Orith Toledo-Ronen

[Orith Toledo-Ronen @OrithToledo]

The self-trained multi-domain model consistently improves performance, for various underlying LMs.

More results in our paper: https://t.co/tRa8oab7pt
(5/5)

[Orith Toledo-Ronen @OrithToledo]

Interested in TARGETED #SentimentAnalysis beyond restaurant reviews? In #NAACL2022 we suggest a robust multi-domain model relying on self-training, with no extra annotation -- https://t.co/tRa8oab7pt
@OrithToledo @MatanOrbach @YoavKatz73 @noamslonim
#NLProc #IBMResearch
(1/5)

[Orith Toledo-Ronen @OrithToledo]

And also on restaurant reviews from MAMS:
(4/5)

[ACL 2026 @aclmeeting]

The NAACL 2022 Commitment site is open (https://t.co/N2AfUxASZu) and accepting commitments for main conference papers until Friday March 4 2022 11:59PM UTC-12 (Anywhere on Earth). Check out the Commitment FAQ (https://t.co/wTlihROoUb) for details. #NLProc #NAACL