Intelligent Traffic Monitoring (ITMo) technologies hold the potential for improving road safety/security and for enabling smart city infrastructure. Understanding traffic situations requires a complex fusion of perceptual information with domain-specific and causal commonsense knowledge. Whereas prior work has provided benchmarks and methods for traffic monitoring, it remains unclear whether models can effectively align these information sources and reason in novel scenarios. To address this assessment gap, we devise three novel text-based tasks for situational reasoning in the traffic domain: i) BDD-QA, which evaluates the ability of Language Models (LMs) to perform situational decision-making, ii) TV-QA, which assesses LMs' abilities to reason about complex event causality, and iii) HDT-QA, which evaluates the ability of models to solve human driving exams. We adopt four knowledge-enhanced methods that have shown generalization capability across language reasoning tasks in prior work, based on natural language inference, commonsense knowledge-graph self-supervision, multi-QA joint training, and dense retrieval of domain information. We associate each method with a relevant knowledge source, including knowledge graphs, relevant benchmarks, and driving manuals. In extensive experiments, we benchmark various knowledge-aware methods against the three datasets, under zero-shot evaluation; we provide in-depth analyses of model performance on data partitions and examine model predictions categorically, to yield useful insights on traffic understanding, given different background knowledge and reasoning strategies.

Procedural text understanding is a challenging language reasoning task that requires models to track entity states across the development of a narrative. We identify three core aspects required for modeling this task, namely the local and global view of the inputs, as well as the global view of outputs. Prior methods have considered a subset of these aspects, which leads to either low precision or low recall. In this paper, we propose a new model Coalescing Global and Local Information (CGLI), which builds entity- and timestep-aware input representations (local input) considering the whole context (global input), and we jointly model the entity states with a structured prediction objective (global output). Thus, CGLI simultaneously optimizes for both precision and recall. Moreover, we extend CGLI with additional output layers and integrate it into a story reasoning framework. Extensive experiments on a popular procedural text understanding dataset show that our model achieves state-of-the-art results, while experiments on a story reasoning benchmark show the positive impact of our model on downstream reasoning.

Recent developments in pre-trained neural language modeling have led to leaps in accuracy on common-sense question-answering benchmarks. However, there is increasing concern that models overfit to specific tasks, without learning to utilize external knowledge or perform general semantic reasoning. In contrast, zero-shot evaluations have shown promise as a more robust measure of a model’s general reasoning abilities. In this paper, we propose a novel neuro-symbolic framework for zero-shot question answering across commonsense tasks. Guided by a set of hypotheses, the framework studies how to transform various pre-existing knowledge resources into a form that is most effective for pre-training models. We vary the set of language models, training regimes, knowledge sources, and data generation strategies, and measure their impact across tasks. Extending on prior work, we devise and compare four constrained distractor-sampling strategies. We provide empirical results across five commonsense question-answering tasks with data generated from five external knowledge resources. We show that, while an individual knowledge graph is better suited for specific tasks, a global knowledge graph brings consistent gains across different tasks. In addition, both preserving the structure of the task as well as generating fair and informative questions help language models learn more effectively.

Commonsense reasoning benchmarks have been largely solved by fine-tuning language models.The downside is that fine-tuning may cause models to overfit to task-specific data and thereby forget their knowledge gained during pre-training.Recent works only propose lightweight model updates as models may already possess useful knowledge from past experience, but a challenge remains in understanding what parts and to what extent models should be refined for a given task.In this paper, we investigate what models learn from commonsense reasoning datasets.We measure the impact of three different adaptation methods on the generalization and accuracy of models.Our experiments with two models show that fine-tuning performs best, by learning both the content and the structure of the task, but suffers from overfitting and limited generalization to novel answers.We observe that alternative adaptation methods like prefixtuning have comparable accuracy, but generalize better to unseen answers and are more robust to adversarial splits.

Ontologists build formal models to understand the structure of reality. The fun starts –and I had a lot of it back in the PhD days (!)– when Formal Ontology is applied to understand the structure of what we indisputably use to understand reality itself: the mind. Philosophers have spent lifetimes hovering over this conundrum but I stopped more than a decade ago. Fast-forwarding to the present, I have been busy with a not-so-distant, yet more mundane, problem: building ontologies for AI.

In this paper we propose an analysis and an upgrade of WordNet's top-level synset taxonomy. We briefly review WordNet and identify its main semantic limitations. Some principles from a forthcoming OntoClean methodology are applied to the ontological analysis of WordNet. A revised top-level taxonomy is proposed, which is meant to be more conceptually rigorous, cognitively transparent, and efficiently exploitable in several applications.