Semitic morphologically-rich languages (MRLs) are characterized by extreme word ambiguity.Because most vowels are omitted in standard texts, many of the words are homographs with multiple possible analyses, each with a different pronunciation and different morphosyntactic properties.This ambiguity goes beyond word-sense disambiguation (WSD), and may include token segmentation into multiple word units.Previous research on MRLs claimed that standardly trained pre-trained language models (PLMs) based on word-pieces may not sufficiently capture the internal structure of such tokens in order to distinguish between these analyses.Taking Hebrew as a case study, we investigate the extent to which Hebrew homographs can be disambiguated and analyzed using PLMs.We evaluate all existing models for contextualized Hebrew embeddings on a novel Hebrew homograph challenge sets that we deliver.Our empirical results demonstrate that contemporary Hebrew contextualized embeddings outperform non-contextualized embeddings; and that they are most effective for disambiguating segmentation and morphosyntactic features, less so regarding pure word-sense disambiguation.We show that these embeddings are more effective when the number of word-piece splits is limited, and they are more effective for 2-way and 3-way ambiguities than for 4-way ambiguity.We show that the embeddings are equally effective for homographs of both balanced and skewed distributions, whether calculated as masked or unmasked tokens.Finally, we show that these embeddings are as effective for homograph disambiguation with extensive supervised training as with a few-shot setup.

We have developed Brain-Voyant, an efficient general-purpose machine learning tool for real-time functional magnetic resonance imaging classification using whole-brain data, which can be used to explore novel brain-computer interface paradigms or advanced neurofeedback protocols. We have created a convenient and configurable front-end tool that receives fMRI-based multi-voxel raw brain data as input. Our tool processes, analyses, classifies and transfers the classification to an external object such as a virtual avatar or a humanoid robot in real-time. Our tool is focused on minimizing delay time, and to that end, it employs a method that is based on examining in advance the voxels that have been found to be task-relevant in the machine learning model training phase. The tool's code base was designed to be easily extended to support additional feature reduction, normalization and classification algorithms. This tool was used in several published studies using motor execution, motor imagery, and visual category classification in cue-based and free-choice brain-computer interface experiments, with both healthy and amputated subjects. This tool is not limited by number of classes, is not limited to predefined regions of interest, and classifier instances can run in parallel to combine multiple classification tasks in real time. Finally, our tool is able use the slow peaking blood-oxygen-level dependent signal to classify our subjects' intention during the two-second window TR. We release this tool as open-source for non-commercial usage.

We discuss a real‐world application of a recently proposed machine learning method for authorship verification. Authorship verification is considered an extremely difficult task in computational text classification, because it does not assume that the correct author of an anonymous text is included in the candidate authors available. To determine whether 2 documents have been written by the same author, the verification method discussed uses repeated feature subsampling and a pool of impostor authors. We use this technique to attribute a newly discovered Latin text from antiquity (the Compendiosa expositio) to Apuleius. This North African writer was one of the most important authors of the Roman Empire in the 2nd century and authored one of the world's first novels. This attribution has profound and wide‐reaching cultural value, because it has been over a century since a new text by a major author from antiquity was discovered. This research therefore illustrates the rapidly growing potential of computational methods for studying the global textual heritage.

We show how automatically extracted citations in historical corpora can be used to measure the direct and indirect influence of authors on each other. These measures can in turn be used to determine an author's overall prominence in the corpus and to identify distinct schools of thought. We apply our methods to two major historical corpora. Using scholarly consensus as a gold standard, we demonstrate empirically the superiority of indirect influence over direct influence as a basis for various measures of authorial impact.

Almost any conceivable authorship attribution problem can be reduced to one fundamental problem: whether a pair of (possibly short) documents were written by the same author. In this article, we offer an (almost) unsupervised method for solving this problem with surprisingly high accuracy. The main idea is to use repeated feature subsampling methods to determine if one document of the pair allows us to select the other from among a background set of “impostors” in a sufficiently robust manner.

