paper-with-me

Papers

FastFusionNet: New State-of-the-Art for DAWNBench SQuAD

2019-02-28 · Felix Wu, Boyi Li, Lequn Wang, Ni Lao, John Blitzer, Kilian Q. Weinberger

In this technical report, we introduce FastFusionNet, an efficient variant of FusionNet [12]. FusionNet is a high performing reading comprehension architecture, which was designed primarily for maximum retrieval accuracy with less regard towards computational requirements. For FastFusionNets we remove the expensive CoVe layers [21] and substitute the BiLSTMs with far more efficient SRU layers [19]. The resulting architecture obtains state-of-the-art results on DAWNBench [5] while achieving the lowest training and inference time on SQuAD [25] to-date. The code is available at https://github.com/felixgwu/FastFusionNet.

📄 PDF Abstract BibTeX arXiv:1902.11291

Code (2)

felixgwu/FastFusionNet 공식 구현 pytorch
yellowpsyduck/OccamFusionNet pytorch

Tasks

Reading ComprehensionRetrieval

Methods 이 논문이 사용한 방법론

Highway Layer 설명 없음
SRU SRU, or Simple Recurrent Unit, is a recurrent neural unit with a light form of recurrence. SRU exhibits the same level of parallelism as…
Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
GloVe GloVe Embeddings are a type of word embedding that encode the co-occurrence probability ratio between two words as vector differences. GloVe uses a weighted least squares…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…
Location-based Attention 설명 없음

Similar Papers 제목 키워드 기반

Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark

2018-06-04 · Cody Coleman, Daniel Kang, Deepak Narayanan, Luigi Nardi 외

Researchers have proposed hardware, software, and algorithmic optimizations to improve the computational performance of deep learning. While some of these optimizations perform the same operations faster (e.g., increasin…

BenchmarkingBIG-bench Machine LearningGPU

Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates

2017-08-23 · Leslie N. Smith, Nicholay Topin

In this paper, we describe a phenomenon, which we named "super-convergence", where neural networks can be trained an order of magnitude faster than with standard training methods. The existence of super-convergence is re…

Know What You Don't Know: Unanswerable Questions for SQuAD

2018-06-11 · ACL 2018 7 · Pranav Rajpurkar, Robin Jia, Percy Liang

Extractive reading comprehension systems can often locate the correct answer to a question in a context document, but they also tend to make unreliable guesses on questions for which the correct answer is not stated in t…

Natural Language UnderstandingQuestion AnsweringReading Comprehension

The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models

2023-01-31 · Son Quoc Tran, Phong Nguyen-Thuan Do, Uyen Le, Matt Kretchmar

Pretrained language models have achieved super-human performances on many Machine Reading Comprehension (MRC) benchmarks. Nevertheless, their relative inability to defend against adversarial attacks has spurred skepticis…

Adversarial AttackMachine Reading ComprehensionNatural Language UnderstandingReading Comprehension

EQuANt (Enhanced Question Answer Network)

2019-06-24 · François-Xavier Aubet, Dominic Danks, Yuchen Zhu

Machine Reading Comprehension (MRC) is an important topic in the domain of automated question answering and in natural language processing more generally. Since the release of the SQuAD 1.1 and SQuAD 2 datasets, progress…

Machine Reading ComprehensionMulti-Task LearningQuestion AnsweringReading Comprehension