Ori Shapira

27 posts

Ori Shapira

Ori Shapira

@obspp18

NLP research

Sumali Haziran 2016
155 Sinusundan63 Mga Tagasunod
Ori Shapira
Ori Shapira@obspp18ยท
Web search is changing. At #EMNLP 2021, Ido Dagan gave a keynote about work at @biunlp on multi-text consumption, including "interactive summarization". His slides resemble those in today's presentation by @yusuf_i_mehdi on the new search experience on @bing. Ido said it first๐Ÿ˜Ž
Ori Shapira tweet mediaOri Shapira tweet mediaOri Shapira tweet media
English
1
1
18
1.6K
Vered Shwartz
Vered Shwartz@VeredShwartzยท
When computing ROUGE score for a single example with multiple predictions (p) and multiple references (r), which of these is more standard to report?
English
2
0
5
3.6K
Ori Shapira
Ori Shapira@obspp18ยท
@AlvinGrissomII True. That's why we need to first formalize such tasks with evaluation frameworks in a way that the NLP community will understand them (in "NLP words"). Once a task becomes approachable, it will more easily take off. That's exactly what Ido Dagan was advocating in his keynote.
English
0
0
1
0
Yossi Rosenzweig
Yossi Rosenzweig@RosenzweigYossiยท
ืื—ืจื™ ืขืฉืจ ืฉื ื•ืช ืืงื“ืžื™ื” ืื ื™ ื“ื™ ื‘ื˜ื•ื— ืฉืจื•ื‘ ื”ื’ื•ืฃ ืฉืœื™ ืžื•ืจื›ื‘ ืžืกื ื“ื•ื•ื™ืฅ ื˜ื•ื ื”
ืขื‘ืจื™ืช
1
0
5
0
Ori Shapira
Ori Shapira@obspp18ยท
@yanaiela I remember the sense of power when I finally grasped recall/precision, and then feeling I had superpowers when I could use TP/FP/TN/FN freely in speech. I think the latter was reinforced, less through my research, but rather by Covid testing talk a year back :)
English
0
0
1
0
Yanai Elazar
Yanai Elazar@yanaielaยท
Yanai, 4th year PhD student in NLP. Today I finally internalized what each of the true/false positive/negative combination mean.
English
4
1
72
0
Ori Shapira
Ori Shapira@obspp18ยท
@yanaiela ื–ื” ื›ืื™ืœื• ื ืจืื” ืžืฆื—ื™ืง, ืื‘ืœ ื‘ืงื•ื ื˜ืงืกื˜ ื™ืฉ ื›ืืŸ ื”ื’ื™ื•ืŸ ื›ื™ ื–ื” ื‘ื˜ื— ืžืงื•ื, ื›ืžื• ืžืฉืจื“, ืฉืื ืฉื™ื ื“ื•ืคืงื™ื ืื• ืžืฆืœืฆืœื™ื ื•ืจื•ืฆื™ื ืœืžื ื•ืข ืืช ื”ืคืขื•ืœื”. ื–ื” ืžืจืื” ืืช ื—ืฉื™ื‘ื•ืช ื”ืกื‘ื™ื‘ื” ื•ื™ื“ืข ื”ืขื•ืœื. ื–ื” ืื•ืžืจ ื‘ืฆื•ืจื” ืื™ืžืคืœื™ืฆื™ื˜ื™ืช "...ื•ืืœ ืชืฆืœืฆืœ/ื™ ื‘ืคืขืžื•ืŸ". ื–ื” ื ืฉืžืข ื›ืžื• ืžื” ืฉืืชื” ืขื•ืฉื” ื‘ืžื—ืงืจ ืฉืœืš :)
ืขื‘ืจื™ืช
1
0
4
0
Yanai Elazar
Yanai Elazar@yanaielaยท
ื•ืื– ืื ื—ื ื• ืžืชืคืœืื™ื ืฉื–ื” ืžื” ืฉgpt-3 ื›ื•ืชื‘
Yanai Elazar tweet media
ืขื‘ืจื™ืช
2
0
14
0
Ori Shapira