This paper demonstrates the use of genetic algorithms for evolving: 1) a grandmaster-level evaluation function, and 2) a search mechanism for a chess program, the parameter values of which are initialized randomly. The evaluation function of the program is evolved by learning from databases of (human) grandmaster games. At first, the organisms are evolved to mimic the behavior of human grandmasters, and then these organisms are further improved upon by means of coevolution. The search mechanism is evolved by learning from tactical test suites. Our results show that the evolved program outperforms a two-time world computer chess champion and is at par with the other leading computer chess programs.

Full natural language understanding requires identifying and analyzing the meanings of metaphors, which are ubiquitous in both text and speech. Over the last thirty years, linguistic metaphors have been shown to be based on more general conceptual metaphors, partial semantic mappings between disparate conceptual domains. Though some achievements have been made in identifying linguistic metaphors over the last decade or so, little work has been done to date on automatically identifying conceptual metaphors. This paper describes research on identifying conceptual metaphors based on corpus data. Our method uses as little background knowledge as possible, to ease transfer to new languages and to mini- mize any bias introduced by the knowledge base construction process. The method relies on general heuristics for identifying linguistic metaphors and statistical clustering (guided by Wordnet) to form conceptual metaphor candidates. Human experiments show the system effectively finds meaningful conceptual metaphors.

The identification of pseudepigraphic textstexts not written by the authors to which they are attributedhas important historical, forensic and commercial applications.We introduce an unsupervised technique for identifying pseudepigrapha.The idea is to identify textual outliers in a corpus based on the pairwise similarities of all documents in the corpus.The crucial point is that document similarity not be measured in any of the standard ways but rather be based on the output of a recently introduced algorithm for authorship verification.The proposed method strongly outperforms existing techniques in systematic experiments on a blog corpus.

Work on authorship attribution has traditionally focused on long texts.In this work, we tackle the question of whether the author of a very short text can be successfully identified.We use Twitter as an experimental testbed.We introduce the concept of an author's unique "signature", and show that such signatures are typical of many authors when writing very short texts.We also present a new authorship attribution feature ("flexible patterns") and demonstrate a significant improvement over our baselines.Our results show that the author of a single tweet can be identified with good accuracy in an array of flavors of the authorship attribution task.

Given an unsegmented multi‐author text, we wish to automatically separate out distinct authorial threads. We present a novel, entirely unsupervised, method that achieves strong results on multiple testbeds, including those for which authorial threads are topically identical. Unlike previous work, our method requires no specialized linguistic tools and can be easily applied to any text.

This paper demonstrates the use of genetic algorithms for evolving a grandmaster-level evaluation function for a chess program. This is achieved by combining supervised and unsupervised learning. In the supervised learning phase the organisms are evolved to mimic the behavior of human grandmasters, and in the unsupervised learning phase these evolved organisms are further improved upon by means of coevolution.

We show how an Arabic language religious-political document can be automatically classified according to the ideological stream and organizational affiliation that it represents. Tests show that our methods achieve near-perfect accuracy.

Abstract Statistical authorship attribution has a long history, culminating in the use of modern machine learning classification methods. Nevertheless, most of this work suffers from the limitation of assuming a small closed set of candidate authors and essentially unlimited training text for each. Real‐life authorship attribution problems, however, typically fall short of this ideal. Thus, following detailed discussion of previous work, three scenarios are considered here for which solutions to the basic attribution problem are inadequate. In the first variant, the profiling problem, there is no candidate set at all; in this case, the challenge is to provide as much demographic or psychological information as possible about the author. In the second variant, the needle‐in‐a‐haystack problem, there are many thousands of candidates for each of whom we might have a very limited writing sample. In the third variant, the verification problem, there is no closed candidate set but there is one suspect; in this case, the challenge is to determine if the suspect is or is not the author. For each variant, it is shown how machine learning methods can be adapted to handle the special challenges of that variant.

In this paper we demonstrate how genetic algorithms can be used to reverse engineer an evaluation function's parameters for computer chess. Our results show that using an appropriate mentor, we can evolve a program that is on par with top tournament-playing chess programs, outperforming a two-time World Computer Chess Champion. This performance gain is achieved by evolving a program with a smaller number of parameters in its evaluation function to mimic the behavior of a superior mentor which uses a more extensive evaluation function. In principle, our mentor-assisted approach could be used in a wide range of problems for which appropriate mentors are available.

