Approach to automatic population of ontologies of scientific subject domain using lexico-syntactic patterns

This paper presents an approach to automatic population of ontologies of a scientific subject domain (SSD) using Lexico-Syntactic Patterns (LSPs) and a corpus of texts related to modeled domain. The main feature of this approach is that such patterns are automatically built based on Ontology Design Patterns of other types provided by the system for the automated development of SSD ontologies using heterogeneous Ontology Design Patterns. The implementation of the ontology population using constructed LSPs is described in detail. The results of the experiments on the SSD ontology population are presented. It is noted that there is a problem in establishing a subject of a relation when extracting facts. To address this problem, the authors are planning to employ the coreference resolution methods.

DEEP LEARNING FOR SEMANTIC MATCHING: A SURVEY

Semantic matching finds certain types of semantic relationships among schema/data constructs. Examples include entity matching, entity linking, coreference resolution, schema/ontology matching, semantic text similarity, textual entailment, question answering, tagging, etc. Semantic matching has received much attention in the database, AI, KDD, Web, and Semantic Web communities. Recently, many works have also applied deep learning (DL) to semantic matching. In this paper we survey this fast growing topic. We define the semantic matching problem, categorize its variations into a taxonomy, and describe important applications. We describe DL solutions for important variations of semantic matching. Finally, we discuss future R\&D directions.

Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias throughout the Machine Learning Lifecyle

Correctly resolving textual mentions of people fundamentally entails making inferences about those people. Such inferences raise the risk of systematic biases in coreference resolution systems, including biases that can harm binary and non-binary trans and cis stakeholders. To better understand such biases, we foreground nuanced conceptualizations of gender from sociology and sociolinguistics, and investigate where in the machine learning pipeline such biases can enter a coreference resolution system. We inspect many existing datasets for trans-exclusionary biases, and develop two new datasets for interrogating bias in both crowd annotations and in existing coreference resolution systems. Through these studies, conducted on English text, we confirm that without acknowledging and building systems that recognize the complexity of gender, we will build systems that fail for: quality of service, stereotyping, and over- or under-representation, especially for binary and non-binary trans users.

Generalizing Cross-Document Event Coreference Resolution Across Multiple Corpora

Cross-document event coreference resolution (CDCR) is an NLP task in which mentions of events need to be identified and clustered throughout a collection of documents. CDCR aims to benefit downstream multi-document applications, but despite recent progress on corpora and system development, downstream improvements from applying CDCR have not been shown yet. We make the observation that every CDCR system to date was developed, trained, and tested only on a single respective corpus. This raises strong concerns on their generalizability — a must-have for downstream applications where the magnitude of domains or event mentions is likely to exceed those found in a curated corpus. To investigate this assumption, we define a uniform evaluation setup involving three CDCR corpora: ECB+, the Gun Violence Corpus and the Football Coreference Corpus (which we reannotate on token level to make our analysis possible). We compare a corpus-independent, feature-based system against a recent neural system developed for ECB+. Whilst being inferior in absolute numbers, the feature-based system shows more consistent performance across all corpora whereas the neural system is hit-and-miss. Via model introspection, we find that the importance of event actions, event time, etc. for resolving coreference in practice varies greatly between the corpora. Additional analysis shows that several systems overfit on the structure of the ECB+ corpus. We conclude with recommendations on how to achieve generally applicable CDCR systems in the future — the most important being that evaluation on multiple CDCR corpora is strongly necessary. To facilitate future research, we release our dataset, annotation guidelines, and system implementation to the public.