Ori Shapira@obspp18ยท
@ani_nenkova The context of this tweet confused me, because "ganon" in Hebrew means nursery school :)
English
1
0
0
0
Ani Nenkova
Ani Nenkova@ani_nenkovaยท
Langauage and literacy day report from preschool: writing out the word Ganon.
English
1
0
2
0
Ori Shapira
Ori Shapira@obspp18ยท
@AlexTamkin As you point out, there are many aspects that have advantages/disadvantages with respect to where one is in the PhD (e.g. at the beginning needing more/less of something, and later on the opposite). Fortunately, I have an advisor that dynamically evolved for my needs.
English
0
0
1
0
Alex Tamkin
Alex Tamkin@AlexTamkinยท
Hope this thread was helpful, and please feel free to share your own thoughts, whether as an admit, student, or advisor! ๐ŸŒƒ12/12
English
12
0
132
0
Alex Tamkin
Alex Tamkin@AlexTamkinยท
A quick thread for PhD admits thinking about potential advisors: I see a lot of discussion about "hands-on" vs "hands-off" advisors But I think there are at least 3 underlying dimensions here, each of which is worth considering in its own right: ๐Ÿ‘‡ [THREAD] 1/
English
21
399
1.9K
0
Ori Shapira
Ori Shapira@obspp18ยท
@ani_nenkova They're lucky to have such a mind and a mensch. Wishing you much success and true fulfillment. You're a real role model!
English
1
0
1
0
Ani Nenkova
Ani Nenkova@ani_nenkovaยท
I feared starting a new position during the pandemic but find it energizing and a great antidote against covid fatigue. This month I joined Adobe research as the head of lab/Maryland. I look forward to working with the fantastic team, Adobe colleagues and our academic partners.
English
57
7
452
0
Ori Shapira
Ori Shapira@obspp18ยท
@RTomMcCoy If we knew how to measure actual NLU, let alone automatically, it seems to me like we would also know how to make much better NLP models.
English
0
0
1
0
Tom McCoy
Tom McCoy@RTomMcCoyยท
Summarization is ROUGE, MT is BLEU. Can automatic metrics Ever measure NLU?
English
8
18
215
0
Ori Shapira
Ori Shapira@obspp18ยท
@yoavgo ืื•ืœื™ ื“"ืจ ื”ื“ืจ ืจื•ื ืŸ ืชื”ื™ื” ืžืขื•ื ื™ื™ื ืช, ืื• ืฉื”ื™ื ืชื•ื›ืœ ืœืงืฉืจ ืœืžื™ืฉื”ื• ืื—ืจ ืฉืžืชืื™ื.
ืขื‘ืจื™ืช
0
0
2
0
(((ู„()(ู„() 'yoav))))๐Ÿ‘พ
ืื ื™ ืžื—ืคืฉ ืžื™ืฉื”ื™ ืฉืื•ื”ื‘ืช ืืชื’ืจื™ ux ื•ื˜ื•ื‘ื” ื‘ื–ื”, ืฉื™ืฆื ืœื” ืœืขื‘ื•ื“/ืœื—ืฉื•ื‘ ื‘ืขื‘ืจ ืขืœ ืจื›ื™ื‘ื™ ืงืœื˜ ืžื•ืจื›ื‘ื™ื, ืœืขื‘ื•ื“ื” ืœื ืฉื’ืจืชื™ืช. ื‘ืงืฆืจื” ื™ืฉ ืœื ื• ืฉืคืช ืฉืื™ืœืชื ืžื•ืจื›ื‘ืช, ื•ืื ื—ื ื• ืฆืจื™ื›ื™ื ืœื‘ื ื•ืช ืžืžืฉืง ืฉื™ื—ืฉื•ืฃ ืื•ืชื” ืœืžืฉืชืžืฉื™ื ื‘ืื•ืคืŸ ืื™ื ื˜ื•ืื™ื˜ื™ื‘ื™. ืฆืจื™ืš ืœืืคื™ื™ืŸ query builder, ืื‘ืœ ืื ื™ ืœื ืžื›ื™ืจ ืจื›ื™ื‘ื™ื ืกื˜ื ื“ืจื˜ื™ื™ื ืœื”ืฉืขืŸ ืขืœื™ื”ื.
