Babelfy is a software algorithm for the disambiguation of text written in any language. It performs the tasks of multilingual Word Sense Disambiguation (i.e., the disambiguation of common nouns, verbs, adjectives and adverbs) and Entity Linking (i.e. the disambiguation of mentions to encyclopedic entities like people, companies, places, etc.). == Overview == Babelfy uses the BabelNet multilingual knowledge graph to perform disambiguation and entity linking in three steps: It associates with each vertex of the BabelNet semantic network, i.e., either concept or named entity, a semantic signature, that is, a set of related vertices. This is a preliminary step which needs to be performed only once, independently of the input text. Given an input text, it extracts all the linkable fragments from this text and, for each of them, lists the possible meanings according to the semantic network. It creates a graph-based semantic interpretation of the whole text by linking the candidate meanings of the extracted fragments using the previously computed semantic signatures. It then extracts a dense subgraph of this representation and selects the best candidate meaning for each fragment. As a result, the text, written in any of the 271 languages supported by BabelNet, is output with possibly overlapping semantic annotations.
Speech segmentation
Speech segmentation is the process of identifying the boundaries between words, syllables, or phonemes in spoken natural languages. The term applies both to the mental processes used by humans, and to artificial processes of natural language processing. In the field of automatic pronunciation assessment, the process of segmenting an utterance against expected word(s) is called forced alignment. Speech segmentation is a subfield of general speech perception and an important subproblem of the technologically focused field of speech recognition, and cannot be adequately solved in isolation. As in most natural language processing problems, one must take into account context, grammar, and semantics, and even so the result is often a probabilistic division (statistically based on likelihood) rather than a categorical one. Though it seems that coarticulation—a phenomenon which may happen between adjacent words just as easily as within a single word—presents the main challenge in speech segmentation across languages, some other problems and strategies employed in solving those problems can be seen in the following sections. This problem overlaps to some extent with the problem of text segmentation that occurs in some languages which are traditionally written without inter-word spaces, like Chinese and Japanese, compared to writing systems which indicate speech segmentation between words by a word divider, such as the space. However, even for those languages, text segmentation is often much easier than speech segmentation, because the written language usually has little interference between adjacent words, and often contains additional clues not present in speech (such as the use of Chinese characters for word stems in Japanese). == Lexical recognition == In natural languages, the meaning of a complex spoken sentence can be understood by decomposing it into smaller lexical segments (roughly, the words of the language), associating a meaning to each segment, and combining those meanings according to the grammar rules of the language. Though lexical recognition is not thought to be used by infants in their first year, due to their highly limited vocabularies, it is one of the major processes involved in speech segmentation for adults. Three main models of lexical recognition exist in current research: first, whole-word access, which argues that words have a whole-word representation in the lexicon; second, decomposition, which argues that morphologically complex words are broken down into their morphemes (roots, stems, inflections, etc.) and then interpreted and; third, the view that whole-word and decomposition models are both used, but that the whole-word model provides some computational advantages and is therefore dominant in lexical recognition. To give an example, in a whole-word model, the word "cats" might be stored and searched for by letter, first "c", then "ca", "cat", and finally "cats". The same word, in a decompositional model, would likely be stored under the root word "cat" and could be searched for after removing the "s" suffix. "Falling", similarly, would be stored as "fall" and suffixed with the "ing" inflection. Though proponents of the decompositional model recognize that a morpheme-by-morpheme analysis may require significantly more computation, they argue that the unpacking of morphological information is necessary for other processes (such as syntactic structure) which may occur parallel to lexical searches. As a whole, research into systems of human lexical recognition is limited due to little experimental evidence that fully discriminates between the three main models. In any case, lexical recognition likely contributes significantly to speech segmentation through the contextual clues it provides, given that it is a heavily probabilistic system—based on the statistical likelihood of certain words or constituents occurring together. For example, one can imagine a situation where a person might say "I bought my dog at a ____ shop" and the missing word's vowel is pronounced as in "net", "sweat", or "pet". While the probability of "netshop" is extremely low, since "netshop" isn't currently