Search

We present the TRIAGE Benchmark, a novel machine ethics (ME) benchmark that tests LLMs' ability to make ethical decisions during mass casualty incidents. It uses real-world ethical dilemmas with clear solutions designed by medical professionals, offering a more realistic alternative to annotation-based benchmarks. TRIAGE incorporates various prompting styles to evaluate model performance across different contexts. Most models consistently outperformed random guessing, suggesting LLMs may support decision-making in triage scenarios. Neutral or factual scenario formulations led to the best performance, unlike other ME benchmarks where ethical reminders improved outcomes. Adversarial prompts reduced performance but not to random guessing levels. Open-source models made more morally serious errors, and general capability overall predicted better performance.

In this review paper, we delve into the realm of Large Language Models (LLMs), covering their foundational principles, diverse applications, and nuanced training processes. The article sheds light on the mechanics of in-context learning and a spectrum of fine-tuning approaches, with a special focus on methods that optimize efficiency in parameter usage. Additionally, it explores how LLMs can be more closely aligned with human preferences through innovative reinforcement learning frameworks and other novel methods that incorporate human feedback. The article also examines the emerging technique of retrieval augmented generation, integrating external knowledge into LLMs. The ethical dimensions of LLM deployment are discussed, underscoring the need for mindful and responsible application. Concluding with a perspective on future research trajectories, this review offers a succinct yet comprehensive overview of the current state and emerging trends in the evolving landscape of LLMs, serving as an insightful guide for both researchers and practitioners in artificial intelligence.

Large language models (LLMs) demonstrate outstanding capabilities, but challenges remain regarding their ability to solve complex reasoning tasks, as well as their transparency, robustness, truthfulness, and ethical alignment. In this preliminary study, we compile a set of core principles for steering and evaluating the reasoning of LLMs by curating literature from several relevant strands of work: structured reasoning in LLMs, self-evaluation/self-reflection, explainability, AI system safety/security, guidelines for human critical thinking, and ethical/regulatory guidelines for AI. We identify and curate a list of 220 principles from literature, and derive a set of 37 core principles organized into seven categories: assumptions and perspectives, reasoning, information and evidence, robustness and security, ethics, utility, and implications. We conduct a small-scale expert survey, eliciting the subjective importance experts assign to different principles and lay out avenues for future work beyond our preliminary results. We envision that the development of a shared model of principles can serve multiple purposes: monitoring and steering models at inference time, improving model behavior during training, and guiding human evaluation of model reasoning., Comment: Accepted at Socially Responsible Language Modelling Research (SoLaR) workshop, NeurIPS 2023 (https://openreview.net/forum?id=8iXdNXW34d). Based on previous manuscript version: doi:10.2139/ssrn.4446991

Systematic literature reviews (SLRs) play an essential role in summarising, synthesising and validating scientific evidence. In recent years, there has been a growing interest in using machine learning techniques to automate the identification of relevant studies for SLRs. However, the lack of standardised evaluation datasets makes comparing the performance of such automated literature screening systems difficult. In this paper, we analyse the citation screening evaluation datasets, revealing that many of the available datasets are either too small, suffer from data leakage or have limited applicability to systems treating automated literature screening as a classification task, as opposed to, for example, a retrieval or question-answering task. To address these challenges, we introduce CSMeD, a meta-dataset consolidating nine publicly released collections, providing unified access to 325 SLRs from the fields of medicine and computer science. CSMeD serves as a comprehensive resource for training and evaluating the performance of automated citation screening models. Additionally, we introduce CSMeD-FT, a new dataset designed explicitly for evaluating the full text publication screening task. To demonstrate the utility of CSMeD, we conduct experiments and establish baselines on new datasets., Comment: Accepted at NeurIPS 2023 Datasets and Benchmarks Track

Emergent chain-of-thought (CoT) reasoning capabilities promise to improve performance and explainability of large language models (LLMs). However, uncertainties remain about how reasoning strategies formulated for previous model generations generalize to new model generations and different datasets. In this small-scale study, we compare different reasoning strategies induced by zero-shot prompting across six recently released LLMs (davinci-002, davinci-003, GPT-3.5-turbo, GPT-4, Flan-T5-xxl and Cohere command-xlarge) on a mixture of six question-answering datasets, including datasets from scientific and medical domains. Our findings demonstrate that while some variations in effectiveness occur, gains from CoT reasoning strategies remain robust across different models and datasets. GPT-4 has the most benefit from current state-of-the-art reasoning strategies and exhibits the best performance by applying a prompt previously discovered through automated discovery.

