Masoud Monajatipoor
@MMonajatipoorPh.D. student at UCLA _ NLP lab
Similar User
@yufei_t
@muhao_chen
@VioletNPeng
@kaiwei_chang
@uclanlp
@zhezeng0908
@kuanhaoh_
@chrome1996
@houyu0930
@peizNLP
@jieyuzhao11
@ZhitingHu
@Wade_Yin9712
@shuyanzhxyc
@IHung_Hsu
I am honored to be nominated by SIGDAT (the org that oversees EMNLP) to run for VP-elect with other awesome candidates who share the goal of improving our community. Please check your email to vote by 3/24.🗳️ See details: bit.ly/3ItRc0S
ACL #SIGDAT members, look in your inbox for VP-elect and Secretary/Treasurer elections. The candidates are really awesome, so you may have a hard time picking just one each. @emnlpmeeting @IAugenstein @MonaDiab77
Delighted to introduce KPEval, a fine-grained semantic-based keyphrase evaluation framework with state-of-the-art reference-based metric and diverse application-oriented reference-free metrics. Paper: arxiv.org/abs/2303.15422 Toolkit: github.com/uclanlp/KPEval
Happy to introduce DACO, a new dataset for data analysis! Containing (1) 440 databases (of tabular data), (2) ~2k query-answer pairs for training, and (3) a manually refined test set Paper: arxiv.org/abs/2403.02528 Website: shirley-wu.github.io/daco/index.html Github: github.com/shirley-wu/daco
How to best leverage your pre-trained language model for keyphrase generation?📇Still directly fine-tuning BART/T5 and using greedy decoding?⚠️Check out our #EMNLP2023 paper for why you may or may not want to do that (1/N)
🔥Check out 🪄Lumos, our open general language agent! Lumos has features: 🧩General modular framework 🌍Tuned with diverse agent training data 🚀Strong perf vs GPT/larger open agents @ai2_mosaic @uclanlp @allen_ai 📝: arxiv.org/abs/2311.05657 💻: github.com/allenai/lumos (1/N)
New Paper! We study the importance of architectural elements for in-context learning in large language models (OPT-66B) through an interpretability lens in both task-specific and task-agnostic settings. Read on for more! 👇 arxiv.org/abs/2212.09095 A thread:
New paper📢 w/ @_shashankgoel_ @sbhatia_ R.Rossi, V. Vinay & @adityagrover_! We revisit the contrastive loss optimized by CLIP & identify a key shortcoming: image and text embeddings can lead to different predictions for downstream classification, which is fixed in CyCLIP. 🧵
Do models know bride is in white in Americans wedding while bride usually wears in red in traditional Indian weddings? We design a brand new geo-diverse commonsense probing benchmark **GeoMLAMA** to evaluate model’s geo-diversity. 1/N Paper: wadeyin9712.github.io/files/emnlp202…
UCLA Chang's (@kaiwei_chang ) and Plus lab (@VioletNPeng) will present papers and a tutorial on topics including Fairness & Robustness, NLG, IE & QA, Multilinguality & Multimodality at #EMNLP2021. Details are at shorturl.at/imqOZ. #NLProc #UCLANLP (1/n)
Check out our new #EMNLP2021 paper on non-binary gender in NLP. I learned a lot from this diverse team, which brings in many new perspectives. Thank for the team and survey respondents, who make this happens.
🌈 Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies 🏳️⚧️ #EMNLP2021 paper w/ @sunipa17 @MMonajatipoor @ovalle_elia @probablyjeff @kaiwei_chang @uclanlp 👉 paper: arxiv.org/abs/2108.12084 👉 blog post: uclanlp.medium.com/harms-of-gende… 👇 🧵
🌈 Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies 🏳️⚧️ #EMNLP2021 paper w/ @sunipa17 @MMonajatipoor @ovalle_elia @probablyjeff @kaiwei_chang @uclanlp 👉 paper: arxiv.org/abs/2108.12084 👉 blog post: uclanlp.medium.com/harms-of-gende… 👇 🧵
Excited to share our NAACL paper Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions! arxiv.org/abs/2010.12831 We show that one could pre-train a V&L model on unaligned images and text with competitive performance as models trained on aligned data.
.@uclanlp is researching the harms of treating gender as binary in NLP tasks, as seen and experienced by non-binary folks. As part of this, we are conducting a participatory survey (forms.gle/BdScck4YBwYQXG…) of non-binary folks with any level of familiarity with AI.
United States Trends
- 1. Ole Miss 25,9 B posts
- 2. Indiana 57,1 B posts
- 3. Jaxson Dart 5.450 posts
- 4. Gators 15,1 B posts
- 5. Ohio State 37,6 B posts
- 6. Lane Kiffin 3.881 posts
- 7. Billy Napier 3.075 posts
- 8. Ryan Day N/A
- 9. Wayne 132 B posts
- 10. UMass 5.760 posts
- 11. Howard 25,5 B posts
- 12. Rutgers 4.340 posts
- 13. Lagway 7.038 posts
- 14. Buckeyes 12,5 B posts
- 15. Caleb Downs 7.782 posts
- 16. Surgeon General 163 B posts
- 17. Gerard Martin 21,3 B posts
- 18. Devin Neal N/A
- 19. Cignetti 5.773 posts
- 20. #GoBucks 7.920 posts
Who to follow
-
Yufei Tian @EMNLP
@yufei_t -
🌴Muhao Chen🌴
@muhao_chen -
Violet Peng
@VioletNPeng -
Kai-Wei Chang
@kaiwei_chang -
uclanlp
@uclanlp -
Zhe Zeng
@zhezeng0908 -
Kuan-Hao Huang
@kuanhaoh_ -
Chenghao Yang
@chrome1996 -
Yu (Hope) Hou
@houyu0930 -
Pei Zhou
@peizNLP -
Jieyu Zhao
@jieyuzhao11 -
Zhiting Hu
@ZhitingHu -
Da Yin (on job market)
@Wade_Yin9712 -
Shuyan Zhou
@shuyanzhxyc -
I-Hung Hsu
@IHung_Hsu
Something went wrong.
Something went wrong.