More Like this

1. BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models

   Hao Shibo, Tan Bowen ( July 2023 , Findings of the Association for Computational Linguistics: ACL 2023)

   It is crucial to automatically construct knowledge graphs (KGs) of diverse new relations to support knowledge discovery and broad applications. Previous KG construction methods, based on either crowdsourcing or text mining, are often limited to a small predefined set of relations due to manual cost or restrictions in text corpus. Recent research proposed to use pretrained language models (LMs) as implicit knowledge bases that accept knowledge queries with prompts. Yet, the implicit knowledge lacks many desirable properties of a full-scale symbolic KG, such as easy access, navigation, editing, and quality assurance. In this paper, we propose a new approach of harvesting massive KGs of arbitrary relations from pretrained LMs. With minimal input of a relation definition (a prompt and a few shot of example entity pairs), the approach efficiently searches in the vast entity pair space to extract diverse accurate knowledge of the desired relation. We develop an effective search-and-rescore mechanism for improved efficiency and accuracy. We deploy the approach to harvest KGs of over 400 new relations, from LMs of varying capacities such as RoBERTaNet. Extensive human and automatic evaluations show our approach manages to extract diverse accurate knowledge, including tuples of complex relations (e.g., “A is capable of but not good at B”). The resulting KGs as a symbolic interpretation of the source LMs also reveal new insights into the LMs’ knowledge capacities. 

   more » « less
2. Jupyter Notebooks, the PmagPy Software Package and the Magnetics Information Consortium (MagIC) Database

   https://doi.org/10.1002/essoar.10504416.1  

   Tauxe, L. ( June 2020 , Earthcube2020)

   PmagPy Online: Jupyter Notebooks, the PmagPy Software Package and the Magnetics Information Consortium (MagIC) Database Lisa Tauxe$^1$, Rupert Minnett$^2$, Nick Jarboe$^1$, Catherine Constable$^1$, Anthony Koppers$^2$, Lori Jonestrask$^1$, Nick Swanson-Hysell$^3$ $^1$Scripps Institution of Oceanography, United States of America; $^2$ Oregon State University; $^3$ University of California, Berkely; ltauxe@ucsd.edu The Magnetics Information Consortium (MagIC), hosted at http://earthref.org/MagIC is a database that serves as a Findable, Accessible, Interoperable, Reusable (FAIR) archive for paleomagnetic and rock magnetic data. It has a flexible, comprehensive data model that can accomodate most kinds of paleomagnetic data. The PmagPy software package is a cross-platform and open-source set of tools written in Python for the analysis of paleomagnetic data that serves as one interface to MagIC, accommodating various levels of user expertise. It is available through github.com/PmagPy. Because PmagPy requires installation of Python, several non-standard Python modules, and the PmagPy software package, there is a speed bump for many practitioners on beginning to use the software. In order to make the software and MagIC more accessible to the broad spectrum of scientists interested in paleo and rock magnetism, we have prepared a set of Jupyter notebooks, hosted on jupyterhub.earthref.org which serve a set of purposes. 1) There is a complete course in Python for Earth Scientists, 2) a set of notebooks that introduce PmagPy (pulling the software package from the github repository) and illustrate how it can be used to create data products and figures for typical papers, and 3) show how to prepare data from the laboratory to upload into the MagIC database. The latter will satisfy expectations from NSF for data archiving and for example the AGU publication data archiving requirements. Getting started To use the PmagPy notebooks online, go to website at https://jupyterhub.earthref.org/. Create an Earthref account using your ORCID and log on. [This allows you to keep files in a private work space.] Open the PmagPy Online - Setup notebook and execute the two cells. Then click on File = > Open and click on the PmagPy_Online folder. Open the PmagPy_online notebook and work through the examples. There are other notebooks that are useful for the working paleomagnetist. Alternatively, you can install Python and the PmagPy software package on your computer (see https://earthref.org/PmagPy/cookbook for instructions). Follow the instructions for "Full PmagPy install and update" through section 1.4 (Quickstart with PmagPy notebooks). This notebook is in the collection of PmagPy notebooks. Overview of MagIC The Magnetics Information Consortium (MagIC), hosted at http://earthref.org/MagIC is a database that serves as a Findable, Accessible, Interoperable, Reusable (FAIR) archive for paleomagnetic and rock magnetic data. Its datamodel is fully described here: https://www2.earthref.org/MagIC/data-models/3.0. Each contribution is associated with a publication via the DOI. There are nine data tables: contribution: metadata of the associated publication. locations: metadata for locations, which are groups of sites (e.g., stratigraphic section, region, etc.) sites: metadata and derived data at the site level (units with a common expectation) samples: metadata and derived data at the sample level. specimens: metadata and derived data at the specimen level. criteria: criteria by which data are deemed acceptable ages: ages and metadata for sites/samples/specimens images: associated images and plots. Overview of PmagPy The functionality of PmagPy is demonstrated within notebooks in the PmagPy repository: PmagPy_online.ipynb: serves as an introdution to PmagPy and MagIC (this conference). It highlights the link between PmagPy and the Findable Accessible Interoperable Reusabe (FAIR) database maintained by the Magnetics Information Consortium (MagIC) at https://earthref.org/MagIC. Other notebooks of interest are: PmagPy_calculations.ipynb: demonstrates many of the PmagPy calculation functions such as those that rotate directions, return statistical parameters, and simulate data from specified distributions. PmagPy_plots_analysis.ipynb: demonstrates PmagPy functions that can be used to visual data as well as those that conduct statistical tests that have associated visualizations. PmagPy_MagIC.ipynb: demonstrates how PmagPy can be used to read and write data to and from the MagIC database format including conversion from many individual lab measurement file formats. Please see also our YouTube channel with more presentations from the 2020 MagIC workshop here: https://www.youtube.com/playlist?list=PLirL2unikKCgUkHQ3m8nT29tMCJNBj4kj 

