paper-with-me

홈 › Papers

Benchmarking: Past, Present and Future

2021-08-01 · ACL (BPPF) 2021 8 · Kenneth Church, Mark Liberman, Valia Kordoni

Where have we been, and where are we going? It is easier to talk about the past than the future. These days, benchmarks evolve more bottom up (such as papers with code). There used to be more top-down leadership from government (and industry, in the case of systems, with benchmarks such as SPEC). Going forward, there may be more top-down leadership from organizations like MLPerf and/or influencers like David Ferrucci, who was responsible for IBM’s success with Jeopardy, and has recently written a paper suggesting how the community should think about benchmarking for machine comprehension. Tasks such as reading comprehension become even more interesting as we move beyond English. Multilinguality introduces many challenges, and even more opportunities.

📄 PDF Abstract BibTeX

Code (1)

kwchurch/benchmarking_past_present_future 공식 구현

Tasks

BenchmarkingReading Comprehension

Similar Papers 제목 키워드 기반

Bench to the Future: A Pastcasting Benchmark for Forecasting Agents

2025-06-11 · FutureSearch, :, Jack Wildman, Nikos I. Bosse 외

Forecasting is a challenging task that offers a clearly measurable way to study AI systems. Forecasting requires a large amount of research on the internet, and evaluations require time for events to happen, making the d…

Benchmarking

On Evaluation of Embodied Navigation Agents

2018-07-18 · Peter Anderson, Angel Chang, Devendra Singh Chaplot, Alexey Dosovitskiy 외

Skillful mobile operation in three-dimensional environments is a primary topic of study in Artificial Intelligence. The past two years have seen a surge of creative work on navigation. This creative output has produced a…

Benchmarking

Align and Distill: Unifying and Improving Domain Adaptive Object Detection

2024-03-18 · Justin Kay, Timm Haucke, Suzanne Stathatos, Siqi Deng 외

Object detectors often perform poorly on data that differs from their training set. Domain adaptive object detection (DAOD) methods have recently demonstrated strong results on addressing this challenge. Unfortunately, w…

Benchmarkingobject-detectionObject DetectionUnsupervised Domain Adaptation

Towards Reproducibility in Predictive Process Mining: SPICE -- A Deep Learning Library

2025-12-18 · Oliver Stritzel, Nick Hühnerbein, Simon Rauch, Itzel Zarate 외 arxiv

In recent years, Predictive Process Mining (PPM) techniques based on artificial neural networks have evolved as a method for monitoring the future behavior of unfolding business processes and predicting Key Performance I…

Decision Making

The Elusive Present: Hidden Past and Future Dependency and Why We Build Models

2015-07-02 · Pooneh M. Ara, Ryan G. James, James P. Crutchfield

Modeling a temporal process as if it is Markovian assumes the present encodes all of the process's history. When this occurs, the present captures all of the dependency between past and future. We recently showed that if…