| Home | << 1 >> |
|
Atkinson, J., & Escudero, A. (2022). Evolutionary natural-language coreference resolution for sentiment analysis. Int. J. Inf. Manage. Data Insights, 2(2), 100115.
Abstract: Communicating messages on social media usually conveys much implicit linguistic knowledge, which makes it difficult to process texts for further analysis. One of the major problems, the linguistic coreference resolution task involves detecting coreference chains of entities and pronouns that coreference them. It has mostly been addressed for formal and full-sized text in which a relatively clear discourse structure can be discovered, using Natural-Language Processing techniques. However, texts in social media are short, informal and lack a lot of underlying linguistic information to make decisions so traditional methods can not be applied. Furthermore, this may significantly impact the performance of several tasks on social media applications such as opinion mining, network analysis, sentiment analysis, text categorization. In order to deal with these issues, this research address the task of linguistic co-referencing using an evolutionary computation approach. It combines discourse coreference analysis techniques, domain-based heuristics (i.e., syntactic, semantic and world knowledge), graph representation methods, and evolutionary computation algorithms to resolving implicit co-referencing within informal opinion texts. Experiments were conducted to assess the ability of the model to find implicit referents on informal messages, showing the promise of our approach when compared to related methods.
|
|
Gregor, C., Ashlock, D., Ruz, G. A., MacKinnon, D., & Kribs, D. (2022). A novel linear representation for evolving matrices. Soft Comput., 26(14), 6645–6657.
Abstract: A number of problems from specifiers for Boolean networks to programs for quantum computers can be encoded as matrices. The paper presents a novel family of linear, generative representations for evolving matrices. The matrices can be general or restricted within special classes of matrices like permutation matrices, Hermitian matrices, or other groups of matrices with particular algebraic properties. These classes include unitary matrices which encode quantum programs. This representation avoids the brittleness that arises in direct representations of matrices and permits the researcher substantial control of the part of matrix space being searched. The representation is demonstrated on a relatively simple matrix problem in automatic content generation as well as Boolean map induction and automatic quantum programming. The automatic content generation problem yields interesting results; the generative matrix representation yields worse fitness but a substantially greater variety of outcomes than a direct encoding, which is acceptable when generating content. The Boolean map experiments extend and confirm results that demonstrate that the generative encoding is superior to a direct encoding for the transition matrix of a Boolean map. The quantum programming results are generally quite good, with poor performance on the simplest problems in two of the families of programming tasks studied. The viability of the new representation for evolutionary matrix induction is well supported.
|
|
Travisany, D., Goles, E., Latorre, M., Cort?s, M. P., & Maass, A. (2020). Generation and robustness of Boolean networks to model Clostridium difficile infection. Nat. Comput., 19(1), 111–134.
Abstract: One of the more common healthcare associated infection is Chronic diarrhea. This disease is caused by the bacterium Clostridium difficile which alters the normal composition of the human gut flora. The most successful therapy against this infection is the fecal microbial transplant (FMT). They displace C. difficile and contribute to gut microbiome resilience, stability and prevent further episodes of diarrhea. The microorganisms in the FMT their interactions and inner dynamics reshape the gut microbiome to a healthy state. Even though microbial interactions play a key role in the development of the disease, currently, little is known about their dynamics and properties. In this context, a Boolean network model for C. difficile infection (CDI) describing one set of possible interactions was recently presented. To further explore the space of possible microbial interactions, we propose the construction of a neutral space conformed by a set of models that differ in their interactions, but share the final community states of the gut microbiome under antibiotic perturbation and CDI. To begin with the analysis, we use the previously described Boolean network model and we demonstrate that this model is in fact a threshold Boolean network (TBN). Once the TBN model is set, we generate and use an evolutionary algorithm to explore to identify alternative TBNs. We organize the resulting TBNs into clusters that share similar dynamic behaviors. For each cluster, the associated neutral graph is constructed and the most relevant interactions are identified. Finally, we discuss how these interactions can either affect or prevent CDI.
|