NLP in the era of generative AI, cognitive sciences, and societal transformation
Join us at Mila in October for a three-day workshop to explore the transformative potential of language technologies and their implications for society.
This program is designed to provide decision-makers, policymakers and professional working in policy with a foundational understanding of AI technology.
We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Commonly, learning-based topological navigation approaches produce a local policy while preserving some loose connectivity of the space thro… (see more)ugh a topological map. Nevertheless, spurious or missing edges in the topological graph often lead to navigation failure. In this work, we propose a sampling-based graph building method, which results in sparser graphs yet with higher navigation performance compared to baseline methods. We also propose graph maintenance strategies that eliminate spurious edges and expand the graph as needed, which improves lifelong navigation performance. Unlike controllers that learn from fixed training environments, we show that our model can be fine-tuned using only a small number of collected trajectory images from a real-world environment where the agent is deployed. We demonstrate successful navigation after fine-tuning on real-world environments, and notably show significant navigation improvements over time by applying our lifelong graph maintenance strategies.
Prompt tuning has recently emerged as an effective method for adapting pre-trained language models to a number of language understanding and… (see more) generation tasks. In this paper, we investigate prompt tuning for semantic parsing—the task of mapping natural language utterances onto formal meaning representations. On the low-resource splits of Overnight and TOPv2, we find that a prompt tuned T5-xl significantly outperforms its fine-tuned counterpart, as well as strong GPT-3 and BART baselines. We also conduct ablation studies across different model scales and target representations, finding that, with increasing model scale, prompt tuned T5 models improve at generating target representations that are far from the pre-training distribution.
To explain NLP models a popular approach is to use importance measures, such as attention, which inform input tokens are important for makin… (see more)g a prediction. However, an open question is how well these explanations accurately reflect a model's logic, a property called faithfulness. To answer this question, we propose Recursive ROAR, a new faithfulness metric. This works by recursively masking allegedly important tokens and then retraining the model. The principle is that this should result in worse model performance compared to masking random tokens. The result is a performance curve given a masking-ratio. Furthermore, we propose a summarizing metric using relative area-between-curves (RACU), which allows for easy comparison across papers, models, and tasks. We evaluate 4 different importance measures on 8 different datasets, using both LSTM-attention models and RoBERTa models. We find that the faithfulness of importance measures is both model-dependent and task-dependent. This conclusion contradicts previous evaluations in both computer vision and faithfulness of attention literature.
We evaluated the use of rapid antigen detection tests (RADT) for the diagnosis of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-… (see more)2) infection in school settings to determine RADT performance characteristics compared to PCR. Methods: We did a real-world, prospective observational cohort study where recruited high-school students and staff from two high-schools in Montreal (Canada) were followed from January 25th to June 10th, 2021. Twenty-five percent of asymptomatic participants were tested weekly by RADT (nasal) and PCR (gargle). Class contacts of a case were tested. Symptomatic participants were tested by RADT (nasal) and PCR (nasal and gargle). The number of cases/outbreak and number of outbreaks were compared to other high schools in the same area. Results: Overall, 2,099 students and 286 school staff members consented to participate. The overall RADT specificity varied from 99.8 to 100%, with a lower sensitivity, varying from 28.6% in asymptomatic to 83.3% in symptomatic participants. The number of outbreaks was not different in the 2 participating schools compared to other high schools in the same area, but included a greater proportion of asymptomatic cases. Returning students to school after a 7-day quarantine, with a negative PCR on D6-7 after exposure, did not lead to subsequent outbreaks, as shown by serial testing. