Translating training data into target languages has proven beneficial for cross-lingual transfer. However, for structure extraction tasks, translating data requires a label projection step, which translates input text and obtains translated labels in the translated text jointly. Previous research in label projection mostly compromises translation quality by either facilitating easy identification of translated labels from translated text or using word-level alignment between translation pairs to assemble translated phrase-level labels from the aligned words. In this paper, we introduce CLAP, which first translates text to the target language and performs contextual translation on the labels using the translated text as the context, ensuring better accuracy for the translated labels. We leverage instruction-tuned language models with multilingual capabilities as our contextual translator, imposing the constraint of the presence of translated labels in the translated text via instructions. We compare CLAP with other label projection techniques for creating pseudo-training data in target languages on event argument extraction, a representative structure extraction task. Results show that CLAP improves by 2-2.5 F1-score over other methods on the Chinese and Arabic ACE05 datasets.

In modern commercial search engines and recommendation systems, data from multiple domains is available to jointly train the multi-domain model. Traditional methods train multi-domain models in the multi-task setting, with shared parameters to learn the similarity of multiple tasks, and task-specific parameters to learn the divergence of features, labels, and sample distributions of individual tasks. With the development of large language models, LLM can extract global domain-invariant text features that serve both search and recommendation tasks. We propose a novel framework called S\&R Multi-Domain Foundation, which uses LLM to extract domain invariant features, and Aspect Gating Fusion to merge the ID feature, domain invariant text features and task-specific heterogeneous sparse features to obtain the representations of query and item. Additionally, samples from multiple search and recommendation scenarios are trained jointly with Domain Adaptive Multi-Task module to obtain the multi-domain foundation model. We apply the S\&R Multi-Domain foundation model to cold start scenarios in the pretrain-finetune manner, which achieves better performance than other SOTA transfer learning methods. The S\&R Multi-Domain Foundation model has been successfully deployed in Alipay Mobile Application's online services, such as content query recommendation and service card recommendation, etc.

A key objective in field of artificial intelligence is to develop cognitive models that can exhibit human-like intellectual capabilities. One promising approach to achieving this is through neural-symbolic systems, which combine the strengths of deep learning and symbolic reasoning. However, current approaches in this area have been limited in their combining way, generalization and interpretability. To address these limitations, we propose a general bi-level probabilistic graphical reasoning framework called GBPGR. This framework leverages statistical relational learning to effectively integrate deep learning models and symbolic reasoning in a mutually beneficial manner. In GBPGR, the results of symbolic reasoning are utilized to refine and correct the predictions made by the deep learning models. At the same time, the deep learning models assist in enhancing the efficiency of the symbolic reasoning process. Through extensive experiments, we demonstrate that our approach achieves high performance and exhibits effective generalization in both transductive and inductive tasks.

The emergence of human-like abilities of AI systems for content generation in domains such as text, audio, and vision has prompted the development of classifiers to determine whether content originated from a human or a machine. Implicit in these efforts is an assumption that the generation properties of a human are different from that of the machine. In this work, we provide a framework in the language of statistical pattern recognition that quantifies the difference between the distributions of human and machine-generated content conditioned on an evaluation context. We describe current methods in the context of the framework and demonstrate how to use the framework to evaluate the progression of generative models towards human-like capabilities, among many axes of analysis.

Understanding when two pieces of text convey the same information is a goal touching many subproblems in NLP, including textual entailment and fact-checking. This problem becomes more complex when those two pieces of text are in different languages. Here, we introduce X-PARADE (Cross-lingual Paragraph-level Analysis of Divergences and Entailments), the first cross-lingual dataset of paragraph-level information divergences. Annotators label a paragraph in a target language at the span level and evaluate it with respect to a corresponding paragraph in a source language, indicating whether a given piece of information is the same, new, or new but can be inferred. This last notion establishes a link with cross-language NLI. Aligned paragraphs are sourced from Wikipedia pages in different languages, reflecting real information divergences observed in the wild. Armed with our dataset, we investigate a diverse set of approaches for this problem, including classic token alignment from machine translation, textual entailment methods that localize their decisions, and prompting of large language models. Our results show that these methods vary in their capability to handle inferable information, but they all fall short of human performance.

