Fine-tuning the Natural Language Processing (NLP) models for each new data set requires higher computational time associated with increased carbon footprint and cost. However, fine-tuning helps the pre-trained models adapt to the latest data sets; what if we avoid the fine-tuning steps and attempt to generate summaries using just the pre-trained models to reduce computational time and cost. In this paper, we tried to omit the fine-tuning steps and investigate whether the Marginal Maximum Relevance (MMR)-based approach can help the pre-trained models to obtain query-focused summaries directly from a new data set that was not used to pre-train the models. First, we used topic modelling on Wikipedia Current Events Portal (WCEP) and Debatepedia datasets to generate queries for summarization tasks. Then, using MMR, we ranked the sentences of the documents according to the queries. Next, we passed the ranked sentences to seven transformer-based pre-trained models to perform the summarization tasks. Finally, we used the MMR approach again to select the query relevant sentences from the generated summaries of individual pre-trained models and constructed the final summary. As indicated by the experimental results, our MMR-based approach successfully ranked and selected the most relevant sentences as summaries and showed better performance than the individual pre-trained models.

We study online learning problems in which a decision maker wants to maximize their expected reward without violating a finite set of $m$ resource constraints. By casting the learning process over a suitably defined space of strategy mixtures, we recover strong duality on a Lagrangian relaxation of the underlying optimization problem, even for general settings with non-convex reward and resource-consumption functions. Then, we provide the first best-of-many-worlds type framework for this setting, with no-regret guarantees under stochastic, adversarial, and non-stationary inputs. Our framework yields the same regret guarantees of prior work in the stochastic case. On the other hand, when budgets grow at least linearly in the time horizon, it allows us to provide a constant competitive ratio in the adversarial case, which improves over the best known upper bound bound of $O(\log m \log T)$. Moreover, our framework allows the decision maker to handle non-convex reward and cost functions. We provide two game-theoretic applications of our framework to give further evidence of its flexibility. In doing so, we show that it can be employed to implement budget-pacing mechanisms in repeated first-price auctions.

This paper describes an end-to-end (E2E) neural architecture for the audio rendering of small portions of display content on low resource personal computing devices. It is intended to address the problem of accessibility for vision-impaired or vision-distracted users at the hardware level. Neural image-to-text (ITT) and text-to-speech (TTS) approaches are reviewed and a new technique is introduced to efficiently integrate them in a way that is both efficient and back-propagate-able, leading to a non-autoregressive E2E image-to-speech (ITS) neural network that is efficient and trainable. Experimental results are presented showing that, compared with the non-E2E approach, the proposed E2E system is 29% faster and uses 19% fewer parameters with a 2% reduction in phone accuracy. A future direction to address accuracy is presented.

At the Technical University of Denmark, we currently teach a MSc level course on automated reasoning using the Isabelle proof assistant [11] as our main tool. The course is a 5 ECTS optional course and the homepage is here: https://courses.compute.dtu.dk/02256/ The course is an introduction to automatic and interactive theorem proving, and Isabelle is used to formalize almost all of the concepts we introduce during the course. We have developed a number of external tools to allow us to teach basic proofs in natural deduction and sequent calculus while slowly progressing towards showing students the full power of Isabelle. The learning objectives of the course are as follows: 1. explain the basic concepts introduced in the course 2. express mathematical theorems and properties of IT systems formally 3. master the natural deduction proof system 4. relate first-order logic, higher-order logic and type theory 5. construct formal proofs in the procedural style and in the declarative style 6. use automatic and interactive computer systems for automated reasoning 7. evaluate the trustworthiness of proof assistants and related tools 8. communicate solutions to problems in a clear and precise manner We expect students to already know some logic and to be relatively proficient in functional programming before starting the course. Additionally, we expect students to have some basic knowledge of artificial intelligence algorithms for deduction. Our undergraduate program in computer science and engineering, which many of our students have completed, contains several courses that introduce students to these topics.

Narratives are fundamental to our understanding of the world, providing us with a natural structure for knowledge representation over time. Computational narrative extraction is a subfield of artificial intelligence that makes heavy use of information retrieval and natural language processing techniques. Despite the importance of computational narrative extraction, relatively little scholarly work exists on synthesizing previous research and strategizing future research in the area. In particular, this article focuses on extracting news narratives from an event-centric perspective. Extracting narratives from news data has multiple applications in understanding the evolving information landscape. This survey presents an extensive study of research in the area of event-based news narrative extraction. In particular, we screened over 900 articles that yielded 54 relevant articles. These articles are synthesized and organized by representation model, extraction criteria, and evaluation approaches. Based on the reviewed studies, we identify recent trends, open challenges, and potential research lines.