In recent years, deep neural networks have been widely used for building high-performance Artificial Intelligence (AI) systems for computer vision applications. Object detection is a fundamental task in computer vision, which has been greatly progressed through developing large and intricate AI models. However, the lack of transparency is a big challenge that may not allow the widespread adoption of these models. Explainable artificial intelligence is a field of research where methods are developed to help users understand the behavior, decision logics, and vulnerabilities of AI systems. Previously, few explanation methods were developed for object detection based on random masking. However, random masks may raise some issues regarding the actual importance of pixels within an image. In this paper, we design and implement a black-box explanation method named Black-box Object Detection Explanation by Masking (BODEM) through adopting a hierarchical random masking approach for object detection systems. We propose a hierarchical random masking framework in which coarse-grained masks are used in lower levels to find salient regions within an image, and fine-grained mask are used to refine the salient regions in higher levels. Experimentations on various object detection datasets and models showed that BODEM can effectively explain the behavior of object detectors. Moreover, our method outperformed Detector Randomized Input Sampling for Explanation (D-RISE) and Local Interpretable Model-agnostic Explanations (LIME) with respect to different quantitative measures of explanation effectiveness. The experimental results demonstrate that BODEM can be an effective method for explaining and validating object detection systems in black-box testing scenarios.

Clinical notes containing valuable patient information are written by different health care providers with various scientific levels and writing styles. It might be helpful for clinicians and researchers to understand what information is essential when dealing with extensive electronic medical records. Entities recognizing and mapping them to standard terminologies is crucial in reducing ambiguity in processing clinical notes. Although named entity recognition and entity linking are critical steps in clinical natural language processing, they can also result in the production of repetitive and low-value concepts. In other hand, all parts of a clinical text do not share the same importance or content in predicting the patient's condition. As a result, it is necessary to identify the section in which each content is recorded and also to identify key concepts to extract meaning from clinical texts. In this study, these challenges have been addressed by using clinical natural language processing techniques. In addition, in order to identify key concepts, a set of popular unsupervised key phrase extraction methods has been verified and evaluated. Considering that most of the clinical concepts are in the form of multi-word expressions and their accurate identification requires the user to specify n-gram range, we have proposed a shortcut method to preserve the structure of the expression based on TF-IDF. In order to evaluate the pre-processing method and select the concepts, we have designed two types of downstream tasks (multiple and binary classification) using the capabilities of transformer-based models. The obtained results show the superiority of proposed method in combination with SciBERT model, also offer an insight into the efficacy of general extracting essential phrase methods for clinical notes.

Large language models (LLMs) such as GPT-4 have recently demonstrated impressive results across a wide range of tasks. LLMs are still limited, however, in that they frequently fail at complex reasoning, their reasoning processes are opaque, they are prone to 'hallucinate' facts, and there are concerns about their underlying biases. Letting models verbalize reasoning steps as natural language, a technique known as chain-of-thought prompting, has recently been proposed as a way to address some of these issues. Here we present ThoughtSource, a meta-dataset and software library for chain-of-thought (CoT) reasoning. The goal of ThoughtSource is to improve future artificial intelligence systems by facilitating qualitative understanding of CoTs, enabling empirical evaluations, and providing training data. This first release of ThoughtSource integrates seven scientific/medical, three general-domain and five math word question answering datasets., Comment: Revision: added datasets, formatting

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.

