The emergence of Large Language Models (LLMs) has boosted performance and possibilities in various NLP tasks. While the usage of generative AI models like ChatGPT opens up new opportunities for several business use cases, their current tendency to hallucinate fake content strongly limits their applicability to document analysis, such as information retrieval from documents. In contrast, extractive language models like question answering (QA) or passage retrieval models guarantee query results to be found within the boundaries of an according context document, which makes them candidates for more reliable information extraction in productive environments of companies. In this work we propose an approach that uses and integrates extractive QA models for improved feature extraction of German business documents such as insurance reports or medical leaflets into a document analysis solution. We further show that fine-tuning existing German QA models boosts performance for tailored extraction tasks of complex linguistic features like damage cause explanations or descriptions of medication appearance, even with using only a small set of annotated data. Finally, we discuss the relevance of scoring metrics for evaluating information extraction tasks and deduce a combined metric from Levenshtein distance, F1-Score, Exact Match and ROUGE-L to mimic the assessment criteria from human experts.
相關內容
《計算機信息》雜志發表高質量的論文，擴大了運籌學和計算的范圍，尋求有關理論、方法、實驗、系統和應用方面的原創研究論文、新穎的調查和教程論文，以及描述新的和有用的軟件工具的論文。官網鏈接： ·
Graph Transformer
·
Analysis
·
圖
·
MoDELS
·
The Business Process Modeling Notation (BPMN) is a widely used standard notation for defining intra- and inter-organizational workflows. However, the informal description of the BPMN execution semantics leads to different interpretations of BPMN elements and difficulties in checking behavioral properties. In this article, we propose a formalization of the execution semantics of BPMN that, compared to existing approaches, covers more BPMN elements while also facilitating property checking. Our approach is based on a higher-order transformation from BPMN models to graph transformation systems. To show the capabilities of our approach, we implemented it as an open-source web-based tool.
In industrial applications, it is common to scan objects on a moving conveyor belt. If slice-wise 2D computed tomography (CT) measurements of the moving object are obtained we call it a sequential scanning geometry. In this case, each slice on its own does not carry sufficient information to reconstruct a useful tomographic image. Thus, here we propose the use of a Dimension reduced Kalman Filter to accumulate information between slices and allow for sufficiently accurate reconstructions for further assessment of the object. Additionally, we propose to use an unsupervised clustering approach known as Density Peak Advanced, to perform a segmentation and spot density anomalies in the internal structure of the reconstructed objects. We evaluate the method in a proof of concept study for the application of wood log scanning for the industrial sawing process, where the goal is to spot anomalies within the wood log to allow for optimal sawing patterns. Reconstruction and segmentation quality are evaluated from experimental measurement data for various scenarios of severely undersampled X-measurements. Results show clearly that an improvement in reconstruction quality can be obtained by employing the Dimension reduced Kalman Filter allowing to robustly obtain the segmented logs.
Graph Neural Networks (GNNs) are a broad class of connectionist models for graph processing. Recent studies have shown that GNNs can approximate any function on graphs, modulo the equivalence relation on graphs defined by the Weisfeiler--Lehman (WL) test. However, these results suffer from some limitations, both because they were derived using the Stone--Weierstrass theorem -- which is existential in nature, -- and because they assume that the target function to be approximated must be continuous. Furthermore, all current results are dedicated to graph classification/regression tasks, where the GNN must produce a single output for the whole graph, while also node classification/regression problems, in which an output is returned for each node, are very common. In this paper, we propose an alternative way to demonstrate the approximation capability of GNNs that overcomes these limitations. Indeed, we show that GNNs are universal approximators in probability for node classification/regression tasks, as they can approximate any measurable function that satisfies the 1--WL equivalence on nodes. The proposed theoretical framework allows the approximation of generic discontinuous target functions and also suggests the GNN architecture that can reach a desired approximation. In addition, we provide a bound on the number of the GNN layers required to achieve the desired degree of approximation, namely $2r-1$, where $r$ is the maximum number of nodes for the graphs in the domain.
Motivation: The abundance of gene flow in the Tree of Life challenges the notion that evolution can be represented with a fully bifurcating process, as this process cannot capture important biological realities like hybridization, introgression, or horizontal gene transfer. Coalescent-based network methods are increasingly popular, yet not scalable for big data, because they need to perform a heuristic search in the space of networks as well as numerical optimization that can be NP-hard. Results: Here, we introduce a novel method to reconstruct phylogenetic networks based on algebraic invariants. While there is a long tradition of using algebraic invariants in phylogenetics, our work is the first to define phylogenetic invariants on concordance factors (frequencies of 4-taxon splits in the input gene trees) to identify level-1 phylogenetic networks under the multispecies coalescent model. Our novel inference methodology is optimization-free as it only requires the evaluation of polynomial equations, and as such, it bypasses the traversal of network space, yielding a computational speed at least 10 times faster than the fastest-to-date network methods. We illustrate the accuracy and speed of our new method on a variety of simulated scenarios as well as in the estimation of a phylogenetic network for the genus Canis. Availability and Implementation: We implement our novel theory on an open-source publicly available Julia package PhyloDiamond.jl available at //github.com/solislemuslab/PhyloDiamond.jl with broad applicability within the evolutionary biology community. Contact:
Construction of a universal detector poses a crucial question: How can we most effectively train a model on a large mixture of datasets? The answer lies in learning dataset-specific features and ensembling their knowledge but do all this in a single model. Previous methods achieve this by having separate detection heads on a common backbone but that results in a significant increase in parameters. In this work, we present Mixture-of-Experts as a solution, highlighting that MoEs are much more than a scalability tool. We propose Dataset-Aware Mixture-of-Experts, DAMEX where we train the experts to become an `expert' of a dataset by learning to route each dataset tokens to its mapped expert. Experiments on Universal Object-Detection Benchmark show that we outperform the existing state-of-the-art by average +10.2 AP score and improve over our non-MoE baseline by average +2.0 AP score. We also observe consistent gains while mixing datasets with (1) limited availability, (2) disparate domains and (3) divergent label sets. Further, we qualitatively show that DAMEX is robust against expert representation collapse.
