There has been an increasing interest in incorporating Artificial Intelligence (AI) into Defence and military systems to complement and augment human intelligence and capabilities. However, much work still needs to be done toward achieving an effective human-machine partnership. This work is aimed at enhancing human-machine communications by developing a capability for automatically translating human natural language into a machine-understandable language (e.g., SQL queries). Techniques toward achieving this goal typically involve building a semantic parser trained on a very large amount of high-quality manually-annotated data. However, in many real-world Defence scenarios, it is not feasible to obtain such a large amount of training data. To the best of our knowledge, there are few works trying to explore the possibility of training a semantic parser with limited manually-paraphrased data, in other words, zero-shot. In this paper, we investigate how to exploit paraphrasing methods for the automated generation of large-scale training datasets (in the form of paraphrased utterances and their corresponding logical forms in SQL format) and present our experimental results using real-world data in the maritime domain.

Semantic medical image segmentation using deep learning has recently achieved high accuracy, making it appealing to clinical problems such as radiation therapy. However, the lack of high-quality semantically labelled data remains a challenge leading to model brittleness to small shifts to input data. Most works require extra data for semi-supervised learning and lack the interpretability of the boundaries of the training data distribution during training, which is essential for model deployment in clinical practice. We propose a fully supervised generative framework that can achieve generalisable segmentation with only limited labelled data by simultaneously constructing an explorable manifold during training. The proposed approach creates medical image style paired with a segmentation task driven discriminator incorporating end-to-end adversarial training. The discriminator is generalised to small domain shifts as much as permissible by the training data, and the generator automatically diversifies the training samples using a manifold of input features learnt during segmentation. All the while, the discriminator guides the manifold learning by supervising the semantic content and fine-grained features separately during the image diversification. After training, visualisation of the learnt manifold from the generator is available to interpret the model limits. Experiments on a fully semantic, publicly available pelvis dataset demonstrated that our method is more generalisable to shifts than other state-of-the-art methods while being more explainable using an explorable manifold.

Path prediction is an essential task for many real-world Cyber-Physical Systems (CPS) applications, from autonomous driving and traffic monitoring/management to pedestrian/worker safety. These real-world CPS applications need a robust, lightweight path prediction that can provide a universal network architecture for multiple subjects (e.g., pedestrians and vehicles) from different perspectives. However, most existing algorithms are tailor-made for a unique subject with a specific camera perspective and scenario. This article presents Pishgu, a universal lightweight network architecture, as a robust and holistic solution for path prediction. Pishgu's architecture can adapt to multiple path prediction domains with different subjects (vehicles, pedestrians), perspectives (bird's-eye, high-angle), and scenes (sidewalk, highway). Our proposed architecture captures the inter-dependencies within the subjects in each frame by taking advantage of Graph Isomorphism Networks and the attention module. We separately train and evaluate the efficacy of our architecture on three different CPS domains across multiple perspectives (vehicle bird's-eye view, pedestrian bird's-eye view, and human high-angle view). Pishgu outperforms state-of-the-art solutions in the vehicle bird's-eye view domain by 42% and 61% and pedestrian high-angle view domain by 23% and 22% in terms of ADE and FDE, respectively. Additionally, we analyze the domain-specific details for various datasets to understand their effect on path prediction and model interpretation. Finally, we report the latency and throughput for all three domains on multiple embedded platforms showcasing the robustness and adaptability of Pishgu for real-world integration into CPS applications.

The extent to which text-only language models (LMs) learn to represent features of the non-linguistic world is an open question. Prior work has shown that pretrained LMs can be taught to caption images when a vision model's parameters are optimized to encode images in the language space. We test a stronger hypothesis: that the conceptual representations learned by frozen text-only models and vision-only models are similar enough that this can be achieved with a linear map. We show that the image representations from vision models can be transferred as continuous prompts to frozen LMs by training only a single linear projection. Using these to prompt the LM achieves competitive performance on captioning and visual question answering tasks compared to models that tune both the image encoder and text decoder (such as the MAGMA model). We compare three image encoders with increasing amounts of linguistic supervision seen during pretraining: BEIT (no linguistic information), NF-ResNET (lexical category information), and CLIP (full natural language descriptions). We find that all three encoders perform equally well at transferring visual property information to the language model (e.g., whether an animal is large or small), but that image encoders pretrained with linguistic supervision more saliently encode category information (e.g., distinguishing hippo vs. elephant) and thus perform significantly better on benchmark language-and-vision tasks. Our results indicate that LMs encode conceptual information structurally similarly to vision-based models, even those that are solely trained on images. Code is available here: https://github.com/jmerullo/limber

While current dialogue systems like ChatGPT have made significant advancements in text-based interactions, they often overlook the potential of other modalities in enhancing the overall user experience. We present FaceChat, a web-based dialogue framework that enables emotionally-sensitive and face-to-face conversations. By seamlessly integrating cutting-edge technologies in natural language processing, computer vision, and speech processing, FaceChat delivers a highly immersive and engaging user experience. FaceChat framework has a wide range of potential applications, including counseling, emotional support, and personalized customer service. The system is designed to be simple and flexible as a platform for future researchers to advance the field of multimodal dialogue systems. The code is publicly available at https://github.com/qywu/FaceChat.