Mass casualty incidents (MCIs) pose a formidable challenge to emergency medical services by overwhelming available resources and personnel. Effective victim assessment is paramount to minimizing casualties during such a crisis. In this paper, we introduce ARTEMIS, an AI-driven Robotic Triage Labeling and Emergency Medical Information System. This system comprises a deep learning model for acuity labeling that is integrated with a robot, that performs the preliminary assessment of injury severity in patients and assigns appropriate triage labels. Additionally, we have developed a frontend (graphical user interface) that is updated by the robots in real time and is accessible to the first responders. To validate the reliability of our proposed algorithmic triage protocol, we employed an off-the-shelf robot kit equipped with sensors for vital sign acquisition. A controlled laboratory simulation of an MCI was conducted to assess the system's performance and effectiveness in real-world scenarios resulting in a triage-level classification accuracy of 92%. This noteworthy achievement underscores the model's proficiency in discerning crucial patterns for accurate triage classification, showcasing its promising potential in healthcare applications.

We introduce bipol, a new metric with explainability, for estimating social bias in text data. Harmful bias is prevalent in many online sources of data that are used for training machine learning (ML) models. In a step to address this challenge we create a novel metric that involves a two-step process: corpus-level evaluation based on model classification and sentence-level evaluation based on (sensitive) term frequency (TF). After creating new models to detect bias along multiple axes using SotA architectures, we evaluate two popular NLP datasets (COPA and SQUAD). As additional contribution, we created a large dataset (with almost 2 million labelled samples) for training models in bias detection and make it publicly available. We also make public our codes.

Space communications, particularly massive satellite networks, re-emerged as an appealing candidate for next generation networks due to major advances in space launching, electronics, processing power, and miniaturization. However, massive satellite networks rely on numerous underlying and intertwined processes that cannot be truly captured using conventionally used models, due to their dynamic and unique features such as orbital speed, inter-satellite links, short pass time, and satellite footprint, among others. Hence, new approaches are needed to enable the network to proactively adjust to the rapidly varying conditions associated within the link. Artificial intelligence (AI) provides a pathway to capture these processes, analyze their behavior, and model their effect on the network. This article introduces the application of AI techniques for integrated terrestrial satellite networks, particularly massive satellite network communications. It details the unique features of massive satellite networks, and the overarching challenges concomitant with their integration into the current communication infrastructure. Moreover, this article provides insights into state-of-the-art AI techniques across various layers of the communication link. This entails applying AI for forecasting the highly dynamic radio channel, spectrum sensing and classification, signal detection and demodulation, inter-satellite and satellite access network optimization, and network security. Moreover, future paradigms and the mapping of these mechanisms onto practical networks are outlined.

In recent years, a certain type of problems have become of interest where one wants to query a trained classifier. Specifically, one wants to find the closest instance to a given input instance such that the classifier's predicted label is changed in a desired way. Examples of these ``inverse classification'' problems are counterfactual explanations, adversarial examples and model inversion. All of them are fundamentally optimization problems over the input instance vector involving a fixed classifier, and it is of interest to achieve a fast solution for interactive or real-time applications. We focus on solving this problem efficiently for two of the most widely used classifiers: logistic regression and softmax classifiers. Owing to special properties of these models, we show that the optimization can be solved in closed form for logistic regression, and iteratively but extremely fast for the softmax classifier. This allows us to solve either case exactly (to nearly machine precision) in a runtime of milliseconds to around a second even for very high-dimensional instances and many classes.

The fields of soft and bio-inspired robotics promise to imbue synthetic systems with capabilities found in the natural world. However, many of these biological capabilities are yet to be realized. For example, vines in nature direct growth via localized responses embedded in the cells of vine body, allowing an organism without a central brain to successfully search for resources (e.g., light). Yet to date, vine-inspired robots have yet to show such localized embedded responsiveness. Here we present a vine-inspired robotic device with material-level responses embedded in its skin and capable of growing and steering toward either a light or heat stimulus. We present basic modeling of the concept, design details, and experimental results showing its behavior in response to infrared (IR) and visible light. Our simple design concept advances the capabilities of bio-inspired robots and lays the foundation for future growing robots that are capable of seeking light or heat, yet are extremely simple and low-cost. Potential applications include solar tracking, and in the future, firefighting smoldering fires. We envision using similar robots to find hot spots in hard-to-access environments, allowing us to put out potentially long-burning fires faster.