.png){kind=icon}
返回
Effective Subword Segmentation for Text Comprehension
.png){kind=icon}
OA
AI
DOI：10.1109/TASLP.2019.2922537.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to alleviate the problem of effectively representing rare or complex words. However, character itself is not a natural minimal linguistic unit for representation or word embedding composing due to ignoring the linguistic coherence of consecutive characters inside word. This paper presents a general subword-augmented embedding framework for learning and composing computationally derived subword-level representations. We survey a series of unsupervised segmentation methods for subword acquisition and different subword-augmented strategies for text understanding, showing that subword-augmented embedding significantly improves our baselines in various types of text understanding tasks on both English and Chinese benchmarks.
Keyword:
Subword embedding
machine reading comprehension
textual entailment
word segmentation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Characterization of the TRs/IRS origin of DNA replication of herpes simplex virus Type 1.png)
Virology
VirologyIF0
PREAI
分享收藏分享收藏Grafting improves tomato drought tolerance through enhancing photosynthetic capacity and reducing ROS accumulationProtoplasmaOAAI
ProtoplasmaIF0
OAAI分享收藏
查看更多内容