Automatic Gloss Finding for a Knowledge Base using Ontological Constraints

Abstract

While there has been much research on automatically constructing structured Knowledge Bases (KBs), most of it has focused on generating facts to populate a KB. However, a useful KB must go beyond facts. For example, glosses (short natural language definitions) have been found to be very useful in tasks such as Word Sense Disambiguation. However, the important problem of Automatic Gloss Finding, i.e., assigning glosses to entities in an initially gloss-free KB, is relatively unexplored. We address that gap in this paper. In particular, we propose GLOFIN, a hierarchical semi-supervised learning algorithm for this problem which makes effective use of limited amounts of supervision and available ontological constraints. To the best of our knowledge, GLOFIN is the first system for this task.Through extensive experiments on real-world datasets, we demonstrate GLOFIN's effectiveness. It is encouraging to see that GLOFIN outperforms other state-of-the-art SSL algorithms, especially in low supervision settings. We also demonstrate GLOFIN's robustness to noise through experiments on a wide variety of KBs, ranging from user contributed (e.g., Freebase) to automatically constructed (e.g., NELL). To facilitate further research in this area, we have made the datasets and code used in this paper publicly available.

A New Approach to Ontology-Based Semantic Modelling for Opinion Mining

“…key concepts and their synonyms and ground facts, as well as the relation between them [5]. Such domain knowledge can be utilised to improve the processes of opinion mining process.…”

Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking

“…Our structural, hierarchy-aware loss between types and entities draws on research in Knowledge Base Inference such as Jain et al (2018), Trouillon et al (2016) and Nickel et al (2011). Combining KB completion with hierarchical structure in knowledge bases has been explored in (Dalvi et al, 2015;Xie et al, 2016). Recently, Wu et al (2017) proposed a hierarchical loss for text classification.…”

SenseDefs: a multilingual corpus of semantically annotated textual definitions

“…However, as new encyclopedic knowledge about the world is constantly being harvested, keeping up using only human annotation is becoming an increasingly expensive endeavor. With a view to tackling this problem, a great deal of research has recently focused on the automatic extraction of definitions from unstructured text (Navigli and Velardi 2010;Benedictis et al 2013;Espinosa-Anke and Saggion 2014;Dalvi et al 2015). At the same time, the prominent role of collaborative resources (Hovy et al 2013) has created a convenient development ground for NLP systems based on encyclopedic definitional knowledge.…”