SCIIE benefits from expressive contextualized span representations as classifier features. By sharing span representations, sentence-level tasks can benefit from information propagated from coreference resolution across sentences, without increasing the complexity of inference. Figure 2 shows a high-level overview of the SCIIE multi-task framework.
这一段还是说到了用了contextualized span representations。
We use the same span representations g from (Lee et al., 2017) and share them across the three
tasks. We start by building bi-directional LSTMs (Hochreiter and Schmidhuber, 1997) from word, character and ELMo (Peters et al., 2018) embeddings.
For a span si , its vector representation gi is constructed by concatenating si’s left and right end
points from the BiLSTM outputs, an attentionbased soft “headword,” and embedded span width
features. Hyperparameters and other implementation details will be described in Section 6.
一句话总结:
只做了一个叫做SCIERC的数据集,用于进行entities, relations, and coreference clusters这三个task,最终目的是为了构建KG。
资源:
论文信息:
笔记:
本来是打算找将ELMo用于context learning,然后构建复杂classifier的例子的,结果这篇没什么特别大关系。但是还挺有意思的,直接通过multi-task来构筑KG。
4 Model
SCIIE benefits from expressive contextualized span representations as classifier features. By sharing span representations, sentence-level tasks can benefit from information propagated from coreference resolution across sentences, without increasing the complexity of inference. Figure 2 shows a high-level overview of the SCIIE multi-task framework.
这一段还是说到了用了contextualized span representations。
We use the same span representations g from (Lee et al., 2017) and share them across the three tasks. We start by building bi-directional LSTMs (Hochreiter and Schmidhuber, 1997) from word, character and ELMo (Peters et al., 2018) embeddings.
For a span si , its vector representation gi is constructed by concatenating si’s left and right end points from the BiLSTM outputs, an attentionbased soft “headword,” and embedded span width features. Hyperparameters and other implementation details will be described in Section 6.
这两段说了 contextualized span representations是由好几部分组成的,bi-LSTMs,character, ELMo这三种
模型图:
结果:
接下来要看的论文: