Though model robustness has been extensively studied in language understanding, the robustness of Seq2Seq generation remains understudied. In this paper, we conduct the first quantitative analysis on the robustness of pre-trained Seq2Seq models. We find that even current SOTA pre-trained Seq2Seq model (BART) is still vulnerable, which leads to significant degeneration in faithfulness and informativeness for text generation tasks. This motivated us to further propose a novel adversarial augmentation framework, namely AdvSeq, for generally improving faithfulness and informativeness of Seq2Seq models via enhancing their robustness. AdvSeq automatically constructs two types of adversarial augmentations during training, including implicit adversarial samples by perturbing word representations and explicit adversarial samples by word swapping, both of which effectively improve Seq2Seq robustness. Extensive experiments on three popular text generation tasks demonstrate that AdvSeq significantly improves both the faithfulness and informativeness of Seq2Seq generation under both automatic and human evaluation settings.

Summarizing legal decisions requires the expertise of law practitioners, which is both time- and cost-intensive. This paper presents techniques for extractive summarization of legal decisions in a low-resource setting using limited expert annotated data. We test a set of models that locate relevant content using a sequential model and tackle redundancy by leveraging maximal marginal relevance to compose summaries. We also demonstrate an implicit approach to help train our proposed models generate more informative summaries. Our multi-task learning model variant leverages rhetorical role identification as an auxiliary task to further improve the summarizer. We perform extensive experiments on datasets containing legal decisions from the US Board of Veterans' Appeals and conduct quantitative and expert-ranked evaluations of our models. Our results show that the proposed approaches can achieve ROUGE scores vis-\`a-vis expert extracted summaries that match those achieved by inter-annotator comparison.

Fact-checking requires retrieving evidence related to a claim under investigation. The task can be formulated as question generation based on a claim, followed by question answering. However, recent question generation approaches assume that the answer is known and typically contained in a passage given as input, whereas such passages are what is being sought when verifying a claim. In this paper, we present {\it Varifocal}, a method that generates questions based on different focal points within a given claim, i.e.\ different spans of the claim and its metadata, such as its source and date. Our method outperforms previous work on a fact-checking question generation dataset on a wide range of automatic evaluation metrics. These results are corroborated by our manual evaluation, which indicates that our method generates more relevant and informative questions. We further demonstrate the potential of focal points in generating sets of clarification questions for product descriptions.

Maximum likelihood estimation (MLE) is the predominant algorithm for training text generation models. This paradigm relies on direct supervision examples, which is not applicable to many emerging applications, such as generating adversarial attacks or generating prompts to control language models. Reinforcement learning (RL) on the other hand offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. Yet previous RL algorithms for text generation, such as policy gradient (on-policy RL) and Q-learning (off-policy RL), are often notoriously inefficient or unstable to train due to the large sequence space and the sparse reward received only at the end of sequences. In this paper, we introduce a new RL formulation for text generation from the soft Q-learning (SQL) perspective. It enables us to draw from the latest RL advances, such as path consistency learning, to combine the best of on-/off-policy updates, and learn effectively from sparse reward. We apply the approach to a wide range of novel text generation tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation. Experiments show our approach consistently outperforms both task-specialized algorithms and the previous RL methods.

Detecting suspicious activities in surveillance videos is a longstanding problem in real-time surveillance that leads to difficulties in detecting crimes. Hence, we propose a novel approach for detecting and summarizing suspicious activities in surveillance videos. We have also created ground truth summaries for the UCF-Crime video dataset. We modify a pre-existing approach for this task by leveraging the Human-Object Interaction (HOI) model for the Visual features in the Bi-Modal Transformer. Further, we validate our approach against the existing state-of-the-art algorithms for the Dense Video Captioning task for the ActivityNet Captions dataset. We observe that this formulation for Dense Captioning performs significantly better than other discussed BMT-based approaches for BLEU@1, BLEU@2, BLEU@3, BLEU@4, and METEOR. We further perform a comparative analysis of the dataset and the model to report the findings based on different NMS thresholds (searched using Genetic Algorithms). Here, our formulation outperforms all the models for BLEU@1, BLEU@2, BLEU@3, and most models for BLEU@4 and METEOR falling short of only ADV-INF Global by 25% and 0.5%, respectively.

