We present labeled morphological segmentation, an alternative view of morphological processing that unifies several tasks. From an annotation standpoint, we additionally introduce a new hierarchy of morphotactic tagsets. Finally, we develop \modelname, a discriminative morphological segmentation system that, contrary to previous work, explicitly models morphotactics. We show that \textsc{chipmunk} yields improved performance on three tasks for all six languages: (i) morphological segmentation, (ii) stemming and (iii) morphological tag classification. On morphological segmentation, our method shows absolute improvements of 2--6 points $F_1$ over the baseline.

Recently, Bonaventure Dossou learned of an alarming tendency in a popular AI model. The program described Fon--a language spoken by Dossou's mother and millions of others in Benin and neighboring countries--as "a fictional language." This result, which I replicated, is not unusual. Dossou is accustomed to the feeling that his culture is unseen by technology that so easily serves other people. He grew up with no Wikipedia pages in Fon, and no translation programs to help him communicate with his mother in French, in which he is more fluent.

South Africa's Aerobotics is utilizing artificial intelligence (AI) in helping fruit and nut farmers in over 18 countries. JOHANNESBURG - South Africa's Aerobotics is utilizing artificial intelligence (AI) in helping fruit and nut farmers improve crop yields. Although the Cape Town-based company only started nine years ago, it is already operating in 18 countries, with the U.S. being their largest market, followed by South Africa, Australia, Spain and Portugal. Its customers produce tens of millions of tons of fresh produce every year. California is now ground zero for Aerobotics – where the company has the biggest concentration of customers.

Blocking events are an important cause of extreme weather, especially long-lasting blocking events that trap weather systems in place. The duration of blocking events is, however, underestimated in climate models. Explainable Artificial Intelligence are a class of data analysis methods that can help identify physical causes of prolonged blocking events and diagnose model deficiencies. We demonstrate this approach on an idealized quasigeostrophic model developed by Marshall and Molteni (1993). We train a convolutional neural network (CNN), and subsequently, build a sparse predictive model for the persistence of Atlantic blocking, conditioned on an initial high-pressure anomaly. Shapley Additive ExPlanation (SHAP) analysis reveals that high-pressure anomalies in the American Southeast and North Atlantic, separated by a trough over Atlantic Canada, contribute significantly to prediction of sustained blocking events in the Atlantic region. This agrees with previous work that identified precursors in the same regions via wave train analysis. When we apply the same CNN to blockings in the ERA5 atmospheric reanalysis, there is insufficient data to accurately predict persistent blocks. We partially overcome this limitation by pre-training the CNN on the plentiful data of the Marshall-Molteni model, and then using Transfer Learning to achieve better predictions than direct training. SHAP analysis before and after transfer learning allows a comparison between the predictive features in the reanalysis and the quasigeostrophic model, quantifying dynamical biases in the idealized model. This work demonstrates the potential for machine learning methods to extract meaningful precursors of extreme weather events and achieve better prediction using limited observational data.

As artificial intelligence (AI) continues to penetrate ever deeper into modern life, one particular family of machine learning algorithms--namely, deep neural networks--have come to be seen as the solution to many of the challenges that have stumped more classical algorithms in the past. Modeled loosely on the structure of biological neural networks, artificial neural networks consist of chains of simple mathematical transformations that can model complex non-linear decision boundaries in large problem spaces. In particular, deep neural networks--artificial neural networks that consist of multiple layers of transformations--allow for sufficient complexity to tackle tasks in a wide variety of fields. These models are collectively and more colloquially referred to as deep learning. A growing body of education researchers are now also turning their attention to leveraging the power of deep learning algorithms for the tasks of improving and understanding human learning. Researchers in educational data science, a field consisting of various interrelated research communities such as Educational Data Mining (EDM), Learning Analytics (LA), and AI in Education (AIED), have been involved in this endeavor.

