We describe a transfer method based on annotation projection to develop a
dependency-based semantic role labeling system for languages for which no
supervised linguistic information other than parallel data is available. Unlike
previous work that presumes the availability of supervised features such as
lemmas, part-of-speech tags, and dependency parse trees, we only make use of
word and character features. Our deep model considers using character-based
representations as well as unsupervised stem embeddings to alleviate the need
for supervised features. Our experiments outperform a state-of-the-art method
that uses supervised lexico-syntactic features on 6 out of 7 languages in the
Universal Proposition Bank.

使用基于注释投影的转移方法，开发了一种基于依赖关系的语义角色标注系统，在只有平行数据可用的语言中，不需要其他监督的语言信息。相比之前的工作，我们只使用了词和字符特征来避免使用监督的特征。我们的深度模型考虑使用基于字符的表示以及无监督的词干嵌入来减轻对监督特征的需求。我们的实验在通用命题库的 7 种语言中有 6 种优于使用监督词汇 - 句法特征的最先进方法。

语义角色跨语言转移：从原始文本到语义角色

Cross-Lingual Transfer of Semantic Roles: From Raw Text to Semantic  Roles

In this paper, we propose a new method called ProfWeight for transferring
information from a pre-trained deep neural network that has a high test
accuracy to a simpler interpretable model or a very shallow network of low
complexity and a priori low test accuracy. We are motivated by applications in
interpretability and model deployment in severely memory constrained
environments (like sensors). Our method uses linear probes to generate
confidence scores through flattened intermediate representations. Our transfer
method involves a theoretically justified weighting of samples during the
training of the simple model using confidence scores of these intermediate
layers. The value of our method is first demonstrated on CIFAR-10, where our
weighting method significantly improves (3-4%) networks with only a fraction of
the number of Resnet blocks of a complex Resnet model. We further demonstrate
operationally significant results on a real manufacturing problem, where we
dramatically increase the test accuracy of a CART model (the domain standard)
by roughly 13%.

本文提出一种名为 ProfWeight 的新方法，用于从预训练的深度神经网络向一个较简单的可解释模型或低计算复杂度的浅层网络中传输信息，该方法使用线性探针通过展开的中间表示生成置信度分数，并在训练简单模型时使用这些中间层的置信度分数进行加权。该方法已在 CIFAR-10 和一个真实制造问题中证明了其价值。

使用置信度配置优化简单模型

Improving Simple Models with Confidence Profiles

Our paper addresses the problem of annotation projection for semantic role
labeling for resource-poor languages using supervised annotations from a
resource-rich language through parallel data. We propose a transfer method that
employs information from source and target syntactic dependencies as well as
word alignment density to improve the quality of an iterative bootstrapping
method. Our experiments yield a $3.5$ absolute labeled F-score improvement over
a standard annotation projection method.

本文探讨使用平行数据从资源丰富语言的监督注释中进行语义角色标注的注释投影问题，并提出了一种转移方法来提高迭代自启动方法的质量。实验结果表明，与标准注释投影方法相比，我们的方法可以获得 3.5 个绝对标记 F 分数的提高。