We propose a multilingual data-driven method for generating reading comprehension questions using dependency trees. Our method provides a strong, mostly deterministic, and inexpensive-totrain baseline for less-resourced languages. While a language-specific corpus is still required, its size is nowhere near those required by modern neural question generation (QG) architectures. Our method surpasses QG baselines previously reported in the literature and shows a good performance in terms of human evaluation. 1 Introduction We are interested in question generation (QG) - the task of automatically generating reading comprehension questions and their correct answers from given declarative sentences. Numerous methods have been proposed for solving this task, most of which have been aimed at the English language. Recent methods are based on neural networks and rely on the availability of large-scale datasets, such as SQuAD (Rajpurkar et al. 2016) - a question-answering dataset repurposed for QG - or large-scale pretrained models, such as GPT-3 (Brown et al. 2020). Early methods, mostly based on context-free grammars, relied on the strict word order and the limited inflectional morphology of English. These traits made it relatively straightforward to craft handwritten templates based on these grammars. The above mentioned idiosyncracies and the unique availability of large-scale resources for English leave a number of open challenges for developing QG methods applicable to languages other than English. The first challenge is the lack of large-scale training datasets, and a prohibitively high cost of obtaining such resources. State-of-the-art QG methods for English train their models on the previously mentioned SQuAD dataset, which contains more than 100,000 questions. Obtaining a good-quality dataset of a similar size is very expensive, especially for languages with fewer native speakers around the world. The second challenge is knowing how well available methods developed for English would generalize to other languages, especially synthetic ones with richer inflectional morphology and less strict word order (e.g., Finnish, Turkish or Russian). To the best of our knowledge, not much research has been done on QG for these kinds of languages. The third challenge is assessing the obtained performance results.

Ensuring that large language models (LMs) are fair, robust and useful requires an understanding of how different modifications to their inputs impact the model's behaviour. In the context of open-text generation tasks, however, such an evaluation is not trivial. For example, when introducing a model with an input text and a perturbed, "contrastive" version of it, meaningful differences in the next-token predictions may not be revealed with standard decoding strategies. With this motivation in mind, we propose Contrastive Input Decoding (CID): a decoding algorithm to generate text given two inputs, where the generated text is likely given one input but unlikely given the other. In this way, the contrastive generations can highlight potentially subtle differences in how the LM output differs for the two inputs in a simple and interpretable manner. We use CID to highlight context-specific biases that are hard to detect with standard decoding strategies and quantify the effect of different input perturbations.

This paper presents a novel RL algorithm, S-REINFORCE, which is designed to generate interpretable policies for dynamic decision-making tasks. The proposed algorithm leverages two types of function approximators, namely Neural Network (NN) and Symbolic Regressor (SR), to produce numerical and symbolic policies, respectively. The NN component learns to generate a numerical probability distribution over the possible actions using a policy gradient, while the SR component captures the functional form that relates the associated states with the action probabilities. The SR-generated policy expressions are then utilized through importance sampling to improve the rewards received during the learning process. We have tested the proposed S-REINFORCE algorithm on various dynamic decision-making problems with low and high dimensional action spaces, and the results demonstrate its effectiveness and impact in achieving interpretable solutions. By leveraging the strengths of both NN and SR, S-REINFORCE produces policies that are not only well-performing but also easy to interpret, making it an ideal choice for real-world applications where transparency and causality are crucial.

Quantifying forecast uncertainty is a key aspect of state-of-the-art numerical weather prediction and data assimilation systems. Ensemble-based data assimilation systems incorporate state-dependent uncertainty quantification based on multiple model integrations. However, this approach is demanding in terms of computations and development. In this work a machine learning method is presented based on convolutional neural networks that estimates the state-dependent forecast uncertainty represented by the forecast error covariance matrix using a single dynamical model integration. This is achieved by the use of a loss function that takes into account the fact that the forecast errors are heterodastic. The performance of this approach is examined within a hybrid data assimilation method that combines a Kalman-like analysis update and the machine learning based estimation of a state-dependent forecast error covariance matrix. Observing system simulation experiments are conducted using the Lorenz'96 model as a proof-of-concept. The promising results show that the machine learning method is able to predict precise values of the forecast covariance matrix in relatively high-dimensional states. Moreover, the hybrid data assimilation method shows similar performance to the ensemble Kalman filter outperforming it when the ensembles are relatively small.

Anonymization techniques based on obfuscating the quasi-identifiers by means of value generalization hierarchies are widely used to achieve preset levels of privacy. To prevent different types of attacks against database privacy it is necessary to apply several anonymization techniques beyond the classical k-anonymity or $\ell$-diversity. However, the application of these methods is directly connected to a reduction of their utility in prediction and decision making tasks. In this work we study four classical machine learning methods currently used for classification purposes in order to analyze the results as a function of the anonymization techniques applied and the parameters selected for each of them. The performance of these models is studied when varying the value of k for k-anonymity and additional tools such as $\ell$-diversity, t-closeness and $\delta$-disclosure privacy are also deployed on the well-known adult dataset.

