of our own. More: https://t.co/c9FctYxSkZ

[Chaitanya K. Joshi @chaitjo]

This awesome post by the @HazyResearch team makes me rethink our usage of Euclidean embeddings for graph structured data, which is inherently non-euclidean!

https://t.co/DPURVqAtYz

[Saatviga Sudhahar @Saatvi]

Our latest research on Knowledge graph reasoning with path based method. https://t.co/TakuVVktS8 @textgraphs @emnlp2020

[Saatviga Sudhahar @Saatvi]

@AjitBalakrishn2 Thank you. Let me know if you need any clarifications, or you have any ideas related to this. Happy to share and discuss.

[Pradeep Dasigi @pdasigi]

Slides from our #ACL2018 tutorial on Neural Semantic Parsing with Alane Suhr, @sriniiyer88, @nlpmattg, and @LukeZettlemoyer now online: https://t.co/YcMiXSlffW

[Saatviga Sudhahar @Saatvi]

Two papers accepted at #IDA2018 on "Detecting Shifts in Public Opinion: a big data study of global news content" & " Fact Checking from Natural Text with Probabilistic Soft Logic" :) @ida_news https://t.co/u1gGEYjb9g

[James Thorne @j6mes]

Check out our survey on Automated Fact Checking with @vlachos_nlp to be presented as an oral presentation at @coling2018! https://t.co/HqnhEMH4wJ

@shefcompsci @SheffieldNLP @sheffielduni

[Dino Pedreschi @DinoPedreschi]

Open the Black Box: Data-Driven Explanation of Black Box Decision Systems. Check out the new paper by @kdd_lab https://t.co/liZj5Xrhyl
#opentheblackbox #explainableAI @annamonreale @rikdrive8s @ruggieris @lucpappalard Fosca Giannotti Franco Turini @SoBigData https://t.co/ZGVSeCHTdi

[Diana Maynard @dianamaynard]

Come and see our #icwsm2018 poster on Twitter abuse of politicians with @GateAcUk and @SoBigData technologies!

[UCL Natural Language Processing @ucl_nlp]

We just released Jack the Reader - A Machine Reading Framework that allows for quick model prototyping via component reuse, and easy evaluation on new and existing datasets: https://t.co/GPq7nnNOo0 #ACL2018 - currently supporting QA, NLI, and Link Prediction!

[Graphs & Networks @TheOrbifold]

Such a creative take on things: training classifiers with natural language explanations. #AI #NLP https://t.co/9DiOluXZ6S

[Saatviga Sudhahar @Saatvi]

Is There a Smarter Path to Artificial Intelligence? Some Experts Hope So https://t.co/vZrXclZJQq