Training and evaluating language models increasingly requires the construction of meta-datasets --diverse collections of curated data with clear provenance. Natural language prompting has recently lead to improved zero-shot generalization by transforming existing, supervised datasets into a diversity of novel pretraining tasks, highlighting the benefits of meta-dataset curation. While successful in general-domain text, translating these data-centric approaches to biomedical language modeling remains challenging, as labeled biomedical datasets are significantly underrepresented in popular data hubs. To address this challenge, we introduce BigBIO a community library of 126+ biomedical NLP datasets, currently covering 12 task categories and 10+ languages. BigBIO facilitates reproducible meta-dataset curation via programmatic access to datasets and their metadata, and is compatible with current platforms for prompt engineering and end-to-end few/zero shot language model evaluation. We discuss our process for task schema harmonization, data auditing, contribution guidelines, and outline two illustrative use cases: zero-shot evaluation of biomedical prompts and large-scale, multi-task learning. BigBIO is an ongoing community effort and is available at https://github.com/bigscience-workshop/biomedical, Comment: Submitted to NeurIPS 2022 Datasets and Benchmarks Track

Measuring the performance of natural language processing models is challenging. Traditionally used metrics, such as BLEU and ROUGE, originally devised for machine translation and summarization, have been shown to suffer from low correlation with human judgment and a lack of transferability to other tasks and languages. In the past 15 years, a wide range of alternative metrics have been proposed. However, it is unclear to what extent this has had an impact on NLP benchmarking efforts. Here we provide the first large-scale cross-sectional analysis of metrics used for measuring performance in natural language processing. We curated, mapped and systematized more than 3500 machine learning model performance results from the open repository 'Papers with Code' to enable a global and comprehensive analysis. Our results suggest that the large majority of natural language processing metrics currently used have properties that may result in an inadequate reflection of a models' performance. Furthermore, we found that ambiguities and inconsistencies in the reporting of metrics may lead to difficulties in interpreting and comparing model performances, impairing transparency and reproducibility in NLP research., Comment: "NLP Power" workshop at ACL 2022. This work is based on a previous arXiv submission: arXiv:2008.02577 [cs.AI]

Benchmarks are crucial to measuring and steering progress in artificial intelligence (AI). However, recent studies raised concerns over the state of AI benchmarking, reporting issues such as benchmark overfitting, benchmark saturation and increasing centralization of benchmark dataset creation. To facilitate monitoring of the health of the AI benchmarking ecosystem, we introduce methodologies for creating condensed maps of the global dynamics of benchmark creation and saturation. We curated data for 3765 benchmarks covering the entire domains of computer vision and natural language processing, and show that a large fraction of benchmarks quickly trended towards near-saturation, that many benchmarks fail to find widespread utilization, and that benchmark performance gains for different AI tasks were prone to unforeseen bursts. We analyze attributes associated with benchmark popularity, and conclude that future benchmarks should emphasize versatility, breadth and real-world utility., Comment: This version includes more recent data and additional analyses

In this article, we first give an introduction to artificial intelligence and its applications in biology and medicine in Section 1. Deep learning methods are then described in Section 2. We narrow down the focus of the study on textual data in Section 3, where natural language processing and its applications in the biomedical domain are described. In Section 4, we give an introduction to explainable artificial intelligence and discuss the importance of explainability of artificial intelligence systems, especially in the biomedical domain.

Publicly accessible benchmarks that allow for assessing and comparing model performances are important drivers of progress in artificial intelligence (AI). While recent advances in AI capabilities hold the potential to transform medical practice by assisting and augmenting the cognitive processes of healthcare professionals, the coverage of clinically relevant tasks by AI benchmarks is largely unclear. Furthermore, there is a lack of systematized meta-information that allows clinical AI researchers to quickly determine accessibility, scope, content and other characteristics of datasets and benchmark datasets relevant to the clinical domain. To address these issues, we curated and released a comprehensive catalogue of datasets and benchmarks pertaining to the broad domain of clinical and biomedical natural language processing (NLP), based on a systematic review of literature and online resources. A total of 450 NLP datasets were manually systematized and annotated with rich metadata, such as targeted tasks, clinical applicability, data types, performance metrics, accessibility and licensing information, and availability of data splits. We then compared tasks covered by AI benchmark datasets with relevant tasks that medical practitioners reported as highly desirable targets for automation in a previous empirical study. Our analysis indicates that AI benchmarks of direct clinical relevance are scarce and fail to cover most work activities that clinicians want to see addressed. In particular, tasks associated with routine documentation and patient data administration workflows are not represented despite significant associated workloads. Thus, currently available AI benchmarks are improperly aligned with desired targets for AI automation in clinical settings, and novel benchmarks should be created to fill these gaps., Comment: (this version extends the literature references)

