Multi-Task Learning of Keyphrase Boundary Classification

By Isabelle Augenstein, Anders Søgaard. 2017

73 citations recorded by the source corpus.

Keyphrase boundary classification (KBC) is the task of detecting keyphrases in scientific articles and labelling them with respect to predefined types. Although important in practice, this task is so far underexplored, partly due to the lack of labelled data. To overcome this, we explore several auxiliary tasks, including semantic super-sense tagging and identification of multi-word expressions, and cast the task as a multi-task learning problem with deep recurrent neural networks. Our multi-task models perform significantly better than previous state of the art approaches on two scientific KBC datasets, particularly for long keyphrases.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Semi-supervised Multitask Learning for Sequence Labeling (2017, methodology): “While predicting word frequency can be useful for POS-tagging, language modeling provides a more general training signal, allowing us to apply the model to many different Recently, Augenstein and Søgaard (2017) explored multi-task learning for classifying keyphrase boundaries, by incorporating tasks”
Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction (2018, methodology): “Using these datasets, neural models (Ammar et al., 2017, 2018; Luan et al., 2017b; Augenstein and Søgaard, 2017) are introduced for extracting scientific information.”
SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications (2017, background): “Furthermore, we expect the task to be interesting for researchers studying tasks aiming at understanding scientific content, such as keyphrase extraction (Kim et al., 2010b; Hasan and Ng, 2014; Sterckx et al., 2016; Augenstein and Søgaard, 2017), semantic relation extraction (Tateisi et al.”
A Supervised Approach to Extractive Summarisation of Scientific Papers (2017, background): “tion community, for other tasks in the space of automatically understand scientific publications, such as keyphrase extraction (Kim et al., 2010; Sterckx et al., 2016; Augenstein et al., 2017; Augenstein and Søgaard, 2017), semantic relation extraction (Gupta and Manning, 2011; Marsi and”