a compound or phrase in English, and "sweatshop" also seems contextually improbable, "pet shop" is a good fit because it is a common phrase and is also related to the word "dog". Moreover, an utterance can have different meanings depending on how it is split into words. A popular example, often quoted in the field, is the phrase "How to wreck a nice beach", which sounds very similar to "How to recognize speech". As this example shows, proper lexical segmentation depends on context and semantics which draws on the whole of human knowledge and experience, and would thus require advanced pattern recognition and artificial intelligence technologies to be implemented on a computer. Lexical recognition is of particular value in the field of computer speech recognition, since the ability to build and search a network of semantically connected ideas would greatly increase the effectiveness of speech-recognition software. Statistical models can be used to segment and align recorded speech to words or phones. Applications include automatic lip-synch timing for cartoon animation, follow-the-bouncing-ball video sub-titling, and linguistic research. Automatic segmentation and alignment software is commercially available. == Phonotactic cues == For most spoken languages, the boundaries between lexical units are difficult to identify; phonotactics are one answer to this issue. One might expect that the inter-word spaces used by many written languages like English or Spanish would correspond to pauses in their spoken version, but that is true only in very slow speech, when the speaker deliberately inserts those pauses. In normal speech, one typically finds many consecutive words being said with no pauses between them, and often the final sounds of one word blend smoothly or fuse with the initial sounds of the next word. The notion that speech is produced like writing, as a sequence of distinct vowels and consonants, may be a relic of alphabetic heritage for some language communities. In fact, the way vowels are produced depends on the surrounding consonants just as consonants are affected by surrounding vowels; this is called coarticulation. For example, in the word "kit", the [k] is farther forward than when we say 'caught'. But also, the vowel in "kick" is phonetically different from the vowel in "kit", though we normally do not hear this. In addition, there are language-specific changes which occur in casual speech which makes it quite different from spelling. For example, in English, the phrase "hit you" could often be more appropriately spelled "hitcha". From a decompositional perspective, in many cases, phonotactics play a part in letting speakers know where to draw word boundaries. In English, the word "strawberry" is perceived by speakers as consisting (phonetically) of two parts: "straw" and "berry". Other interpretations such as "stra" and "wberry" are inhibited by English phonotactics, which does not allow the cluster "wb" word-initially. Other such examples are "day/dream" and "mile/stone" which are unlikely to be interpreted as "da/ydream" or "mil/estone" due to the phonotactic probability or improbability of certain clusters. The sentence "Five women left", which could be phonetically transcribed as [faɪvwɪmɘnlɛft], is marked since neither /vw/ in /faɪvwɪmɘn/ nor /nl/ in /wɪmɘnlɛft/ are allowed as syllable onsets or codas in English phonotactics. These phonotactic cues often allow speakers to easily distinguish the boundaries in words. Vowel harmony in languages like Finnish can also serve to provide phonotactic cues. While the system does not allow front vowels and back vowels to exist together within one morpheme, compounds allow two morphemes to maintain their own vowel harmony while coexisting in a word. Therefore, in compounds such as "selkä/ongelma" ('back problem') where vowel harmony is distinct between two constituents in a compound, the boundary will be wherever the switch in harmony takes place—between the "ä" and the "ö" in this case. Still, there are instances where phonotactics may not aid in segmentation. Words with unclear clusters or uncontrasted vowel harmony as in "opinto/uudistus" ('student reform') do not offer phonotactic clues as to how they are segmented. From the perspective of the whole-word model, however, these words are thought be stored as full words, so the constituent parts would not necessarily be relevant to lexical recognition. == In infants and non-natives == Infants are one major focus of research in speech segmentation. Since infants have not yet acquired a lexicon capable of providing extensive contextual clues or probability-based word searches within their first year, as mentioned above, they must often rely primarily upon phonotactic and rhythmic cues (with prosody being the dominant cue), all
Portable Format for Analytics