Land cover classification and change detection are two important applications of remote sensing and Earth observation (EO) that have benefited greatly from the advances in deep learning. Convolutional and transformer-based U-net models are the state-of-the-art architectures for these tasks, and their performances have been boosted by an increased availability of large-scale annotated EO datasets. However, the influence of different visual characteristics of the input EO data on a model's predictions is not well understood. In this work we systematically examine model sensitivities with respect to several color-and texture-based distortions on the input EO data during inference, given models that have been trained without such distortions. We conduct experiments with multiple state-of-the-art segmentation networks for land cover classification and show that they are in general more sensitive to texture than to color distortions. Beyond revealing intriguing characteristics of widely used land cover classification models, our results can also be used to guide the development of more robust models within the EO domain. Land cover classification is a key application for remote sensing and Earth observation (EO) data, as it provides essential information for various domains, such as urban planning, environmental monitoring, disaster management, and agriculture.

Earth system models (ESMs) are the principal tools used in climate science to generate future climate projections under various atmospheric emissions scenarios on a global or regional scale. Generative deep learning approaches are suitable for emulating these tools due to their computational efficiency and ability, once trained, to generate realizations in a fraction of the time required by ESMs. We extend previous work that used a generative probabilistic diffusion model to emulate ESMs by targeting the joint emulation of multiple variables, temperature and precipitation, by a single diffusion model. Joint generation of multiple variables is critical to generate realistic samples of phenomena resulting from the interplay of multiple variables. The diffusion model emulator takes in the monthly mean-maps of temperature and precipitation and produces the daily values of each of these variables that exhibit statistical properties similar to those generated by ESMs. Our results show the outputs from our extended model closely resemble those from ESMs on various climate metrics including dry spells and hot streaks, and that the joint distribution of temperature and precipitation in our sample closely matches those of ESMs.

This paper presents a new approach to evaluating the quality of answers in political question-and-answer sessions. We propose to measure an answer's quality based on the degree to which it allows us to infer the initial question accurately. This conception of answer quality inherently reflects their relevance to initial questions. Drawing parallels with semantic search, we argue that this measurement approach can be operationalized by fine-tuning a large language model on the observed corpus of questions and answers without additional labeled data. We showcase our measurement approach within the context of the Question Period in the Canadian House of Commons. Our approach yields valuable insights into the correlates of the quality of answers in the Question Period. We find that answer quality varies significantly based on the party affiliation of the members of Parliament asking the questions and uncover a meaningful correlation between answer quality and the topics of the questions.

Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing. While there have been remarkable improvements in model accuracy, deploying these models on lightweight devices, such as mobile phones and microcontrollers, is constrained by limited resources. In this survey, we provide comprehensive design guidance tailored for these devices, detailing the meticulous design of lightweight models, compression methods, and hardware acceleration strategies. The principal goal of this work is to explore methods and concepts for getting around hardware constraints without compromising the model's accuracy. Additionally, we explore two notable paths for lightweight deep learning in the future: deployment techniques for TinyML and Large Language Models. Although these paths undoubtedly have potential, they also present significant challenges, encouraging research into unexplored areas.

Large-scale multilingual Pretrained Language Models (mPLMs) yield impressive performance on cross-language tasks, yet significant performance disparities exist across different languages within the same mPLM. Previous studies endeavored to narrow these disparities by supervise fine-tuning the mPLMs with multilingual data. However, obtaining labeled multilingual data is time-consuming, and fine-tuning mPLM with limited labeled multilingual data merely encapsulates the knowledge specific to the labeled data. Therefore, we introduce ALSACE to leverage the learned knowledge from the well-performing languages to guide under-performing ones within the same mPLM, eliminating the need for additional labeled multilingual data. Experiments show that ALSACE effectively mitigates language-level performance disparity across various mPLMs while showing the competitive performance on different multilingual NLU tasks, ranging from full resource to limited resource settings. The code for our approach is available at https://github.com/pkunlp-icler/ALSACE.