Abstract:The task of Fine-grained Entity Type Classification (FETC) consists of assigning types from a hierarchy to entity mentions in text. Existing methods rely on distant supervision and are thus susceptible to noisy labels that can be out-of-context or overly-specific for the training sentence. Previous methods that attempt to address these issues do so with heuristics or with the help of hand-crafted features. Instead, we propose an end-to-end solution with a neural network model that uses a variant of crossentrop… Show more
“…Ren et al [10] designed a novel partial-label loss to further reduce the label noise. Moreover, Xu et al [22] introduced a method of normalization of hierarchical loss to reduce specific types of noise. A recent study [23] introduced a penalty term in the optimization process to effectively diminish the side effect of the label noise and confirmation bias.…”
Section: A Distant Supervision-based Methodsmentioning
“…Ren et al [10] designed a novel partial-label loss to further reduce the label noise. Moreover, Xu et al [22] introduced a method of normalization of hierarchical loss to reduce specific types of noise. A recent study [23] introduced a penalty term in the optimization process to effectively diminish the side effect of the label noise and confirmation bias.…”
Section: A Distant Supervision-based Methodsmentioning
“…Existing work on FGET focuses on performing context-sensitive typing (Gillick et al, 2014;Corro et al, 2015), learning from noisy training data (Abhishek et al, 2017;Ren et al, 2016;Xu and Barbosa, 2018), and exploiting the type hierarchies to improve the learning and inference (Yogatama et al, 2015;Murty et al, 2018). More recent studies support even finer granularity (Choi et al, 2018;Murty et al, 2018).…”
Fine-grained Entity typing (FGET) is the task of assigning a fine-grained type from a hierarchy to entity mentions in the text. As the taxonomy of types evolves continuously, it is desirable for an entity typing system to be able to recognize novel types without additional training. This work proposes a zero-shot entity typing approach that utilizes the type description available from Wikipedia to build a distributed semantic representation of the types. During training, our system learns to align the entity mentions and their corresponding type representations on the known types. At test time, any new type can be incorporated into the system given its Wikipedia descriptions. We evaluate our approach on FIGER, a public benchmark entity tying dataset. Because the existing test set of FIGER covers only a small portion of the fine-grained types, we create a new test set by manually annotating a portion of the noisy training data. Our experiments demonstrate the effectiveness of the proposed method in recognizing novel types that are not present in the training data.
“…Shimaoka et al (2017) encode the hierarchy through a sparse matrix. Xu and Barbosa (2018) model the relations through a hierarchy-aware loss function. Ma et al (2016) and Abhishek et al (2017) learn embeddings for labels and feature representations into a joint space in order to facilitate information sharing among them.…”
How can we represent hierarchical information present in large type inventories for entity typing? We study the ability of hyperbolic embeddings to capture hierarchical relations between mentions in context and their target types in a shared vector space. We evaluate on two datasets and investigate two different techniques for creating a large hierarchical entity type inventory: from an expert-generated ontology and by automatically mining type co-occurrences. We find that the hyperbolic model yields improvements over its Euclidean counterpart in some, but not all cases. Our analysis suggests that the adequacy of this geometry depends on the granularity of the type inventory and the way hierarchical relations are inferred. 1
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.