Automatic speech recognition (ASR) systems based on deep neural networks are weak against adversarial perturbations. We propose mixPGD adversarial training method to improve the robustness of the model for ASR systems. In standard adversarial training, adversarial samples are generated by leveraging supervised or unsupervised methods. We merge the capabilities of both supervised and unsupervised approaches in our method to generate new adversarial samples which aid in improving model robustness. Extensive experiments and comparison across various state-of-the-art defense methods and adversarial attacks have been performed to show that mixPGD gains 4.1% WER of better performance than previous best performing models under white-box adversarial attack setting. We tested our proposed defense method against both white-box and transfer based black-box attack settings to ensure that our defense strategy is robust against various types of attacks. Empirical results on several adversarial attacks validate the effectiveness of our proposed approach.

This work studies knowledge distillation (KD) and addresses its constraints for recurrent neural network transducer (RNN-T) models. In hard distillation, a teacher model transcribes large amounts of unlabelled speech to train a student model. Soft distillation is another popular KD method that distills the output logits of the teacher model. Due to the nature of RNN-T alignments, applying soft distillation between RNN-T architectures having different posterior distributions is challenging. In addition, bad teachers having high word-error-rate (WER) reduce the efficacy of KD. We investigate how to effectively distill knowledge from variable quality ASR teachers, which has not been studied before to the best of our knowledge. We show that a sequence-level KD, full-sum distillation, outperforms other distillation methods for RNN-T models, especially for bad teachers. We also propose a variant of full-sum distillation that distills the sequence discriminative knowledge of the teacher leading to further improvement in WER. We conduct experiments on public datasets namely SpeechStew and LibriSpeech, and on in-house production data.

The free flow of information has been accelerated by the rapid development of social media technology. There has been a significant social and psychological impact on the population due to the outbreak of Coronavirus disease (COVID-19). The COVID-19 pandemic is one of the current events being discussed on social media platforms. In order to safeguard societies from this pandemic, studying people's emotions on social media is crucial. As a result of their particular characteristics, sentiment analysis of texts like tweets remains challenging. Sentiment analysis is a powerful text analysis tool. It automatically detects and analyzes opinions and emotions from unstructured data. Texts from a wide range of sources are examined by a sentiment analysis tool, which extracts meaning from them, including emails, surveys, reviews, social media posts, and web articles. To evaluate sentiments, natural language processing (NLP) and machine learning techniques are used, which assign weights to entities, topics, themes, and categories in sentences or phrases. Machine learning tools learn how to detect sentiment without human intervention by examining examples of emotions in text. In a pandemic situation, analyzing social media texts to uncover sentimental trends can be very helpful in gaining a better understanding of society's needs and predicting future trends. We intend to study society's perception of the COVID-19 pandemic through social media using state-of-the-art BERT and Deep CNN models. The superiority of BERT models over other deep models in sentiment analysis is evident and can be concluded from the comparison of the various research studies mentioned in this article.

Out-of-distribution (OOD) detection has recently received special attention due to its critical role in safely deploying modern deep learning (DL) architectures. This work proposes a reconstruction-based multi-class OOD detector that operates on radar range doppler images (RDIs). The detector aims to classify any moving object other than a person sitting, standing, or walking as OOD. We also provide a simple yet effective pre-processing technique to detect minor human body movements like breathing. The simple idea is called respiration detector (RESPD) and eases the OOD detection, especially for human sitting and standing classes. On our dataset collected by 60GHz short-range FMCW Radar, we achieve AUROCs of 97.45%, 92.13%, and 96.58% for sitting, standing, and walking classes, respectively. We perform extensive experiments and show that our method outperforms state-of-the-art (SOTA) OOD detection methods. Also, our pipeline performs 24 times faster than the second-best method and is very suitable for real-time processing.

The approach proposed in this paper stems from [9], which uses generative unconditional models of signal components We provide an example of a distribution preserving source in the construction of a separation scheme. While separation method, which aims at addressing perceptual the separation scenarios of [9, 10] are toy-like (because these shortcomings of state-of-the-art methods. Our approach uses approaches assume that generative models of all the mixture unconditioned generative models of signal sources. Reconstruction components are available), they still provide a clean testing is achieved by means of mix-consistent sampling ground for the proposed separation approach. In our case, from a distribution conditioned on a realization of a mix. The we focus on employing high-quality generative models to separated signals follow their respective source distributions, provide in-distribution reconstructions. Specifically, we use which provides an advantage when separation results are generative models operating in a quadrature modulated filter evaluated in a listening test.