Task-agnostic knowledge distillation attempts to address the problem of deploying large pretrained language model in resource-constrained scenarios by compressing a large pretrained model called teacher into a smaller one called student such that the student can be directly finetuned on downstream tasks and retains comparable performance. However, we empirically find that there is a generalization gap between the student and the teacher in existing methods. In this work, we show that we can leverage multi-task learning in task-agnostic distillation to advance the generalization of the resulted student. In particular, we propose Multi-task Infused Task-agnostic Knowledge Distillation (MITKD). We first enhance the teacher by multi-task training it on multiple downstream tasks and then perform distillation to produce the student. Experimental results demonstrate that our method yields a student with much better generalization, significantly outperforms existing baselines, and establishes a new state-of-the-art result on in-domain, out-domain, and low-resource datasets in the setting of task-agnostic distillation. Moreover, our method even exceeds an 8x larger BERT$_{\text{Base}}$ on SQuAD and four GLUE tasks. In addition, by combining ERNIE 3.0, our method achieves state-of-the-art results on 10 Chinese datasets.

Based on an annotated multimedia corpus, television series Mar{\=a}y{\=a} 2013, we dig into the question of ''automatic standardization'' of Arabic dialects for machine translation. Here we distinguish between rule-based machine translation and statistical machine translation. Machine translation from Arabic most of the time takes standard or modern Arabic as the source language and produces quite satisfactory translations thanks to the availability of the translation memories necessary for training the models. The case is different for the translation of Arabic dialects. The productions are much less efficient. In our research we try to apply machine translation methods to a dialect/standard (or modern) Arabic pair to automatically produce a standard Arabic text from a dialect input, a process we call ''automatic standardization''. we opt here for the application of ''statistical models'' because ''automatic standardization'' based on rules is more hard with the lack of ''diglossic'' dictionaries on the one hand and the difficulty of creating linguistic rules for each dialect on the other. Carrying out this research could then lead to combining ''automatic standardization'' software and automatic translation software so that we take the output of the first software and introduce it as input into the second one to obtain at the end a quality machine translation. This approach may also have educational applications such as the development of applications to help understand different Arabic dialects by transforming dialectal texts into standard Arabic.

Knowledge tracing (KT) is the task of using students' historical learning interaction data to model their knowledge mastery over time so as to make predictions on their future interaction performance. Recently, remarkable progress has been made of using various deep learning techniques to solve the KT problem. However, the success behind deep learning based knowledge tracing (DLKT) approaches is still left somewhat unknown and proper measurement and analysis of these DLKT approaches remain a challenge. First, data preprocessing procedures in existing works are often private and custom, which limits experimental standardization. Furthermore, existing DLKT studies often differ in terms of the evaluation protocol and are far away real-world educational contexts. To address these problems, we introduce a comprehensive python based benchmark platform, \textsc{pyKT}, to guarantee valid comparisons across DLKT methods via thorough evaluations. The \textsc{pyKT} library consists of a standardized set of integrated data preprocessing procedures on 7 popular datasets across different domains, and 10 frequently compared DLKT model implementations for transparent experiments. Results from our fine-grained and rigorous empirical KT studies yield a set of observations and suggestions for effective DLKT, e.g., wrong evaluation setting may cause label leakage that generally leads to performance inflation; and the improvement of many DLKT approaches is minimal compared to the very first DLKT model proposed by Piech et al. \cite{piech2015deep}. We have open sourced \textsc{pyKT} and our experimental results at https://pykt.org/. We welcome contributions from other research groups and practitioners.

Current natural language understanding (NLU) models have been continuously scaling up, both in terms of model size and input context, introducing more hidden and input neurons. While this generally improves performance on average, the extra neurons do not yield a consistent improvement for all instances. This is because some hidden neurons are redundant, and the noise mixed in input neurons tends to distract the model. Previous work mainly focuses on extrinsically reducing low-utility neurons by additional post- or pre-processing, such as network pruning and context selection, to avoid this problem. Beyond that, can we make the model reduce redundant parameters and suppress input noise by intrinsically enhancing the utility of each neuron? If a model can efficiently utilize neurons, no matter which neurons are ablated (disabled), the ablated submodel should perform no better than the original full model. Based on such a comparison principle between models, we propose a cross-model comparative loss for a broad range of tasks. Comparative loss is essentially a ranking loss on top of the task-specific losses of the full and ablated models, with the expectation that the task-specific loss of the full model is minimal. We demonstrate the universal effectiveness of comparative loss through extensive experiments on 14 datasets from 3 distinct NLU tasks based on 4 widely used pretrained language models, and find it particularly superior for models with few parameters or long input.

Configurable software systems can be tuned for better performance. Leveraging on some Pareto optimizers, recent work has shifted from tuning for a single, time-related performance objective to two intrinsically different objectives that assess distinct performance aspects of the system, each with varying aspirations. Before we design better optimizers, a crucial engineering decision to make therein is how to handle the performance requirements with clear aspirations in the tuning process. For this, the community takes two alternative optimization models: either quantifying and incorporating the aspirations into the search objectives that guide the tuning, or not considering the aspirations during the search but purely using them in the later decision-making process only. However, despite being a crucial decision that determines how an optimizer can be designed and tailored, there is a rather limited understanding of which optimization model should be chosen under what particular circumstance, and why. In this paper, we seek to close this gap. Firstly, we do that through a review of over 426 papers in the literature and 14 real-world requirements datasets. Drawing on these, we then conduct a comprehensive empirical study that covers 15 combinations of the state-of-the-art performance requirement patterns, four types of aspiration space, three Pareto optimizers, and eight real-world systems/environments, leading to 1,296 cases of investigation. We found that (1) the realism of aspirations is the key factor that determines whether they should be used to guide the tuning; (2) the given patterns and the position of the realistic aspirations in the objective landscape are less important for the choice, but they do matter to the extents of improvement; (3) the available tuning budget can also influence the choice for unrealistic aspirations but it is insignificant under realistic ones.