Deep transformer neural network models have improved the predictive accuracy of intelligent text processing systems in the biomedical domain. They have obtained state-of-the-art performance scores on a wide variety of biomedical and clinical Natural Language Processing (NLP) benchmarks. However, the robustness and reliability of these models has been less explored so far. Neural NLP models can be easily fooled by adversarial samples, i.e. minor changes to input that preserve the meaning and understandability of the text but force the NLP system to make erroneous decisions. This raises serious concerns about the security and trust-worthiness of biomedical NLP systems, especially when they are intended to be deployed in real-world use cases. We investigated the robustness of several transformer neural language models, i.e. BioBERT, SciBERT, BioMed-RoBERTa, and Bio-ClinicalBERT, on a wide range of biomedical and clinical text processing tasks. We implemented various adversarial attack methods to test the NLP systems in different attack scenarios. Experimental results showed that the biomedical NLP models are sensitive to adversarial samples; their performance dropped in average by 21 and 18.9 absolute percent on character-level and word-level adversarial noise, respectively. Conducting extensive adversarial training experiments, we fine-tuned the NLP models on a mixture of clean samples and adversarial inputs. Results showed that adversarial training is an effective defense mechanism against adversarial noise; the models robustness improved in average by 11.3 absolute percent. In addition, the models performance on clean data increased in average by 2.4 absolute present, demonstrating that adversarial training can boost generalization abilities of biomedical NLP systems.

Research in artificial intelligence (AI) is addressing a growing number of tasks through a rapidly growing number of models and methodologies. This makes it difficult to keep track of where novel AI methods are successfully -- or still unsuccessfully -- applied, how progress is measured, how different advances might synergize with each other, and how future research should be prioritized. To help address these issues, we created the Intelligence Task Ontology and Knowledge Graph (ITO), a comprehensive, richly structured and manually curated resource on artificial intelligence tasks, benchmark results and performance metrics. The current version of ITO contain 685,560 edges, 1,100 classes representing AI processes and 1,995 properties representing performance metrics. The goal of ITO is to enable precise and network-based analyses of the global landscape of AI tasks and capabilities. ITO is based on technologies that allow for easy integration and enrichment with external data, automated inference and continuous, collaborative expert curation of underlying ontological models. We make the ITO dataset and a collection of Jupyter notebooks utilising ITO openly available.

BACKGROUND: In this study, we investigated the efficacy of current state-of-the-art neural sentence embedding models for semantic similarity estimation of sentences from biomedical literature. We trained different neural embedding models on 1.7 million articles from the PubMed Open Access dataset, and evaluated them based on a biomedical benchmark set containing 100 sentence pairs annotated by human experts and a smaller contradiction subset derived from the original benchmark set. RESULTS: With a Pearson correlation of 0.819, our best unsupervised model based on the Paragraph Vector Distributed Memory algorithm outperforms previous state-of-the-art results achieved on the BIOSSES biomedical benchmark set. Moreover, our proposed supervised model that combines different string-based similarity metrics with a neural embedding model surpasses previous ontology-dependent supervised state-of-the-art approaches in terms of Pearson's r (r=0.871) on the biomedical benchmark set. In contrast to the promising results for the original benchmark, we found our best models' performance on the smaller contradiction subset to be poor. CONCLUSIONS: In this study we highlighted the value of neural network-based models for semantic similarity estimation in the biomedical domain by showing that they can keep up with and even surpass previous state-of-the-art approaches for semantic similarity estimation that depend on the availability of laboriously curated ontologies when evaluated on a biomedical benchmark set. Capturing contradictions and negations in biomedical sentences, however, emerged as an essential area for further work., Comment: Abstract shortened to comply with arXiv guidelines

