Hitachi at SemEval-2020 Task 10: Emphasis Distribution Fusion on Fine-Tuned Language Models

机译：日立Semeval-2020任务10：精细语言模型的重点分布融合

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

This paper shows our system for SemEval-2020 task 10, Emphasis Selection for Written Text in Visual Media. Our strategy is two-fold. First, we propose fine-tuning many pre-trained language models, predicting an emphasis probability distribution over tokens. Then, we propose stacking a trainable distribution fusion (DISTFUSE) system to fuse the predictions of the fine-tuned models. Experimental results show that DISTFUSE is comparable or better when compared with a naive average ensemble. As a result, we were ranked 2nd amongst 31 teams.

机译：本文显示了Semeval-2020任务10的系统，重点选择了视觉媒体中的书面文本。我们的策略是两倍。首先，我们提出微调许多预训练的语言模型，预测了令牌的强调概率分布。然后，我们建议堆叠培训分配融合（Distfuse）系统以融合微调模型的预测。实验结果表明，与天真的平均集合相比，Distfuse是可比的或更好的。结果，我们在31支球队中排名第二。

著录项

来源
《International Workshop on Semantic Evaluation》|2020年|1658-1664|共7页
会议地点
作者
Gaku Morio; Terufumi Morishita; Hiroaki Ozaki; Toshinori Miyoshi;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词

相似文献

外文文献
中文文献
专利

1. Differential contribution of task conflicts to task switch cost and task mixing cost in alternating runs and cued task-switching: evidence from ex-Gaussian modeling of reaction time distributions [J] . Shahar Nitzan, Meiran Nachshon Psychological research . 2015,第2期

机译：在交替运行和提示任务切换中任务冲突对任务切换成本和任务混合成本的差异贡献：来自前高斯反应时间分布模型的证据
2. Fusion with the cold-active esterase facilitates autotransporter-based surface display of the 10th human fibronectin domain in Escherichia coli [J] . L. E. Petrovskaya, A. V. Zlobinov, L. N. Shingarova, Extremophiles: Life under extreme conditions . 2018,第1期

机译：与冷活性酯酶的融合有助于在<重点型=“斜体”>大肠杆菌中的第10人纤连蛋白结构域的基于自耦基础的表面显示器>大肠杆菌
3. Modeling and forecasting exchange rate volatility in Bangladesh using GARCH models: a comparison based on normal and Student’s t-error distribution [J] . S. M. Abdullah, Salina Siddiqua, Muhammad Shahadat Hossain Siddiquee, Financial Innovation . 2017,第1期

机译：使用GARCH模型对孟加拉国的汇率波动进行建模和预测：基于正态和学生的 t -误差分布的比较
4. ERNIE at SemEval-2020 Task 10: Learning Word Emphasis Selection by Pre-trained Language Model [C] . Zhengjie Huang, Shikun Feng, Weiyue Su, International Workshop on Semantic Evaluation . 2020

机译：Ernie在Semeval-2020任务10：学习单词强调预先训练的语言模型选择
5. Distribution patterns of genetic variation across landscapes at multiple scales: Empirical and modelling approaches with organisms from 10(-6) to .10 meters in size. [D] . Oline, David Kirk. 2001

机译：遗传多样性在多种尺度上的分布模式：使用10（-6）到0.1米大小的生物的经验和建模方法。
6. Reply to Lewis et al.: Inference is key to learning appearance from language for humans and distributional semantic models alike [O] . Judy S. Kim, Giulia V. Elli, Marina Bedny 2019

机译：回复Lewis等人：对于人类和分布语义模型而言推理是从语言中学习外观的关键
7. Microwave generation for magnetic fusion energy applications: Task A -- Experimental and numerical study of microwave sources for ECRH incorporating depressed collectors and with ITER-relevant parameters, and Task B -- Theory and modeling of high frequency, high power gyrotron operation. Final report, July 15, 1994--July 14, 1995 [O] . 1995

机译：用于磁聚变能量应用的微波产生：任务a-用于ECRH的微波源的实验和数值研究，其包括凹陷收集器和ITER相关参数，以及任务B-高频，高功率回旋管操作的理论和建模。最终报告，1994年7月15日 - 1995年7月14日

Hitachi at SemEval-2020 Task 10: Emphasis Distribution Fusion on Fine-Tuned Language Models

摘要

著录项

相似文献

相关主题

期刊订阅