We introduce the concept of a \textbf{neuro-symbolic pair} -- neural and symbolic approaches that are linked through a common knowledge representation. Next, we present \textbf{taxonomic networks}, a type of discrimination network in which nodes represent hierarchically organized taxonomic concepts. Using this representation, we construct a novel neuro-symbolic pair and evaluate its performance. We show that our symbolic method learns taxonomic nets more efficiently with less data and compute, while the neural method finds higher-accuracy taxonomic nets when provided with greater resources. As a neuro-symbolic pair, these approaches can be used interchangeably based on situational needs, with seamless translation between them when necessary. This work lays the foundation for future systems that more fundamentally integrate neural and symbolic computation.

This paper explores null elements in English, Chinese, and Korean Penn treebanks. Null elements contain important syntactic and semantic information, yet they have typically been treated as entities to be removed during language processing tasks, particularly in constituency parsing. Thus, we work towards the removal and, in particular, the restoration of null elements in parse trees. We focus on expanding a rule-based approach utilizing linguistic context information to Chinese, as rule based approaches have historically only been applied to English. We also worked to conduct neural experiments with a language agnostic sequence-to-sequence model to recover null elements for English (PTB), Chinese (CTB) and Korean (KTB). To the best of the authors' knowledge, null elements in three different languages have been explored and compared for the first time. In expanding a rule based approach to Chinese, we achieved an overall F1 score of 80.00, which is comparable to past results in the CTB. In our neural experiments we achieved F1 scores up to 90.94, 85.38 and 88.79 for English, Chinese, and Korean respectively with functional labels.

Spell-checkers are valuable tools that enhance communication by identifying misspelled words in written texts. Recent improvements in deep learning, and in particular in large language models, have opened new opportunities to improve traditional spell-checkers with new functionalities that not only assess spelling correctness but also the suitability of a word for a given context. In our work, we present and compare two new spell-checkers and evaluate them on synthetic, learner, and more general-domain Slovene datasets. The first spell-checker is a traditional, fast, word-based approach, based on a morphological lexicon with a significantly larger word list compared to existing spell-checkers. The second approach uses a language model trained on a large corpus with synthetically inserted errors. We present the training data construction strategies, which turn out to be a crucial component of neural spell-checkers. Further, the proposed neural model significantly outperforms all existing spell-checkers for Slovene in both precision and recall.

Shapley Values are concepts established for eXplainable AI. They are used to explain black-box predictive models by quantifying the features' contributions to the model's outcomes. Since computing the exact Shapley Values is known to be computationally intractable on real-world datasets, neural estimators have emerged as alternative, more scalable approaches to get approximated Shapley Values estimates. However, experiments with neural estimators are currently hard to replicate as algorithm implementations, explainer evaluators, and results visualizations are neither standardized nor promptly usable. To bridge this gap, we present BONES, a new benchmark focused on neural estimation of Shapley Value. It provides researchers with a suite of state-of-the-art neural and traditional estimators, a set of commonly used benchmark datasets, ad hoc modules for training black-box models, as well as specific functions to easily compute the most popular evaluation metrics and visualize results. The purpose is to simplify XAI model usage, evaluation, and comparison. In this paper, we showcase BONES results and visualizations for XAI model benchmarking on both tabular and image data. The open-source library is available at the following link: https://github.com/DavideNapolitano/BONES.