The Portable Format for Analytics (PFA) is a JSON-based predictive model interchange format conceived and developed by Jim Pivarski. PFA provides a way for analytic applications to describe and exchange predictive models produced by analytics and machine learning algorithms. It supports common models such as logistic regression and decision trees. Version 0.8 was published in 2015. Subsequent versions have been developed by the Data Mining Group. As a predictive model interchange format developed by the Data Mining Group, PFA is complementary to the DMG's XML-based standard called the Predictive Model Markup Language or PMML. == Release history == == Data Mining Group == The Data Mining Group is a consortium managed by the Center for Computational Science Research, Inc., a nonprofit founded in 2008. == Examples == reverse array: # reverse input array of doubles input: {"type": "array", "items": "double"} output: {"type": "array", "items": "double"} action: - let: { x : input} - let: { z : input} - let: { l : {a.len: [x]}} - let: { i : l} - while : { ">=" : [i,0]} do: - set : {z : {attr: z, path : [i] , to: {attr : x ,path : [ {"-":[{"-" : [l ,i]},1]}] } } } - set : {i : {-:[i,1]}} - z Bubblesort input: {"type": "array", "items": "double"} output: {"type": "array", "items": "double"} action: - let: { A : input} - let: { N : {a.len: [A]}} - let: { n : {-:[N,1]}} - let: { i : 0} - let: { s : 0.0} - while : { ">=" : [n,0]} do : - set : { i : 0 } - while : { "<=" : [i,{-:[n,1]}]} do : - if: {">": [ {attr: A, path : [i]} , {attr: A, path:[{+:[i,1]}]} ]} then : - set : {s : {attr: A, path: [i]}} - set : {A : {attr: A, path: [i], to: {attr: A, path:[{+:[i,1]}]} } } - set : {A : {attr: A, path: [{+:[i,1]}], to: s }} - set : {i : {+:[i,1]}} - set : {n : {-:[n,1]}} - A == Implementations == Hadrian (Java/Scala/JVM) - Hadrian is a complete implementation of PFA in Scala, which can be accessed through any JVM language, principally Java. It focuses on model deployment, so it is flexible (can run in restricted environments) and fast. Titus (Python 2.x) - Titus is a complete, independent implementation of PFA in pure Python. It focuses on model development, so it includes model producers and PFA manipulation tools in addition to runtime execution. Currently, it works for Python 2. Titus 2 (Python 3.x) - Titus 2 is a fork of Titus which supports PFA implementation for Python 3. Aurelius (R) - Aurelius is a toolkit for generating PFA in the R programming language. It focuses on porting models to PFA from their R equivalents. To validate or execute scoring engines, Aurelius sends them to Titus through rPython (so both must be installed). Antinous (Model development in Jython) - Antinous is a model-producer plugin for Hadrian that allows Jython code to be executed anywhere a PFA scoring engine would go. It also has a library of model producing algorithms.
Semantic analysis (knowledge representation)
Semantic analysis is a method for eliciting and representing knowledge about organisations. Initially the problem must be defined by domain experts and passed to the project analyst(s). The next step is the generation of candidate affordances. This step will generate a list of semantic units that may be included in the schema. The candidate grouping follows where some of the semantic units that will appear in the schema are placed in simple groups. Finally the groups will be integrated together into an ontology chart. Semantic analysis always starts from the problem definition which if not clear, require the analyst to employ relevant literature, interviews with the stakeholders and other techniques towards collecting supplementary information. All assumptions made must be genuine and not limiting the system.
Thinking Machines Lab
Thinking Machines Lab Inc. is an American artificial intelligence (AI) startup founded by Mira Murati, the former chief technology officer of OpenAI. The company was founded in February 2025, and by July had completed an early-stage funding round led by Andreessen Horowitz, raising $2 billion at a valuation of $12 billion overall from investors such as Nvidia, AMD, Cisco, and Jane Street. The company is based in San Francisco and structured as a public benefit corporation. == History == By its launch in February 2025, Thinking Machines Lab was reported to have hired about 30 researchers and engineers from competitors including OpenAI, Meta AI, and Mistral AI. Its founding team members include Barret Zoph, former OpenAI VP of Research (Post-Training), Lilian Weng, former OpenAI VP, and OpenAI cofounder John Schulman, who joined after a brief stint at the lab's competitor Anthropic. In January 2026, it was reported that Barret Zoph and Luke Metz, departed the startup to return to OpenAI. Other former OpenAI employees who have been hired include Jonathan Lachman and Andrew Tulloch (although Tulloch departed after getting recruited for Meta Superintelligence Labs). Thinking Machines Lab's advisers include Bob McGrew, previously OpenAI's chief research officer, and Alec Radford, who was a lead researcher for OpenAI. On October 1, 2025, it announced Tinker, an API for fine-tuning language models. Users would submit jobs through the API for fine-tuning one of the various open-weight models supported. The Lab would run the jobs on its internal clusters and training infrastructure. == Business structure == Thinking Machines Lab grants Mira Murati a deciding vote on board matters, weighted to provide her with a majority decision-making capability. Additionally, founding shareholders possess votes weighted 100 times greater than those of regular shareholders. In July 2025, Andreessen Horowitz was reported to have led the company's initial funding round, raising "about $2 billion at a valuation of $12 billion". The government of Albania (Murati's country of origin) was also included in this round, making a $10 million investment which required an amendment to the country's 2025 budget. == Partnership == In March 2026, Thinking Machines Lab announced a strategic partnership with NVIDIA involving an undisclosed investment and a multi-year agreement to deploy one gigawatt of Vera Rubin computing capacity.