Neural embedding-based machine learning models have shown promise for predicting novel links in knowledge graphs. Unfortunately, their practical utility is diminished by their lack of interpretability. Recently, the fully interpretable, rule-based algorithm AnyBURL yielded highly competitive results on many general-purpose link prediction benchmarks. However, current approaches for aggregating predictions made by multiple rules are affected by redundancies. We improve upon AnyBURL by introducing the SAFRAN rule application framework, which uses a novel aggregation approach called Non-redundant Noisy-OR that detects and clusters redundant rules prior to aggregation. SAFRAN yields new state-of-the-art results for fully interpretable link prediction on the established general-purpose benchmarks FB15K-237, WN18RR and YAGO3-10. Furthermore, it exceeds the results of multiple established embedding-based algorithms on FB15K-237 and WN18RR and narrows the gap between rule-based and embedding-based algorithms on YAGO3-10.

Deep neural language models have set new breakthroughs in many tasks of Natural Language Processing (NLP). Recent work has shown that deep transformer language models (pretrained on large amounts of texts) can achieve high levels of task-specific few-shot performance comparable to state-of-the-art models. However, the ability of these large language models in few-shot transfer learning has not yet been explored in the biomedical domain. We investigated the performance of two powerful transformer language models, i.e. GPT-3 and BioBERT, in few-shot settings on various biomedical NLP tasks. The experimental results showed that, to a great extent, both the models underperform a language model fine-tuned on the full training data. Although GPT-3 had already achieved near state-of-the-art results in few-shot knowledge transfer on open-domain NLP tasks, it could not perform as effectively as BioBERT, which is orders of magnitude smaller than GPT-3. Regarding that BioBERT was already pretrained on large biomedical text corpora, our study suggests that language models may largely benefit from in-domain pretraining in task-specific few-shot learning. However, in-domain pretraining seems not to be sufficient; novel pretraining and few-shot learning strategies are required in the biomedical NLP domain.

Artificial Intelligence (AI) systems are attracting increasing interest in the medical domain due to their ability to learn complicated tasks that require human intelligence and expert knowledge. AI systems that utilize high-performance Natural Language Processing (NLP) models have achieved state-of-the-art results on a wide variety of clinical text processing benchmarks. They have even outperformed human accuracy on some tasks. However, performance evaluation of such AI systems have been limited to accuracy measures on curated and clean benchmark datasets that may not properly reflect how robustly these systems can operate in real-world situations. In order to address this challenge, we introduce and implement a wide variety of perturbation methods that simulate different types of noise and variability in clinical text data. While noisy samples produced by these perturbation methods can often be understood by humans, they may cause AI systems to make erroneous decisions. Conducting extensive experiments on several clinical text processing tasks, we evaluated the robustness of high-performance NLP models against various types of character-level and word-level noise. The results revealed that the NLP models performance degrades when the input contains small amounts of noise. This study is a significant step towards exposing vulnerabilities of AI models utilized in clinical text processing systems. The proposed perturbation methods can be used in performance evaluation tests to assess how robustly clinical NLP models can operate on noisy data, in real-world settings.

High-performance neural language models have obtained state-of-the-art results on a wide range of Natural Language Processing (NLP) tasks. However, results for common benchmark datasets often do not reflect model reliability and robustness when applied to noisy, real-world data. In this study, we design and implement various types of character-level and word-level perturbation methods to simulate realistic scenarios in which input texts may be slightly noisy or different from the data distribution on which NLP systems were trained. Conducting comprehensive experiments on different NLP tasks, we investigate the ability of high-performance language models such as BERT, XLNet, RoBERTa, and ELMo in handling different types of input perturbations. The results suggest that language models are sensitive to input perturbations and their performance can decrease even when small changes are introduced. We highlight that models need to be further improved and that current benchmarks are not reflecting model robustness well. We argue that evaluations on perturbed inputs should routinely complement widely-used benchmarks in order to yield a more realistic understanding of NLP systems robustness., Comment: Accepted by EMNLP 2021

