NLP Power

The First Workshop on Efficient Benchmarking in NLP.

Workshop Programme

Main page

26 May 2022, co-located with ACL, Dublin, Ireland + online

THe program of the workshop will happen within the Ireland timezone (GMT), which means in between 8am and 7pm GMT.

Start time End time Title
09:00:00 09:10:00 Opening remarks
09:10:00 09:30:00 Raison d’être of the benchmark dataset: A Survey of Current Practices of Benchmark Dataset Sharing Platforms
09:30:00 09:50:00 Checking HateCheck: a cross-functional analysis of behaviour-aware learning for hate speech detection
09:50:00 10:10:00 Beyond Static models and test sets: Benchmarking the potential of pre-trained models across tasks and languages
10:10:00 10:30:00 Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP Models
10:30:00 11:00:00 Coffee break
11:00:00 11:40:00 Poster Session (gathertown)
11:40:00 12:00:00 Why only Micro-$F_1$? Class Weighting of Measures for Relation Classification
12:00:00 12:20:00 ACL Findings: Revisiting Automatic Evaluation of Extractive Summarization Task: Can We Do Better than ROUGE?
12:30:00 14:00:00 Lunch break
14:00:00 15:00:00 Invited Talk 1: He He
15:00:00 15:30:00 Coffee break
15:30:00 16:10:00 Invited Talk 2: Ulises Mejias
16:10:00 16:50:00 Invited Talk 3: Anna Rumshisky
16:50:00 17:50:00 Round Table: Beyond GLUE
17:50:00 18:00:00 Closing remarks

NLP Power workshop will be held in a hybrid format. All plenary sessions will be held (either livestreamed or broadcasted) in Zoom and followed by a live Q&A (unless the schedule indicates otherwise). Questions can be asked in the Zoom chat during the presentations. Poster sessions will be held in Gather.town.

The links to the zoom session and Gather.town space can be found on the conference page of the workshop (only accessible with conference registration).