Timely and reliable detection of falls is a large and rapidly growing field of research due to the medical and financial demand of caring for a constantly growing elderly population. Within the past 2 decades, the availability of high-quality hardware (high-quality sensors and AI microchips) and software (machine learning algorithms) technologies has served as a catalyst for this research by giving developers the capabilities to develop such systems. This study developed multiple application components in order to investigate the development challenges and choices for fall detection systems, and provide materials for future research. The smart application developed using this methodology was validated by the results from fall detection modelling experiments and model mobile deployment. The best performing model overall was the ResNet152 on a standardised, and shuffled dataset with a 2s window size which achieved 92.8% AUC, 87.28% sensitivity, and 98.33% specificity. Given these results it is evident that accelerometer and ECG sensors are beneficial for fall detection, and allow for the discrimination between falls and other activities. This study leaves a significant amount of room for improvement due to weaknesses identified in the resultant dataset. These improvements include using a labelling protocol for the critical phase of a fall, increasing the number of dataset samples, improving the test subject representation, and experimenting with frequency domain preprocessing.

Several applications require counting the number of distinct items in the data, which is known as the cardinality counting problem. Example applications include health applications such as rare disease patients counting for adequate awareness and funding, and counting the number of cases of a new disease for outbreak detection, marketing applications such as counting the visibility reached for a new product, and cybersecurity applications such as tracking the number of unique views of social media posts. The data needed for the counting is however often personal and sensitive, and need to be processed using privacy-preserving techniques. The quality of data in different databases, for example typos, errors and variations, poses additional challenges for accurate cardinality estimation. While privacy-preserving cardinality counting has gained much attention in the recent times and a few privacy-preserving algorithms have been developed for cardinality estimation, no work has so far been done on privacy-preserving cardinality counting using record linkage techniques with fuzzy matching and provable privacy guarantees. We propose a novel privacy-preserving record linkage algorithm using unsupervised clustering techniques to link and count the cardinality of individuals in multiple datasets without compromising their privacy or identity. In addition, existing Elbow methods to find the optimal number of clusters as the cardinality are far from accurate as they do not take into account the purity and completeness of generated clusters. We propose a novel method to find the optimal number of clusters in unsupervised learning. Our experimental results on real and synthetic datasets are highly promising in terms of significantly smaller error rate of less than 0.1 with a privacy budget {\epsilon} = 1.0 compared to the state-of-the-art fuzzy matching and clustering method.

The ability to generalise well is one of the primary desiderata of natural language processing (NLP). Yet, what 'good generalisation' entails and how it should be evaluated is not well understood, nor are there any evaluation standards for generalisation. In this paper, we lay the groundwork to address both of these issues. We present a taxonomy for characterising and understanding generalisation research in NLP. Our taxonomy is based on an extensive literature review of generalisation research, and contains five axes along which studies can differ: their main motivation, the type of generalisation they investigate, the type of data shift they consider, the source of this data shift, and the locus of the shift within the modelling pipeline. We use our taxonomy to classify over 400 papers that test generalisation, for a total of more than 600 individual experiments. Considering the results of this review, we present an in-depth analysis that maps out the current state of generalisation research in NLP, and we make recommendations for which areas might deserve attention in the future. Along with this paper, we release a webpage where the results of our review can be dynamically explored, and which we intend to update as new NLP generalisation studies are published. With this work, we aim to take steps towards making state-of-the-art generalisation testing the new status quo in NLP.

Reward functions are notoriously difficult to specify, especially for tasks with complex goals. Reward learning approaches attempt to infer reward functions from human feedback and preferences. Prior works on reward learning have mainly focused on the performance of policies trained alongside the reward function. This practice, however, may fail to detect learned rewards that are not capable of training new policies from scratch and thus do not capture the intended behavior. Our work focuses on demonstrating and studying the causes of these relearning failures in the domain of preference-based reward learning. We demonstrate with experiments in tabular and continuous control environments that the severity of relearning failures can be sensitive to changes in reward model design and the trajectory dataset composition. Based on our findings, we emphasize the need for more retraining-based evaluations in the literature.

Construction of human-curated annotated datasets for abstractive text summarization (ATS) is very time-consuming and expensive because creating each instance requires a human annotator to read a long document and compose a shorter summary that would preserve the key information relayed by the original document. Active Learning (AL) is a technique developed to reduce the amount of annotation required to achieve a certain level of machine learning model performance. In information extraction and text classification, AL can reduce the amount of labor up to multiple times. Despite its potential for aiding expensive annotation, as far as we know, there were no effective AL query strategies for ATS. This stems from the fact that many AL strategies rely on uncertainty estimation, while as we show in our work, uncertain instances are usually noisy, and selecting them can degrade the model performance compared to passive annotation. We address this problem by proposing the first effective query strategy for AL in ATS based on diversity principles. We show that given a certain annotation budget, using our strategy in AL annotation helps to improve the model performance in terms of ROUGE and consistency scores. Additionally, we analyze the effect of self-learning and show that it can further increase the performance of the model.