   more » « less
3. The Deep Learning Epilepsy Detection Challenge: Design, Implementation, and Test of a New Crowd-Sourced AI Challenge Ecosystem

   Kiral, Isabell ; Roy, Subhrajit ; Mummert, Todd ; Braz, Alan ; Tsay, Jason ; Tang, Jianbin ; Asif, Umar ; Schaffter, Thomas ; Mehmet, Eren ; Picone, Joseph ; et al ( April 2019 , Challenges in Machine Learning Competitions for All (CiML))

   null (Ed.)

   The DeepLearningEpilepsyDetectionChallenge: design, implementation, andtestofanewcrowd-sourced AIchallengeecosystem Isabell Kiral*, Subhrajit Roy*, Todd Mummert*, Alan Braz*, Jason Tsay, Jianbin Tang, Umar Asif, Thomas Schaffter, Eren Mehmet, The IBM Epilepsy Consortium◊ , Joseph Picone, Iyad Obeid, Bruno De Assis Marques, Stefan Maetschke, Rania Khalaf†, Michal Rosen-Zvi† , Gustavo Stolovitzky† , Mahtab Mirmomeni† , Stefan Harrer† * These authors contributed equally to this work † Corresponding authors: rkhalaf@us.ibm.com, rosen@il.ibm.com, gustavo@us.ibm.com, mahtabm@au1.ibm.com, sharrer@au.ibm.com ◊ Members of the IBM Epilepsy Consortium are listed in the Acknowledgements section J. Picone and I. Obeid are with Temple University, USA. T. Schaffter is with Sage Bionetworks, USA. E. Mehmet is with the University of Illinois at Urbana-Champaign, USA. All other authors are with IBM Research in USA, Israel and Australia. Introduction This decade has seen an ever-growing number of scientific fields benefitting from the advances in machine learning technology and tooling. More recently, this trend reached the medical domain, with applications reaching from cancer diagnosis [1] to the development of brain-machine-interfaces [2]. While Kaggle has pioneered the crowd-sourcing of machine learning challenges to incentivise data scientists from around the world to advance algorithm and model design, the increasing complexity of problem statements demands of participants to be expert data scientists, deeply knowledgeable in at least one other scientific domain, and competent software engineers with access to large compute resources. People who match this description are few and far between, unfortunately leading to a shrinking pool of possible participants and a loss of experts dedicating their time to solving important problems. Participation is even further restricted in the context of any challenge run on confidential use cases or with sensitive data. Recently, we designed and ran a deep learning challenge to crowd-source the development of an automated labelling system for brain recordings, aiming to advance epilepsy research. A focus of this challenge, run internally in IBM, was the development of a platform that lowers the barrier of entry and therefore mitigates the risk of excluding interested parties from participating. The challenge: enabling wide participation With the goal to run a challenge that mobilises the largest possible pool of participants from IBM (global), we designed a use case around previous work in epileptic seizure prediction [3]. In this “Deep Learning Epilepsy Detection Challenge”, participants were asked to develop an automatic labelling system to reduce the time a clinician would need to diagnose patients with epilepsy. Labelled training and blind validation data for the challenge were generously provided by Temple University Hospital (TUH) [4]. TUH also devised a novel scoring metric for the detection of seizures that was used as basis for algorithm evaluation [5]. In order to provide an experience with a low barrier of entry, we designed a generalisable challenge platform under the following principles: 1. No participant should need to have in-depth knowledge of the specific domain. (i.e. no participant should need to be a neuroscientist or epileptologist.) 2. No participant should need to be an expert data scientist. 3. No participant should need more than basic programming knowledge. (i.e. no participant should need to learn how to process fringe data formats and stream data efficiently.) 4. No participant should need to provide their own computing resources. In addition to the above, our platform should further • guide participants through the entire process from sign-up to model submission, • facilitate collaboration, and • provide instant feedback to the participants through data visualisation and intermediate online leaderboards. The platform The architecture of the platform that was designed and developed is shown in Figure 1. The entire system consists of a number of interacting components. (1) A web portal serves as the entry point to challenge participation, providing challenge information, such as timelines and challenge rules, and scientific background. The portal also facilitated the formation of teams and provided participants with an intermediate leaderboard of submitted results and a final leaderboard at the end of the challenge. (2) IBM Watson Studio [6] is the umbrella term for a number of services offered