Patient similarity assessment, which identifies patients similar to a given patient, can help improve medical care. The assessment can be performed using Electronic Medical Records (EMRs). Patient similarity measurement requires converting heterogeneous EMRs into comparable formats to calculate their distance. While versatile document representation learning methods have been developed in recent years, it is still unclear how complex EMR data should be processed to create the most useful patient representations. This study presents a new data representation method for EMRs that takes the information in clinical narratives into account. To address the limitations of previous approaches in handling complex parts of EMR data, an unsupervised method is proposed for building a patient representation, which integrates unstructured data with structured data extracted from patients' EMRs. In order to model the extracted data, we employed a tree structure that captures the temporal relations of multiple medical events from EMR. We processed clinical notes to extract symptoms, signs, and diseases using different tools such as medspaCy, MetaMap, and scispaCy and mapped entities to the Unified Medical Language System (UMLS). After creating a tree data structure, we utilized two novel relabeling methods for the non-leaf nodes of the tree to capture two temporal aspects of the extracted events. By traversing the tree, we generated a sequence that could create an embedding vector for each patient. The comprehensive evaluation of the proposed method for patient similarity and mortality prediction tasks demonstrated that our proposed model leads to lower mean squared error (MSE), higher precision, and normalized discounted cumulative gain (NDCG) relative to baselines.

In this paper, we propose a novel method named Biomedical Confident Itemsets Explanation (BioCIE), aiming at post-hoc explanation of black-box machine learning models for biomedical text classification. Using sources of domain knowledge and a confident itemset mining method, BioCIE discretizes the decision space of a black-box into smaller subspaces and extracts semantic relationships between the input text and class labels in different subspaces. Confident itemsets discover how biomedical concepts are related to class labels in the black-box's decision space. BioCIE uses the itemsets to approximate the black-box's behavior for individual predictions. Optimizing fidelity, interpretability, and coverage measures, BioCIE produces class-wise explanations that represent decision boundaries of the black-box. Results of evaluations on various biomedical text classification tasks and black-box models demonstrated that BioCIE can outperform perturbation-based and decision set methods in terms of producing concise, accurate, and interpretable explanations. BioCIE improved the fidelity of instance-wise and class-wise explanations by 11.6% and 7.5%, respectively. It also improved the interpretability of explanations by 8%. BioCIE can be effectively used to explain how a black-box biomedical text classification model semantically relates input texts to class labels. The source code and supplementary material are available at https://github.com/mmoradi-iut/BioCIE.

Neural embedding-based machine learning models have shown promise for predicting novel links in biomedical knowledge graphs. Unfortunately, their practical utility is diminished by their lack of interpretability. Recently, the fully interpretable, rule-based algorithm AnyBURL yielded highly competitive results on many general-purpose link prediction benchmarks. However, its applicability to large-scale prediction tasks on complex biomedical knowledge bases is limited by long inference times and difficulties with aggregating predictions made by multiple rules. We improve upon AnyBURL by introducing the SAFRAN rule application framework which aggregates rules through a scalable clustering algorithm. SAFRAN yields new state-of-the-art results for fully interpretable link prediction on the established general-purpose benchmark FB15K-237 and the large-scale biomedical benchmark OpenBioLink. Furthermore, it exceeds the results of multiple established embedding-based algorithms on FB15K-237 and narrows the gap between rule-based and embedding-based algorithms on OpenBioLink. We also show that SAFRAN increases inference speeds by up to two orders of magnitude.

Deep neural networks and other intricate Artificial Intelligence (AI) models have reached high levels of accuracy on many biomedical natural language processing tasks. However, their applicability in real-world use cases may be limited due to their vague inner working and decision logic. A post-hoc explanation method can approximate the behavior of a black-box AI model by extracting relationships between feature values and outcomes. In this paper, we introduce a post-hoc explanation method that utilizes confident itemsets to approximate the behavior of black-box classifiers for medical information extraction. Incorporating medical concepts and semantics into the explanation process, our explanator finds semantic relations between inputs and outputs in different parts of the decision space of a black-box classifier. The experimental results show that our explanation method can outperform perturbation and decision set based explanators in terms of fidelity and interpretability of explanations produced for predictions on a disease-treatment information extraction task.