Surrogate model
A surrogate model is an engineering method used when an outcome of interest cannot be easily measured or computed, so an approximate mathematical model of the outcome is used instead. Most engineering design problems require experiments and/or simulations to evaluate design objective and constraint functions as a function of design variables. For example, in order to find the optimal airfoil shape for an aircraft wing, an engineer simulates the airflow around the wing for different shape variables (e.g., length, curvature, material, etc.). For many real-world problems, however, a single simulation can take many minutes, hours, or even days to complete. As a result, routine tasks such as design optimization, design space exploration, sensitivity analysis and "what-if" analysis become impossible since they require thousands or even millions of simulation evaluations. One way of alleviating this burden is by constructing approximation models, known as surrogate models, metamodels or emulators, that mimic the behavior of the simulation model as closely as possible while being computationally cheaper to evaluate. Surrogate models are constructed using a data-driven, bottom-up approach. The exact, inner working of the simulation code is not assumed to be known (or even understood), relying solely on the input-output behavior. A model is constructed based on modeling the response of the simulator to a limited number of intelligently chosen data points. This approach is also known as behavioral modeling or black-box modeling, though the terminology is not always consistent. When only a single design variable is involved, the process is known as curve fitting. Though using surrogate models in lieu of experiments and simulations in engineering design is more common, surrogate modeling may be used in many other areas of science where there are expensive experiments and/or function evaluations. == Goals == The scientific challenge of surrogate modeling is the generation of a surrogate that is as accurate as possible, using as few simulation evaluations as possible. The process comprises three major steps which may be interleaved iteratively: Sample selection (also known as sequential design, optimal experimental design (OED) or active learning) Construction of the surrogate model and optimizing the model parameters (i.e., bias-variance tradeoff) Appraisal of the accuracy of the surrogate. The accuracy of the surrogate depends on the number and location of samples (expensive experiments or simulations) in the design space. A systematic data representation during training can improve model scalability, thereby reducing the need for expensive simulations. Various design of experiments (DOE) techniques cater to different sources of errors, in particular, errors due to noise in the data or errors due to an improper surrogate model. == Types of surrogate models == Popular surrogate modeling approaches are: polynomial response surfaces; kriging; more generalized Bayesian approaches; gradient-enhanced kriging (GEK); radial basis function; support vector machines; space mapping; artificial neural networks and Bayesian networks. Other methods recently explored include Fourier surrogate modeling , random forests, convolutional neural networks, and generative adversarial networks. For some problems, the nature of the true function is not known a priori, and therefore it is not clear which surrogate model will be the most accurate one. In addition, there is no consensus on how to obtain the most reliable estimates of the accuracy of a given surrogate. Many other problems have known physics properties. In these cases, physics-based surrogates such as space-mapping based models are commonly used. == Invariance properties == Recently proposed comparison-based surrogate models (e.g., ranking support vector machines) for evolutionary algorithms, such as CMA-ES, allow preservation of some invariance properties of surrogate-assisted optimizers: Invariance with respect to monotonic transformations of the function (scaling) Invariance with respect to orthogonal transformations of the search space (rotation) == Applications == An important distinction can be made between two different applications of surrogate models: design optimization and design space approximation (also known as emulation). In surrogate model-based optimization, an initial surrogate is constructed using some of the available budgets of expensive experiments and/or simulations. The remaining experiments/simulations are run for designs which the surrogate model predicts may have promising performance. The process usually takes the form of the following search/update procedure. Initial sample selection (the experiments and/or simulations to be run) Construct surrogate model Search surrogate model (the model can be searched extensively, e.g., using a genetic algorithm, as it is cheap to evaluate) Run and update experiment/simulation at new location(s) found by search and add to sample Iterate steps 2 to 4 until out of time or design is "good enough" Depending on the type of surrogate used and the complexity of the problem, the process may converge on a local or global optimum, or perhaps none at all. In design space approximation, one is not interested in finding the optimal parameter vector, but rather in the global behavior of the system. Here the surrogate is tuned to mimic the underlying model as closely as needed over the complete design space. Such surrogates are a useful, cheap way to gain insight into the global behavior of the system. Optimization can still occur as a post-processing step, although with no update procedure (see above), the optimum found cannot be validated. == Surrogate modeling software == Surrogate Modeling Toolbox (SMT: https://github.com/SMTorg/smt) is a Python package that contains a collection of surrogate modeling methods, sampling techniques, and benchmarking functions. This package provides a library of surrogate models that is simple to use and facilitates the implementation of additional methods. SMT is different from existing surrogate modeling libraries because of its emphasis on derivatives, including training derivatives used for gradient-enhanced modeling, prediction derivatives, and derivatives with respect to the training data. It also includes new surrogate models that are not available elsewhere: kriging by partial-least squares reduction and energy-minimizing spline interpolation. Python library SAMBO Optimization supports sequential optimization with arbitrary models, with tree-based models and Gaussian process models built in. Surrogates.jl is a Julia packages which offers tools like random forests, radial basis methods and kriging. == Surrogate-Assisted Evolutionary Algorithms (SAEAs) == SAEAs are an advanced class of optimization techniques that integrate evolutionary algorithms (EAs) with surrogate models. In traditional EAs, evaluating the fitness of candidate solutions often requires computationally expensive simulations or experiments. SAEAs address this challenge by building a surrogate model, which is a computationally inexpensive approximation of the objective function or constraint functions. The surrogate model serves as a substitute for the actual evaluation process during the evolutionary search. It allows the algorithm to quickly estimate the fitness of new candidate solutions, thereby reducing the number of expensive evaluations needed. This significantly speeds up the optimization process, especially in cases where the objective function evaluations are time-consuming or resource-intensive. SAEAs typically involve three main steps: (1) building the surrogate model using a set of initial sampled data points, (2) performing the evolutionary search using the surrogate model to guide the selection, crossover, and mutation operations, and (3) periodically updating the surrogate model with new data points generated during the evolutionary process to improve its accuracy. By balancing exploration (searching new areas in the solution space) and exploitation (refining known promising areas), SAEAs can efficiently find high-quality solutions to complex optimization problems. They have been successfully applied in various fields, including engineering design, machine learning, and computational finance, where traditional optimization methods may struggle due to the high computational cost of fitness evaluations.
Andrej Karpathy
Andrej Karpathy (born 23 October 1986) is a Slovak-Canadian AI researcher, who co-founded and formerly worked at OpenAI, where he specialized in deep learning and computer vision. He also worked as the director of artificial intelligence and Autopilot Vision at Tesla, and in 2024 he founded Eureka Labs, an AI education platform. In 2026 he joined Anthropic as part of the pretraining team. == Education and early life == Karpathy was born in Bratislava, Czechoslovakia (now Slovakia), and moved with his family to Toronto when he was 15. He completed his Computer Science and Physics bachelor's degrees at University of Toronto in 2009 and his master's degree at University of British Columbia in 2011, where he worked on physically simulated figures (for example, a simulated runner or a simulated person in a crowd) with his adviser Michiel van de Panne. In 2006, Karpathy began posting videos on YouTube on his channel, badmephisto. He garnered fame by posting Rubik's cube tutorials which have been used by famous speedcubers such as Feliks Zemdegs. The channel has over 9 million views as of June 2025. Karpathy received a PhD from Stanford University in 2015 under the supervision of Fei-Fei Li, focusing on the intersection of natural language processing and computer vision, and deep learning models suited for this task. == Career and research == He authored and was the primary instructor of the first deep learning course at Stanford, CS 231n: Convolutional Neural Networks for Visual Recognition. The course became one of the largest classes at Stanford, growing from 150 students in 2015 to 750 in 2017. Karpathy is a founding member of the artificial intelligence research group OpenAI, where he was a research scientist from 2015 to 2017. In June 2017 he became Tesla's director of artificial intelligence and reported to Elon Musk. He was named one of MIT Technology Review's Innovators Under 35 for 2020. After taking a several-months-long sabbatical from Tesla, he announced he was leaving the company in July 2022. As of February 2023, he makes YouTube videos on how to create artificial neural networks. On February 9, 2023, Karpathy announced he was returning to OpenAI. A year later on February 13, 2024, an OpenAI spokesperson confirmed that Karpathy had left OpenAI. In the same year, he was named one of Time Magazine's 100 Most Influential People in AI. On July 16, 2024, Karpathy announced on his X account that he started a new AI education company called Eureka Labs. Their first product was the AI course, LLM101n. He also has a broader educational effort, the "Zero to Hero" series on LLM fundamentals. The company also advocates for AI teaching assistants, a concept which has been criticized due to data privacy concerns and the removal of personal connection between teacher and student. In February 2025, Karpathy coined the term vibe coding to describe how AI tools allow hobbyists to construct apps and websites just by typing prompts. On May 19, 2026, he announced that he joined Anthropic via a statement on X, while the company stated that he will be leading a team for research in pretraining.