Code comments are important for developers in program comprehension. In scenarios of comprehending and reusing a method, developers expect code comments to provide supplementary information beyond the method signature. However, the extent of such supplementary information varies a lot in different code comments. In this paper, we raise the awareness of the supplementary nature of method-level comments and propose a new metric named MESIA (Mean Supplementary Information Amount) to assess the extent of supplementary information that a code comment can provide. With the MESIA metric, we conduct experiments on a popular code-comment dataset and three common types of neural approaches to generate method-level comments. Our experimental results demonstrate the value of our proposed work with a number of findings. (1) Small-MESIA comments occupy around 20% of the dataset and mostly fall into only the WHAT comment category. (2) Being able to provide various kinds of essential information, large-MESIA comments in the dataset are difficult for existing neural approaches to generate. (3) We can improve the capability of existing neural approaches to generate large-MESIA comments by reducing the proportion of small-MESIA comments in the training set. (4) The retrained model can generate large-MESIA comments that convey essential meaningful supplementary information for methods in the small-MESIA test set, but will get a lower BLEU score in evaluation. These findings indicate that with good training data, auto-generated comments can sometimes even surpass human-written reference comments, and having no appropriate ground truth for evaluation is an issue that needs to be addressed by future work on automatic comment generation.

A self-organizing Hopfield network has been developed in the context of Vector Ouantiza(cid:173) -tion, aiming at compression of television images. The metastable states of the spin glass-like network are used as an extra the Minimal Overlap storage resource using and Mezard 1987) to rule (Krauth learning the organization of the attractors.

Graph partitioning aims to divide a graph into $k$ disjoint subsets while optimizing a specific partitioning objective. The majority of formulations related to graph partitioning exhibit NP-hardness due to their combinatorial nature. As a result, conventional approximation algorithms rely on heuristic methods, sometimes with approximation guarantees and sometimes without. Unfortunately, traditional approaches are tailored for specific partitioning objectives and do not generalize well across other known partitioning objectives from the literature. To overcome this limitation, and learn heuristics from the data directly, neural approaches have emerged, demonstrating promising outcomes. In this study, we extend this line of work through a novel framework, NeuroCut. NeuroCut introduces two key innovations over prevailing methodologies. First, it is inductive to both graph topology and the partition count, which is provided at query time. Second, by leveraging a reinforcement learning based framework over node representations derived from a graph neural network, NeuroCut can accommodate any optimization objective, even those encompassing non-differentiable functions. Through empirical evaluation, we demonstrate that NeuroCut excels in identifying high-quality partitions, showcases strong generalization across a wide spectrum of partitioning objectives, and exhibits resilience to topological modifications.

Providing access to information across languages has been a goal of Information Retrieval (IR) for decades. While progress has been made on Cross Language IR (CLIR) where queries are expressed in one language and documents in another, the multilingual (MLIR) task to create a single ranked list of documents across many languages is considerably more challenging. This paper investigates whether advances in neural document translation and pretrained multilingual neural language models enable improvements in the state of the art over earlier MLIR techniques. The results show that although combining neural document translation with neural ranking yields the best Mean Average Precision (MAP), 98% of that MAP score can be achieved with an 84% reduction in indexing time by using a pretrained XLM-R multilingual language model to index documents in their native language, and that 2% difference in effectiveness is not statistically significant. Key to achieving these results for MLIR is to fine-tune XLM-R using mixed-language batches from neural translations of MS MARCO passages.

In a previous module, we examined language models and explored n-gram and neural approaches. We found that the n-gram approach is generally better for higher values of N but this may be constrained by available compute resources. There was also the concern about the lack of representation for n-grams not present in the training corpus. On the other hand, applying subword tokenization methods such as Byte Pair Encoding and Wordpiece, recent neural approaches are able to resolve the issues with n-gram language models and show impressive results. We also traced the development of neural language models from feedforward networks that rely on word embeddings and fixed input length to recurrent neural networks which allowed for variable length input but struggled to capture long term dependencies.

There are many things that distinguish humans from other species, but one of the most important is language. The ability to string together various elements in essentially infinite combinations is a trait that "has often in the past been considered to be the core defining feature of modern humans, the source of human creativity, cultural enrichment, and complex social structure," as linguist Noam Chomsky once said. But as important as language has been in the evolution of humans, there is still much we don't know about how language has evolved. While dead languages like Latin have a wealth of written records and descendants through which we can better understand it, some languages are lost to history. Researchers have been able to reconstruct some lost languages, but the process of deciphering them can be a long one.