Pre-trained Large Language Models (LLMs) have shown success in a diverse set of language inference and understanding tasks. The pre-training stage of LLMs looks at a large corpus of raw textual data. The BabyLM shared task compares LLM pre-training to human language acquisition, where the number of tokens seen by 13-year-old kids is magnitudes smaller than the number of tokens seen by LLMs. In this work, we pre-train and evaluate LLMs on their ability to learn contextual word representations using roughly the same number of tokens as seen by children. We provide a strong set of baselines; with different architectures, evaluation of changes in performance across epochs, and reported pre-training metrics for the strict small and strict tracks of the task. We also try to loosely replicate the RoBERTa baseline given by the task organizers to observe the training robustness to hyperparameter selection and replicability. We provide the submission details to the strict and strict-small tracks in this report.
Compositional Data Analysis (CoDa) has gained popularity in recent years. This type of data consists of values from disjoint categories that sum up to a constant. Both Dirichlet regression and logistic-normal regression have become popular as CoDa analysis methods. However, fitting this kind of multivariate models presents challenges, especially when structured random effects are included in the model, such as temporal or spatial effects. To overcome these challenges, we propose the logistic-normal Dirichlet Model (LNDM). We seamlessly incorporate this approach into the R-INLA package, facilitating model fitting and model prediction within the framework of Latent Gaussian Models (LGMs). Moreover, we explore metrics like Deviance Information Criteria (DIC), Watanabe Akaike information criterion (WAIC), and cross-validation measure conditional predictive ordinate (CPO) for model selection in R-INLA for CoDa. Illustrating LNDM through a simple simulated example and with an ecological case study on Arabidopsis thaliana in the Iberian Peninsula, we underscore its potential as an effective tool for managing CoDa and large CoDa databases.
Accelerated life-tests (ALTs) are applied for inferring lifetime characteristics of highly reliable products. In particular, step-stress ALTs increase the stress level at which units under test are subject at certain pre-fixed times, thus accelerating product wear and inducing its failure. In some cases, due to cost or product nature constraints, continuous monitoring of devices is infeasible but the units are inspected for failures at particular inspection time points. In such setups, the ALT response is interval-censored. Furthermore, when a test unit fails, there are often more than one fatal cause for the failure, known as competing risks. In this paper, we assume that all competing risks are independent and follow an exponential distribution with scale parameter depending on the stress level. Under this setup, we present a family of robust estimators based on the density power divergence, including the classical maximum likelihood estimator as a particular case. We derive asymptotic and robustness properties of the MDPDE, showing its consistency for large samples. Based on these MDPDEs, estimates of the lifetime characteristics of the product as well as estimates of cause-specific lifetime characteristics have been developed. Direct, transformed and bootstrap confidence intervals for the mean lifetime to failure, reliability at a mission time, and distribution quantiles are proposed, and their performance is empirically compared through simulations. Besides, the performance of the MDPDE family has been examined through an extensive numerical study and the methods of inference discussed here are illustrated with a real-data example regarding electronic devices.
We combine the recent relaxation approach with multiderivative Runge-Kutta methods to preserve conservation or dissipation of entropy functionals for ordinary and partial differential equations. Relaxation methods are minor modifications of explicit and implicit schemes, requiring only the solution of a single scalar equation per time step in addition to the baseline scheme. We demonstrate the robustness of the resulting methods for a range of test problems including the 3D compressible Euler equations. In particular, we point out improved error growth rates for certain entropy-conservative problems including nonlinear dispersive wave equations.
Most sequence sketching methods work by selecting specific $k$-mers from sequences so that the similarity between two sequences can be estimated using only the sketches. Estimating sequence similarity is much faster using sketches than using sequence alignment, hence sketching methods are used to reduce the computational requirements of computational biology software packages. Applications using sketches often rely on properties of the $k$-mer selection procedure to ensure that using a sketch does not degrade the quality of the results compared with using sequence alignment. In particular the window guarantee ensures that no long region of the sequence goes unrepresented in the sketch. A sketching method with a window guarantee corresponds to a Decycling Set, aka an unavoidable sets of $k$-mers. Any long enough sequence must contain a $k$-mer from any decycling set (hence, it is unavoidable). Conversely, a decycling set defines a sketching method by selecting the $k$-mers from the set. Although current methods use one of a small number of sketching method families, the space of decycling sets is much larger, and largely unexplored. Finding decycling sets with desirable characteristics is a promising approach to discovering new sketching methods with improved performance (e.g., with small window guarantee). The Minimum Decycling Sets (MDSs) are of particular interest because of their small size. Only two algorithms, by Mykkeltveit and Champarnaud, are known to generate two particular MDSs, although there is a vast number of alternative MDSs. We provide a simple method that allows one to explore the space of MDSs and to find sets optimized for desirable properties. We give evidence that the Mykkeltveit sets are close to optimal regarding one particular property, the remaining path length.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191