Comparing model performances on benchmark datasets is an integral part of measuring and driving progress in artificial intelligence. A model's performance on a benchmark dataset is commonly assessed based on a single or a small set of performance metrics. While this enables quick comparisons, it may entail the risk of inadequately reflecting model performance if the metric does not sufficiently cover all performance characteristics. It is unknown to what extent this might impact benchmarking efforts. To address this question, we analysed the current landscape of performance metrics based on data covering 3867 machine learning model performance results from the open repository 'Papers with Code'. Our results suggest that the large majority of metrics currently used have properties that may result in an inadequate reflection of a models' performance. While alternative metrics that address problematic properties have been proposed, they are currently rarely used. Furthermore, we describe ambiguities in reported metrics, which may lead to difficulties in interpreting and comparing model performances.

Recently, link prediction algorithms based on neural embeddings have gained tremendous popularity in the Semantic Web community, and are extensively used for knowledge graph completion. While algorithmic advances have strongly focused on efficient ways of learning embeddings, fewer attention has been drawn to the different ways their performance and robustness can be evaluated. In this work we propose an open-source evaluation pipeline, which benchmarks the accuracy of neural embeddings in situations where knowledge graphs may experience semantic and structural changes. We define relation-centric connectivity measures that allow us to connect the link prediction capacity to the structure of the knowledge graph. Such an evaluation pipeline is especially important to simulate the accuracy of embeddings for knowledge graphs that are expected to be frequently updated.

Black-box Artificial Intelligence (AI) methods, e.g. deep neural networks, have been widely utilized to build predictive models that can extract complex relationships in a dataset and make predictions for new unseen data records. However, it is difficult to trust decisions made by such methods since their inner working and decision logic is hidden from the user. Explainable Artificial Intelligence (XAI) refers to systems that try to explain how a black-box AI model produces its outcomes. Post-hoc XAI methods approximate the behavior of a black-box by extracting relationships between feature values and the predictions. Perturbation-based and decision set methods are among commonly used post-hoc XAI systems. The former explanators rely on random perturbations of data records to build local or global linear models that explain individual predictions or the whole model. The latter explanators use those feature values that appear more frequently to construct a set of decision rules that produces the same outcomes as the target black-box. However, these two classes of XAI methods have some limitations. Random perturbations do not take into account the distribution of feature values in different subspaces, leading to misleading approximations. Decision sets only pay attention to frequent feature values and miss many important correlations between features and class labels that appear less frequently but accurately represent decision boundaries of the model. In this paper, we address the above challenges by proposing an explanation method named Confident Itemsets Explanation (CIE). We introduce confident itemsets, a set of feature values that are highly correlated to a specific class label. CIE utilizes confident itemsets to discretize the whole decision space of a model to smaller subspaces.

Large ontologies still pose serious challenges to state-of-the-art ontology alignment systems. In this paper we present an approach that combines a neural embedding model and logic-based modules to accurately divide an input ontology matching task into smaller and more tractable matching (sub)tasks. We have conducted a comprehensive evaluation using the datasets of the Ontology Alignment Evaluation Initiative. The results are encouraging and suggest that the proposed method is adequate in practice and can be integrated within the workflow of systems unable to cope with very large ontologies., Comment: Accepted to the 24th European Conference on Artificial Intelligence (ECAI 2020). arXiv admin note: text overlap with arXiv:1805.12402

SUMMARY: Recently, novel machine-learning algorithms have shown potential for predicting undiscovered links in biomedical knowledge networks. However, dedicated benchmarks for measuring algorithmic progress have not yet emerged. With OpenBioLink, we introduce a large-scale, high-quality and highly challenging biomedical link prediction benchmark to transparently and reproducibly evaluate such algorithms. Furthermore, we present preliminary baseline evaluation results. AVAILABILITY AND IMPLEMENTATION: Source code, data and supplementary files are openly available at https://github.com/OpenBioLink/OpenBioLink CONTACT: matthias.samwald ((at)) meduniwien.ac.at

In recent years, summarizers that incorporate domain knowledge into the process of text summarization have outperformed generic methods, especially for summarization of biomedical texts. However, construction and maintenance of domain knowledge bases are resource-intense tasks requiring significant manual annotation. In this paper, we demonstrate that contextualized representations extracted from the pre-trained deep language model BERT, can be effectively used to measure the similarity between sentences and to quantify the informative content. The results show that our BERT-based summarizer can improve the performance of biomedical summarization. Although the summarizer does not use any sources of domain knowledge, it can capture the context of sentences more accurately than the comparison methods. The source code and data are available at https://github.com/BioTextSumm/BERT-based-Summ.