by IBM. Upon creation of a user account through the web portal, an IBM Watson Studio account was automatically created for each participant that allowed users access to IBM's Data Science Experience (DSX), the analytics engine Watson Machine Learning (WML), and IBM's Cloud Object Storage (COS) [7], all of which will be described in more detail in further sections. (3) The user interface and starter kit were hosted on IBM's Data Science Experience platform (DSX) and formed the main component for designing and testing models during the challenge. DSX allows for real-time collaboration on shared notebooks between team members. A starter kit in the form of a Python notebook, supporting the popular deep learning libraries TensorFLow [8] and PyTorch [9], was provided to all teams to guide them through the challenge process. Upon instantiation, the starter kit loaded necessary python libraries and custom functions for the invisible integration with COS and WML. In dedicated spots in the notebook, participants could write custom pre-processing code, machine learning models, and post-processing algorithms. The starter kit provided instant feedback about participants' custom routines through data visualisations. Using the notebook only, teams were able to run the code on WML, making use of a compute cluster of IBM's resources. The starter kit also enabled submission of the final code to a data storage to which only the challenge team had access. (4) Watson Machine Learning provided access to shared compute resources (GPUs). Code was bundled up automatically in the starter kit and deployed to and run on WML. WML in turn had access to shared storage from which it requested recorded data and to which it stored the participant's code and trained models. (5) IBM's Cloud Object Storage held the data for this challenge. Using the starter kit, participants could investigate their results as well as data samples in order to better design custom algorithms. (6) Utility Functions were loaded into the starter kit at instantiation. This set of functions included code to pre-process data into a more common format, to optimise streaming through the use of the NutsFlow and NutsML libraries [10], and to provide seamless access to the all IBM services used. Not captured in the diagram is the final code evaluation, which was conducted in an automated way as soon as code was submitted though the starter kit, minimising the burden on the challenge organising team. Figure 1: High-level architecture of the challenge platform Measuring success The competitive phase of the "Deep Learning Epilepsy Detection Challenge" ran for 6 months. Twenty-five teams, with a total number of 87 scientists and software engineers from 14 global locations participated. All participants made use of the starter kit we provided and ran algorithms on IBM's infrastructure WML. Seven teams persisted until the end of the challenge and submitted final solutions. The best performing solutions reached seizure detection performances which allow to reduce hundred-fold the time eliptologists need to annotate continuous EEG recordings. Thus, we expect the developed algorithms to aid in the diagnosis of epilepsy by significantly shortening manual labelling time. Detailed results are currently in preparation for publication. Equally important to solving the scientific challenge, however, was to understand whether we managed to encourage participation from non-expert data scientists. Figure 2: Primary occupation as reported by challenge participants Out of the 40 participants for whom we have occupational information, 23 reported Data Science or AI as their main job description, 11 reported being a Software Engineer, and 2 people had expertise in Neuroscience. Figure 2 shows that participants had a variety of specialisations, including some that are in no way related to data science, software engineering, or neuroscience. No participant had deep knowledge and experience in data science, software engineering and neuroscience. Conclusion Given the growing complexity of data science problems and increasing dataset sizes, in order to solve these problems, it is imperative to enable collaboration between people with differences in expertise with a focus on inclusiveness and having a low barrier of entry. We designed, implemented, and tested a challenge platform to address exactly this. Using our platform, we ran a deep-learning challenge for epileptic seizure detection. 87 IBM employees from several business units including but not limited to IBM Research with a variety of skills, including sales and design, participated in this highly technical challenge. 

   more » « less
4. Nomenclature over 5 years in TaxonWorks: Approach, implementation, limitations and outcomes

   https://doi.org/10.3897/biss.5.75441  

   Yoder, Matthew ; Dmitriev, Dmitry ( September 2021 , Biodiversity Information Science and Standards)