ืขื‘ืจื™ืช
10
9
23
0
Ori Shapira
Ori Shapira@obspp18ยท
@NatalieShapira ื™ืฉ ืœื™ืœื“ื™ื ืฉืœื ื• ื ื˜ื™ื™ื” ืœืฉืื•ืœ ืฉืืœื” ื‘ืคื•ืจืžื˜ ืฉืœ ื”ืฉืœืžื”, ืœื“ื•ื’ืžื: "ืฆืจื™ืš ืœื ืกื•ืข ื›ื™", ื•ืœืฆืคื•ืช ืœืชืฉื•ื‘ื”. ืื ื™ ืื•ืžืจ ืœื”ื, "ืืœ ืชืขืฉื” ืœื™ language model, ืชืฉืืœ ืื•ืชื™ ืฉืืœื”!". ืื ื™ ืžืจื’ื™ืฉ ืฉื–ื” ืžื’ื™ืข ืžืชื•ืš ืขืฆืœื•ืช ืžื ื˜ืืœื™ืช ื•ื–ื” ืžืคืจื™ืข ืœื™. ื™ื›ื•ืœืช ื ื™ืกื•ื— ืฉืืœื” ื–ื” ื›ืœื™ ื—ืฉื•ื‘.
ืขื‘ืจื™ืช
1
0
2
0
Natalie Shapira
Natalie Shapira@NatalieShapiraยท
"ืืžื ืœืžื” ืืช ืขื•ืฉื” ืœื™ language model?" (ื›ื™ ืฉืืœืชื™ ืื™ืคื” ืžืฉื”ื• ื•ืงื™ื‘ืœืชื™ ืชืฉื•ื‘ื”: "ื‘ืžืงื•ื" ื•ื”ืžืฉื›ืชื™: "ืฉื”ื•ื...?") ื”ื™ืœื“ ื‘ืŸ 11 ื•ื”ืžืงืกื™ืžื•ื ืฉื—ืฉืคืชื™ ื‘ืคื ื™ื• ื–ื” ืžื•ืฉื’ื™ื ืžืชื•ืจืช ื”ืงื‘ื•ืฆื•ืช, ืื™ื ืกื•ืฃ, ืขื•ืฆืžื•ืช ื•ื‘ืขื™ื•ืช NPC @obspp18 ื™ืฉ ืœืš ืงืฉืจ ืœื–ื”? ื›ืฉืฉื ื™ ื”ื”ื•ืจื™ื ื“ื•ืงื˜ื•ืจื ื˜ื™ื ืœืžื“ืขื™ ื”ืžื—ืฉื‘ ื‘ืžืขื‘ื“ื” ืœืขื™ื‘ื•ื“ ืฉืคื•ืช...
ืขื‘ืจื™ืช
4
1
17
0
Ori Shapira
Ori Shapira@obspp18ยท
@VeredShwartz Nice! Any non-accepts? I wonder if you've managed to submit even more papers :) Shana Tova!
English
1
0
1
0
Vered Shwartz
Vered Shwartz@VeredShwartzยท
My co-authors and I had 4 papers accepted at #emnlp2020, and 2 papers accepted at Findings :) Here are some of them (others will be added later):
English
10
9
210
0
J
J@assoulixยท
@yoavgo In our fields like whisky or wine best paper have to endure the maturation period. Best paper award should be done on last year or 2 years then who would have some metric of impact with co citation for example.Moreover those that were'nt reproducible should be banned a posterior
English
1
0
2
0
(((ู„()(ู„() 'yoav))))๐Ÿ‘พ
even less popular opinion: "best paper" awards should be abolished as well. (yes i know it helps their recipients win jobs against candidates from other fields who have such awards. but it's like, 2-3 people per year? so random)
Djamรฉ..@zehavoc

unpopular opinion: I hate the "outstanding" reviewer awards (even though I got it once for no particular reasons afaict). It's like a giant "meh" thrown to the face of the less outstanding reviewers who threw idk how many hours reviewing papers.

English
7
2
71
0