Reinforcement learning has been applied to various real-world tasks, including robotic manipulation with large state-action spaces and sparse reward signals [1]. In these tasks, standard reinforcement learning tends to perform a lot of useless exploration and easily fall into local optimal solutions. To eliminate this problem, previous works often use expert demonstrations to aid online learning, which adopt some successful trajectories to guide the exploration process [2, 3]. However, standard learning from demonstration algorithms often assume that the target leaning task is exactly same with the task where demonstrations are collected [4, 5, 6]. Under this assumption, experts need to collect the corresponding demonstration for each new task, which can be expensive and inefficient. In this paper, we consider a new learning setting where expert data is collected under a single task, while the agent is required to solve different new tasks. For instance as shown in Figure 1, a robot arm aims to solve peg-in-hole tasks.The demonstration is collected on a certain type of hole while the target tasks have different hole shapes (changes in environmental dynamics) or position shifts (changes in reward function). This can be challenging as agents cannot directly imitate those demonstrations from mismatched tasks due to dynamics and reward function changes. However, compared to learning from scratch, those demonstrations should still be able to provide some useful information to help exploration.

This paper proposes a sketching strategy based on spherical designs, which is applied to the classical spherical basis function approach for massive spherical data fitting. We conduct theoretical analysis and numerical verifications to demonstrate the feasibility of the proposed { sketching} strategy. From the theoretical side, we prove that sketching based on spherical designs can reduce the computational burden of the spherical basis function approach without sacrificing its approximation capability. In particular, we provide upper and lower bounds for the proposed { sketching} strategy to fit noisy data on spheres. From the experimental side, we numerically illustrate the feasibility of the sketching strategy by showing its comparable fitting performance with the spherical basis function approach. These interesting findings show that the proposed sketching strategy is capable of fitting massive and noisy data on spheres.

Convolution is one of the most computationally intensive operations that must be performed for machine-learning model inference. A traditional approach to compute convolutions is known as the Im2Col + BLAS method. This paper proposes SConv: a direct-convolution algorithm based on a MLIR/LLVM code-generation toolchain that can be integrated into machine-learning compilers . This algorithm introduces: (a) Convolution Slicing Analysis (CSA) - a convolution-specific 3D cache-blocking analysis pass that focuses on tile reuse over the cache hierarchy; (b) Convolution Slicing Optimization (CSO) - a code-generation pass that uses CSA to generate a tiled direct-convolution macro-kernel; and (c) Vector-Based Packing (VBP) - an architecture-specific optimized input-tensor packing solution based on vector-register shift instructions for convolutions with unitary stride. Experiments conducted on 393 convolutions from full ONNX-MLIR machine-learning models indicate that the elimination of the Im2Col transformation and the use of fast packing routines result in a total packing time reduction, on full model inference, of 2.0x - 3.9x on Intel x86 and 3.6x - 7.2x on IBM POWER10. The speed-up over an Im2Col + BLAS method based on current BLAS implementations for end-to-end machine-learning model inference is in the range of 9% - 25% for Intel x86 and 10% - 42% for IBM POWER10 architectures. The total convolution speedup for model inference is 12% - 27% on Intel x86 and 26% - 46% on IBM POWER10. SConv also outperforms BLAS GEMM, when computing pointwise convolutions, in more than 83% of the 219 tested instances.

Entity Set Expansion (ESE) is a valuable task that aims to find entities of the target semantic class described by given seed entities. Various Natural Language Processing (NLP) and Information Retrieval (IR) downstream applications have benefited from ESE due to its ability to discover knowledge. Although existing corpus-based ESE methods have achieved great progress, they still rely on corpora with high-quality entity information annotated, because most of them need to obtain the context patterns through the position of the entity in a sentence. Therefore, the quality of the given corpora and their entity annotation has become the bottleneck that limits the performance of such methods. To overcome this dilemma and make the ESE models free from the dependence on entity annotation, our work aims to explore a new ESE paradigm, namely corpus-independent ESE. Specifically, we devise a context pattern generation module that utilizes autoregressive language models (e.g., GPT-2) to automatically generate high-quality context patterns for entities. In addition, we propose the GAPA, a novel ESE framework that leverages the aforementioned GenerAted PAtterns to expand target entities. Extensive experiments and detailed analyses on three widely used datasets demonstrate the effectiveness of our method. All the codes of our experiments are available at https://github.com/geekjuruo/GAPA.

Understanding the meaning of words in context is fundamental for reading comprehension. The perceived difficulty, hereafter referred to as complexity, of a target word within a given text varies widely among readers. With an increased demand for distance learning and educational technologies[107], research into automatically predicting which words are likely to cause comprehension problems is becoming a popular area of research [115, 147, 185]. Systems have been created to identify complex words that are difficult to acquire, reproduce, or understand for children [79], second-language learners [89], people suffering from a reading disability, such as dyslexia [131] or aphasia [35, 53], or more generally, individuals with low literacy [59, 175]. In Computational Linguistics and Natural Language Processing (NLP), the task of automatically recognizing complex words is most often achieved by training machine learning (ML) models. These ML models assign a complexity value to each target word within an inputted extract, sentence, or text that allows for the identification of complex words. This information can then be used to improve downstream lexical and text simplification systems that provide simpler alternatives to aid reading comprehension. Take the extract shown in Table 1 for example.