We focus our attention on the link prediction problem for knowledge graphs, which is treated herein as a binary classification task on neural embeddings of the entities. By comparing, combining and extending different methodologies for link prediction on graph-based data coming from different domains, we formalize a unified methodology for the quality evaluation benchmark of neural embeddings for knowledge graphs. This benchmark is then used to empirically investigate the potential of training neural embeddings globally for the entire graph, as opposed to the usual way of training embeddings locally for a specific relation. This new way of testing the quality of the embeddings evaluates the performance of binary classifiers for scalable link prediction with limited data. Our evaluation pipeline is made open source, and with this we aim to draw more attention of the community towards an important issue of transparency and reproducibility of the neural embeddings evaluations., Comment: Accepted to 4th Semantic Deep Learning (SemDeep-4) Workshop at the ISWC 2018

Large ontologies still pose serious challenges to state-of-the-art ontology alignment systems. In the paper we present an approach that combines a lexical index, a neural embedding model and locality modules to effectively divide an input ontology matching task into smaller and more tractable matching (sub)tasks. We have conducted a comprehensive evaluation using the datasets of the Ontology Alignment Evaluation Initiative. The results are encouraging and suggest that the proposed methods are adequate in practice and can be integrated within the workflow of state-of-the-art systems.

In this work we address the problem of fast and scalable learning of neuro-symbolic representations for general biological knowledge. Based on a recently published comprehensive biological knowledge graph (Alshahrani, 2017) that was used for demonstrating neuro-symbolic representation learning, we show how to train fast (under 1 minute) log-linear neural embeddings of the entities. We utilize these representations as inputs for machine learning classifiers to enable important tasks such as biological link prediction. Classifiers are trained by concatenating learned entity embeddings to represent entity relations, and training classifiers on the concatenated embeddings to discern true relations from automatically generated negative examples. Our simple embedding methodology greatly improves on classification error compared to previously published state-of-the-art results, yielding a maximum increase of $+0.28$ F-measure and $+0.22$ ROC AUC scores for the most difficult biological link prediction problem. Finally, our embedding approach is orders of magnitude faster to train ($\leq$ 1 minute vs. hours), much more economical in terms of embedding dimensions ($d=50$ vs. $d=512$), and naturally encodes the directionality of the asymmetric biological relations, that can be controlled by the order with which we concatenate the embeddings., Comment: Accepted to workshop on Deep Learning for Knowledge Graphs and Semantic Technologies (DL4KGS) at ESWC 2018, June 2018, Greece

BACKGROUND: The amount of biomedical literature is rapidly growing and it is becoming increasingly difficult to keep manually curated knowledge bases and ontologies up-to-date. In this study we applied the word2vec deep learning toolkit to medical corpora to test its potential for identifying relationships from unstructured text. We evaluated the efficiency of word2vec in identifying properties of pharmaceuticals based on mid-sized, unstructured medical text corpora available on the web. Properties included relationships to diseases ('may treat') or physiological processes ('has physiological effect'). We compared the relationships identified by word2vec with manually curated information from the National Drug File - Reference Terminology (NDF-RT) ontology as a gold standard. RESULTS: Our results revealed a maximum accuracy of 49.28% which suggests a limited ability of word2vec to capture linguistic regularities on the collected medical corpora compared with other published results. We were able to document the influence of different parameter settings on result accuracy and found and unexpected trade-off between ranking quality and accuracy. Pre-processing corpora to reduce syntactic variability proved to be a good strategy for increasing the utility of the trained vector models. CONCLUSIONS: Word2vec is a very efficient implementation for computing vector representations and for its ability to identify relationships in textual data without any prior domain knowledge. We found that the ranking and retrieved results generated by word2vec were not of sufficient quality for automatic population of knowledge bases and ontologies, but could serve as a starting point for further manual curation.