   We are now over four decades into digitally managing the names of Earth's species. As the number of federating (i.e., software that brings together previously disparate projects under a common infrastructure, for example TaxonWorks) and aggregating (e.g., International Plant Name Index, Catalog of Life (CoL)) efforts increase, there remains an unmet need for both the migration forward of old data, and for the production of new, precise and comprehensive nomenclatural catalogs. Given this context, we provide an overview of how TaxonWorks seeks to contribute to this effort, and where it might evolve in the future. In TaxonWorks, when we talk about governed names and relationships, we mean it in the sense of existing international codes of nomenclature (e.g., the International Code of Zoological Nomenclature (ICZN)). More technically, nomenclature is defined as a set of objective assertions that describe the relationships between the names given to biological taxa and the rules that determine how those names are governed. It is critical to note that this is not the same thing as the relationship between a name and a biological entity, but rather nomenclature in TaxonWorks represents the details of the (governed) relationships between names. Rather than thinking of nomenclature as changing (a verb commonly used to express frustration with biological nomenclature), it is useful to think of nomenclature as a set of data points, which grows over time. For example, when synonymy happens, we do not erase the past, but rather record a new context for the name(s) in question. The biological concept changes, but the nomenclature (names) simply keeps adding up. Behind the scenes, nomenclature in TaxonWorks is represented by a set of nodes and edges, i.e., a mathematical graph, or network (e.g., Fig. 1). Most names (i.e., nodes in the network) are what TaxonWorks calls "protonyms," monomial epithets that are used to construct, for example, bionomial names (not to be confused with "protonym" sensu the ICZN). Protonyms are linked to other protonyms via relationships defined in NOMEN, an ontology that encodes governed rules of nomenclature. Within the system, all data, nodes and edges, can be cited, i.e., linked to a source and therefore anchored in time and tied to authorship, and annotated with a variety of annotation types (e.g., notes, confidence levels, tags). The actual building of the graphs is greatly simplified by multiple user-interfaces that allow scientists to review (e.g. Fig. 2), create, filter, and add to (again, not "change") the nomenclatural history. As in any complex knowledge-representation model, there are outlying scenarios, or edge cases that emerge, making certain human tasks more complex than others. TaxonWorks is no exception, it has limitations in terms of what and how some things can be represented. While many complex representations are hidden by simplified user-interfaces, some, for example, the handling of the ICZN's Family-group name, batch-loading of invalid relationships, and comparative syncing against external resources need more work to simplify the processes presently required to meet catalogers' needs. The depth at which TaxonWorks can capture nomenclature is only really valuable if it can be used by others. This is facilitated by the application programming interface (API) serving its data (https://api.taxonworks.org), serving text files, and by exports to standards like the emerging Catalog of Life Data Package. With reference to real-world problems, we illustrate different ways in which the API can be used, for example, as integrated into spreadsheets, through the use of command line scripts, and serve in the generation of public-facing websites. Behind all this effort are an increasing number of people recording help videos, developing documentation, and troubleshooting software and technical issues. Major contributions have come from developers at many skill levels, from high school to senior software engineers, illustrating that TaxonWorks leads in enabling both technical and domain-based contributions. The health and growth of this community is a key factor in TaxonWork's potential long-term impact in the effort to unify the names of Earth's species. 

   more » « less
5. Guiding Multi-Step Rearrangement Tasks with Natural Language Instructions

   Stengel-Eskin, Elias ; Hundt, Andrew ; He, Zhuohong ; Murali, Aditya ; Gopalan, Nakul ; Gombolay, Matthew ; Hager, Gregory ( October 2021 , Proceedings of Machine Learning Research)

   Faust, Aleksandra ; Hsu, David ; Neumann, Gerhard (Ed.)

   Enabling human operators to interact with robotic agents using natural language would allow non-experts to intuitively instruct these agents. Towards this goal, we propose a novel Transformer-based model which enables a user to guide a robot arm through a 3D multi-step manipulation task with natural language commands. Our system maps images and commands to masks over grasp or place locations, grounding the language directly in perceptual space. In a suite of block rearrangement tasks, we show that these masks can be combined with an existing manipulation framework without re-training, greatly improving learning efficiency. Our masking model is several orders of magnitude more sample efficient than typical Transformer models, operating with hundreds, not millions, of examples. Our modular design allows us to leverage supervised and reinforcement learning, providing an easy interface for experimentation with different architectures. Our model completes block manipulation tasks with synthetic commands more often than a UNet-based baseline, and learns to localize actions correctly while creating a mapping of symbols to perceptual input that supports compositional reasoning. We provide a valuable resource for 3D manipulation instruction following research by porting an existing 3D block dataset with crowdsourced language to a simulated environment. Our method’s absolute improvement in identifying the correct block on the ported dataset demonstrates its ability to handle syntactic and lexical variation. 

   more » « less