In early 2016, Microsoft announced Tay, an AI chatbot capable of conversing with and learning from random users on the internet. Within 24 hours, the bot began spewing racist, misogynistic statements, seemingly unprovoked. The team pulled the plug on Tay, realizing that the ethics of letting a conversational bot loose on the internet were, at best, unexplored. The real questions are whether AI designed for random human interaction is ethical, and whether AI can be coded to stay within bounds. This becomes even more critical with voice AI, which businesses use to communicate automatically and directly with customers.

Deep learning (DL) models have enjoyed tremendous success across application domains within the broader umbrella of artificial intelligence (AI) technologies. However, their "black-box" nature, coupled with their extensive use across application sectors--including safety-critical and risk-sensitive ones such as healthcare, finance, aerospace, law enforcement, and governance--has elicited an increasing need for explainability, interpretability, and transparency of decision-making in these models.11,14,18,24 With the recent progression of legal and policy frameworks that mandate explaining decisions made by AI-driven systems (for example, the European Union's GDPR Article 15(1)(h) and the Algorithmic Accountability Act of 2019 in the U.S.), explainability has become a cornerstone of responsible AI use and deployment. In the Indian context, NITI Aayog recently released a two-part strategy document on envisioning and operationalizing Responsible AI in India,15,16 which puts significant emphasis on the explainability and transparency of AI models. Explainability of DL models lies at the human-machine interface, and different users may expect different explanations in different contexts.

Vislink a global technology leader in the capture, delivery and management of high quality, live video and associated data in the media & entertainment, law enforcement and defense markets, will showcase its latest AI solutions for monetizing live sports content at Sportel Monaco 2022 (Booth #A32) from October 24 through October 26. The company will be introducing its latest AI Clipper Studio toolkit, as well as showcasing its latest updates to the AI-centric IQ Sports Producer system. In addition, Vislink launches a newly integrated partnership with sports OTT provider, StreamViral, at the show. Sportel is the world's leading sports content media rights and technology convention. It represents the perfect venue for Vislink to demonstrate how its AI-automated solutions can help capture and stream more compelling sports content while engaging and expanding audiences -- and do so at a fraction of the traditional cost.

A new study from University of Washington and Johns Hopkins shows that robots trained on artificial intelligence make decisions imbued with racism and sexism. Of course, robots are only the latest in a long line of new technologies found to perpetuate harmful stereotypes--so do search engines, social media, and video games, as well as other popular tech products trained on huge sets of data and driven by algorithms. That devices feed racist and sexist misinformation to adults is terrible enough. But, as a psychologist and advocate for kids, I worry even more about what's being fed to children, including the very young, who are also exposed to--and influenced by--tech-delivered misinformation about race. The study comes out at a time when, across the U.S., a wave of new legislation is censoring what educators can discuss in the classroom, including topics of race, slavery, gender identity, and politics.

Did you realize that you, as a software developer, spend about 75% of your time searching through and querying to understand code, fix bugs and make necessary changes? With every change, applications grow increasingly complex, escalating the importance of software development productivity, which is attracting greater attention from the professional community. Whether a startup's leadership is concerned about how much the software development team costs and wants to promote efficiency to get more done with less, or a corporate engineering leader is "shaking out" their teams to improve output, questions about productivity inevitably arise. While some tools can help improve productivity by suggesting what code to write, even as the developer is writing code, software developers still have to use their brains to add new features, fix bugs, implement changes to meet regulatory requirements, address security needs and solve challenging engineering problems. But what if there was a tool that did some of the hardest thinking for you?