This paper presents a simplified post-classification framework for enhancing the performance of a given speaker recognition classifier by means of other “auxiliary ” classifiers. We call it Virtual Fusion, since the assisting classifiers are used only for training the post-classifier and are not necessary in operating mode. Experiments performed using Nist’04 and ’05 evaluations suggest that the proposed technique is able to consistently improve the EER of a typical GMM-cepstrum classifier by up to 15%. Index Terms: speaker recognition, fusion, post-classifier. 1.

This paper proposes a method for automatic correction of bias in speaker recognition systems, especially fusion-based systems. The method is based on a post-classifier which learns the relative performance obtained by the constituent systems in key trials, given the training and testing conditions in which they occurred. These conditions generally reflect train/test mismatch in factors such as channel, noise, speaker stress, etc. Results obtained with several state-of-the-art systems showed up to 20% decrease in EER compared to ordinary fusion in the NIST'05 Speaker Recognition Evaluation.

In this paper, we use a blog corpus to demonstrate that we can often identify the author of an anonymous text even where there are many thousands of candidate authors. Our approach combines standard information retrieval methods with a text categorization meta-learning scheme that determines when to even venture a guess.

Most research on learning to identify sentiment ignores “neutral” examples, learning only from examples of significant (positive or negative) polarity. We show that it is crucial to use neutral examples in learning polarity for a variety of reasons. Learning from negative and positive examples alone will not permit accurate classification of neutral examples. Moreover, the use of neutral training examples in learning facilitates better distinction between positive and negative examples.

Abstract We introduce a new measure on linguistic features, called stability, which captures the extent to which a language element such as a word or a syntactic construct is replaceable by semantically equivalent elements. This measure may be perceived as quantifying the degree of available “synonymy” for a language item. We show that frequent, but unstable, features are especially useful as discriminators of an author's writing style.

This paper emphasizes the benefits of embedding data categorization within fusion of classifiers for text-independent speaker verification. A selective fusion framework is presented which considers data idiosyncrasies by assigning particular test samples to appropriate fusion schemes. As an extension, incompatible data can be spotted and excluded from inherent classification errors. In addition, it’s shown that multi-resolution low-level classifiers successfully boost fusion capabilities in noise. 1.

In this paper, we show that stylistic text features can be exploited to determine an anonymous author's native language with high accuracy. Specifically, we first use automatic tools to ascertain frequencies of various stylistic idiosyncrasies in a text. These frequencies then serve as features for support vector machines that learn to classify texts according to author native language.

In the authorship verification problem, we are given examples of the writing of a single author and are asked to determine if given long texts were or were not written by this author. We present a new learning-based method for adducing the "depth of difference" between two example sets and offer evidence that this method solves the authorship verification problem with very high accuracy. The underlying idea is to test the rate of degradation of the accuracy of learned models as the best features are iteratively dropped from the learning process.

In this paper we consider the problem of `theory patching', in which we are given a domain theory, some of whose components are indicated to be possibly flawed, and a set of labeled training examples for the domain concept. The theory patching problem is to revise only the indicated components of the theory, such that the resulting theory correctly classifies all the training examples. Theory patching is thus a type of theory revision in which revisions are made to individual components of the theory. Our concern in this paper is to determine for which classes of logical domain theories the theory patching problem is tractable. We consider both propositional and first-order domain theories, and show that the theory patching problem is equivalent to that of determining what information contained in a theory is `stable' regardless of what revisions might be performed to the theory. We show that determining stability is tractable if the input theory satisfies two conditions: that revisions to each theory component have monotonic effects on the classification of examples, and that theory components act independently in the classification of examples in the theory. We also show how the concepts introduced can be used to determine the soundness and completeness of particular theory patching algorithms.

The theory revision problem is the problem of how best to go about revising a deficient domain theory using information contained in examples that expose inaccuracies. In this paper we present our approach to the theory revision problem for propositional domain theories. The approach described here, called PTR, uses probabilities associated with domain theory elements to numerically track the ``flow'' of proof through the theory. This allows us to measure the precise role of a clause or literal in allowing or preventing a (desired or undesired) derivation for a given example. This information is used to efficiently locate and repair flawed elements of the theory. PTR is proved to converge to a theory which correctly classifies all examples, and shown experimentally to be fast and accurate even for deep theories.