15 papers · ranked by Valyu relevance
Halil Kilicoglu, Dina Demner-Fushman, Tudor Groza
Coreference resolution is one of the fundamental and challenging tasks in natural language processing. Resolving coreference successfully can have a significant positive effect on downstream natural language processing tasks, such as information extraction and question answering. The importance of coreference…
Nicole Bidoít, Dario Colazzo, Federico Ulliana
This paper presents a novel static analysis technique to detect XML query-update independence, in the presence of a schema. Rather than types, our system infers chains of types. Each chain represents a path that can be traversed on a valid document during query/update evaluation. The resulting independence analysis is…
Thomas Lavergne, Cyril Grouin, Pierre Zweigenbaum
Background The acquisition of knowledge about relations between bacteria and their locations (habitats and geographical locations) in short texts about bacteria, as defined in the BioNLP-ST 2013 Bacteria Biotope task, depends on the detection of co-reference links between mentions of entities of each of these three…
Ping Chen, David Hinote, Guoqing Chen
Materials and Methods: Experiment materials used in this study is provided by the 2011 i2b2 Natural Language Processing Challenge. The 2011 i2b2 challenge involves coreference resolution in medical documents. Concept mentions have been annotated in clinical texts, and the mentions that co-refer in each document are to…
Hannah S. Sarvasy, Soonja Choi
Clause chains are a special type of complex sentence, found in hundreds of languages outside Western Europe, in which clauses are dependent but not embedded, and dozens of clauses can be combined into a single sentential unit. Unlike English complex sentences, clause chains’ distribution is partially predictable in…
Nils Küchenmeister, Alex Ivliev, Dörthe Arndt, Markus Krötzsch
Combining RDF rule languages, such as N3 or SHACL Rules, with default negation is challenging. Existing methods to stratify negation often fail for RDF rules, since individual triples do not carry enough information to meaningfully restrict potential dependencies. Blank nodes in rule heads further complicate the…
Mante S. Nieuwland, Andrea E. Martin
The ability to use words to refer to the world is vital to the communicative power of human language. In particular, the anaphoric use of words to refer to previously mentioned concepts (antecedents) allows dialogue to be coherent and meaningful. Psycholinguistic theory posits that anaphor comprehension involves…
Kouji Kozaki, Yuki Yamagata, Riichiro Mizoguchi, Takeshi Imai + 1 more
'Kazuhiko Ohe'] Background Medical ontologies are expected to contribute to the effective use of medical information resources that store considerable amount of data. In this study, we focused on disease ontology because the complicated mechanisms of diseases are related to concepts across various medical domains. The…
Paul Anderson, Damon Lin, Jean Davidson, Theresa Migler + 10 more
Link prediction and entity resolution play pivotal roles in uncovering hidden relationships within networks and ensuring data quality in the era of heterogeneous data integration. This paper explores the utilization of large language models to enhance link prediction, particularly through knowledge graphs derived from…
Douglas Summers-Stay
Representing knowledge as high-dimensional vectors in a continuous semantic vector space can help overcome the brittleness and incompleteness of traditional knowledge bases. We present a method for performing deductive reasoning directly in such a vector space, combining analogy, association, and deduction in a…
Parosh Aziz Abdulla, Mohamed Faouzi Atig Bui Phi Diep, Lukáš Holík, Petr Janků
'Petr Janků'] Abstract. We address the satisfiability problem for string constraints that combine relational constraints represented by transducers, word equations, and string length constraints. This problem is undecidable in general. Therefore, we propose a new decidable fragment of string constraints, called weakly…
Huajun Chen, Xi Chen, Peiqin Gu, Zhaohui Wu + 1 more
Recently, huge amounts of data are generated in the domain of biology. Embedded with domain knowledge from different disciplines, the isolated biological resources are implicitly connected. Thus it has shaped a big network of versatile biological knowledge. Faced with such massive, disparate, and interlinked biological…
Shanshan Zhu, Wenjin Yan, Hu Chuan-Peng
Self-referential processing is a fundamental cognitive function, and abnormalities in its neural implementation have been reported across a range of psychiatric disorders, leading to the proposal that such alterations may constitute a transdiagnostic neurobiological feature. Yet claiming transdiagnostic requires…
Emily Bruns, Immanuel Scholz, Georgia Koppe, Peter Kirsch + 1 more
Belief processing as well as self-referential processing have both been consistently associated with cortical midline structures. In addition, seminal neuroimaging papers have implicated cortical regions such as the vmPFC in general belief processing. However, the neural correlates of self-referential belief are yet to…
Authors not listed
Sequence is the critical determinant of macromolecular function, yet current polymer design approaches often optimize monomer composition and ratios while ignoring sequence. This creates poorly defined design spaces for active learning that miss the vast combinatorial landscape of sequence possibilities. We introduce…