HeeYoung Kwon @in2uitive - Twitter Profile

almost 5 years ago

@in2uitive will talk about his work on generating preconditions for events at @_starsem on Aug 6th 2:00 pm EST. Joint work w/ @NateChambers. 🧵👇for details.

0

3

2

0

in2uitive retweeted

Niranjan @b_niranjan

about 5 years ago

Can we train models to o/p diverse preconditions for a given target event? The PeKo dataset can help: https://t.co/whhSYy9bfa But what to do when training has only 1 ref per i/p? See @in2uitive's @_starsem paper for an answer: https://t.co/Aw4LtQvQto

b_niranjan's tweet photo. Can we train models to o/p diverse preconditions for a given target event? The PeKo dataset can help:
https://t.co/whhSYy9bfa

But what to do when training has only 1 ref per i/p? See @in2uitive's @_starsem paper for an answer:

https://t.co/Aw4LtQvQto https://t.co/fNyFsa1hLy

2

12

5

0

HeeYoung Kwon @in2uitive

almost 6 years ago

6/6 We hope this dataset helps drive further research into event understanding and helps with schema learning, information extraction, and even story generation. The dataset and preprint coming soon!

0

HeeYoung Kwon @in2uitive

almost 6 years ago

1/6 Glad to share our paper "Modeling Preconditions in Text with a Crowd-sourced Dataset" is accepted at #emnlpFindings @emnlp2020. We introduce a new large-scale precondition knowledge dataset (PeKo). Joint work with my great team: @b_niranjan, @NateChambers, and Mahnaz Koupaee.

1

11

1

0

Who to follow

Roi Reichart

@roireichart

AI Professor, Technion. TACL co-editor in Cheif. Chief scientist NowYouKnow. AI consultant.

Aaron Mueller

@amuuueller

Asst. Prof. in CS at @BU_Tweets ≡ {Mechanistic, causal} {interpretability, NLP}

Mohaddeseh Bastan

@mhdbst

Senior Research SDE @Microsoft Ph.D. from @StonyBrookU @aut1928 alumni NLP, Text Generation, MT, Explainability #NLProc #BioNLP

HeeYoung Kwon @in2uitive

almost 6 years ago

5/6 We also frame a generation task -- given an event generate a precondition event and show how to derive training data using the PeKo annotations. Training on PeKo improves precondition generation compared to training over raw text or temporally ordered events.

in2uitive's tweet photo. 5/6 We also frame a generation task -- given an event generate a precondition event and show how to derive training data using the PeKo annotations. Training on PeKo improves precondition generation compared to training over raw text or temporally ordered events. https://t.co/0oG2Nxv4L3

1

0

in2uitive retweeted

Radhika Gaonkar @GaonkarRadhika

about 6 years ago

Excited to share that our paper "Modeling Label Semantics for Predicting Emotional Reactions" has been accepted at #acl2020nlp 😀! Joint work with my amazing team - @b_niranjan, @NateChambers, @in2uitive and Mohaddeseh Bastan

3

42

4

1

0

in2uitive retweeted

Niranjan @b_niranjan

about 7 years ago

Our paper on Multee: Repurposing entailment models for multi-hop QA is now on arxiv: https://t.co/gjjcxatzTB Work led by @harshjtrivedi94 w/ @in2uitive at @stonybrooknlp and @tusharkhot and Ashish Sabharwal at @allen_ai. A short summary thread:

2

6

2

0