Existing recommender systems face difficulties with zero-shot items, i.e. items that have no historical interactions with users during the training stage. Though recent works extract universal item representation via pre-trained language models (PLMs), they ignore the crucial item relationships. This paper presents a novel paradigm for the Zero-Shot Item-based Recommendation (ZSIR) task, which pre-trains a model on product knowledge graph (PKG) to refine the item features from PLMs. We identify three challenges for pre-training PKG, which are multi-type relations in PKG, semantic divergence between item generic information and relations and domain discrepancy from PKG to downstream ZSIR task. We address the challenges by proposing four pre-training tasks and novel task-oriented adaptation (ToA) layers. Moreover, this paper discusses how to fine-tune the model on new recommendation task such that the ToA layers are adapted to ZSIR task. Comprehensive experiments on 18 markets dataset are conducted to verify the effectiveness of the proposed model in both knowledge prediction and ZSIR task.

Regression methods assume that accurate labels are available for training. However, in certain scenarios, obtaining accurate labels may not be feasible, and relying on multiple specialists with differing opinions becomes necessary. Existing approaches addressing noisy labels often impose restrictive assumptions on the regression function. In contrast, this paper presents a novel, more flexible approach. Our method consists of two steps: estimating each labeler's expertise and combining their opinions using learned weights. We then regress the weighted average against the input features to build the prediction model. The proposed method is formally justified and empirically demonstrated to outperform existing techniques on simulated and real data. Furthermore, its flexibility enables the utilization of any machine learning technique in both steps. In summary, this method offers a simple, fast, and effective solution for training regression models with noisy labels derived from diverse expert opinions.

Massively multilingual pretrained transformers (MMTs) have tremendously pushed the state of the art on multilingual NLP and cross-lingual transfer of NLP models in particular. While a large body of work leveraged MMTs to mine parallel data and induce bilingual document embeddings, much less effort has been devoted to training general-purpose (massively) multilingual document encoder that can be used for both supervised and unsupervised document-level tasks. In this work, we pretrain a massively multilingual document encoder as a hierarchical transformer model (HMDE) in which a shallow document transformer contextualizes sentence representations produced by a state-of-the-art pretrained multilingual sentence encoder. We leverage Wikipedia as a readily available source of comparable documents for creating training data, and train HMDE by means of a cross-lingual contrastive objective, further exploiting the category hierarchy of Wikipedia for creation of difficult negatives. We evaluate the effectiveness of HMDE in two arguably most common and prominent cross-lingual document-level tasks: (1) cross-lingual transfer for topical document classification and (2) cross-lingual document retrieval. HMDE is significantly more effective than (i) aggregations of segment-based representations and (ii) multilingual Longformer. Crucially, owing to its massively multilingual lower transformer, HMDE successfully generalizes to languages unseen in document-level pretraining. We publicly release our code and models at https://github.com/ogaloglu/pre-training-multilingual-document-encoders .

Most current audio-visual emotion recognition models lack the flexibility needed for deployment in practical applications. We envision a multimodal system that works even when only one modality is available and can be implemented interchangeably for either predicting emotional attributes or recognizing categorical emotions. Achieving such flexibility in a multimodal emotion recognition system is difficult due to the inherent challenges in accurately interpreting and integrating varied data sources. It is also a challenge to robustly handle missing or partial information while allowing direct switch between regression and classification tasks. This study proposes a \emph{versatile audio-visual learning} (VAVL) framework for handling unimodal and multimodal systems for emotion regression and emotion classification tasks. We implement an audio-visual framework that can be trained even when audio and visual paired data is not available for part of the training set (i.e., audio only or only video is present). We achieve this effective representation learning with audio-visual shared layers, residual connections over shared layers, and a unimodal reconstruction task. Our experimental results reveal that our architecture significantly outperforms strong baselines on both the CREMA-D and MSP-IMPROV corpora. Notably, VAVL attains a new state-of-the-art performance in the emotional attribute prediction task on the MSP-IMPROV corpus. Code available at: https://github.com/ilucasgoncalves/VAVL

This paper aims to quantitatively evaluate the performance of ChatGPT, an interactive large language model, on inter-sentential relations such as temporal relations, causal relations, and discourse relations. Given ChatGPT's promising performance across various tasks, we conduct extensive evaluations on the whole test sets of 13 datasets, including temporal and causal relations, PDTB2.0-based and dialogue-based discourse relations, and downstream applications on discourse understanding. To achieve reliable results, we adopt three tailored prompt templates for each task, including the zero-shot prompt template, zero-shot prompt engineering (PE) template, and in-context learning (ICL) prompt template, to establish the initial baseline scores for all popular sentence-pair relation classification tasks for the first time. We find that ChatGPT exhibits strong performance in detecting and reasoning about causal relations, while it may not be proficient in identifying the temporal order between two events. It can recognize most discourse relations with existing explicit discourse connectives, but the implicit discourse relation still remains a challenging task. Meanwhile, ChatGPT performs poorly in the dialogue discourse parsing task that requires structural understanding in a dialogue before being aware of the discourse relation.