按年被提到
20162016 · 4 次2026
大模型与语言模型›序列模型与注意力机制·arXiv:1603.06042 · cs.CL

Globally Normalized Transition-Based Neural Networks

Daniel Andor, Chris Alberti, David Weiss, Aliaksei Severyn, Alessandro Presta, Kuzman Ganchev, Slav Petrov, Michael Collins · 2016
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 4 人首次 2016-05-12 · 最近 2016-06-15
4不同的人
2活跃月份
3讨论串
494被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We introduce a globally normalized transition-based neural network model that achieves state-of-the-art part-of-speech tagging, dependency parsing and sentence compression results. Our model is a simple feed-forward neural network that operates on a task-specific transition system, yet achieves comparable or better accuracies than recurrent models. We discuss the importance of global as opposed to local normalization: a key insight is that the label bias problem implies that globally normalized models can be strictly more expressive than locally normalized models.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论xigency · 2016-05

“Evidence that this is the most accurate parser is here; the previous approach mentioned is a March 2016 paper, "Globally Normalized Transition-Based Neural Networks," http://arxiv.org/abs/1603.06042 "On a standard benchmark consisting of randomly drawn English newswire sentences (the 20 year old Penn Treebank), Parsey McParseface recovers individual depe…”

Announcing SyntaxNet: The World’s Most Accurate Natural Language Parser原评论 ↗
评论the_decider · 2016-05

“According to their paper (http://arxiv.org/pdf/1603.06042v1.pdf), the technique can also be applied to sentence compression. It would be cool if Google publishes that example code/training-data as well.”

Announcing SyntaxNet: The World’s Most Accurate Natural Language Parser原评论 ↗
评论vagabondvector · 2016-05

“http://arxiv.org/abs/1603.06042 this is the paper. the idea is based on the incredible incremental perceptron coupled with beam search for having different hypotheses at the same time trying to find a policy which will build them and select the best one http://dl.acm.org/citation.cfm?id=1218970 The approach to structured prediction that was the fastes…”

SyntaxNet: Neural Models of Syntax原评论 ↗
评论supercarrot · 2016-06

“Still, beam search can be simulated and improved by running decision processes in parallel. For example, instead of learning the sequence labeling as a sequence of n decisions (where n is the length of the sequence) you can learn sequence labeling as a sequence of 3n+1 decisions where you make 3 decisions for each sequence element and after 3n decision p…”

Intro to Hidden Markov Models (2010) [pdf]原评论 ↗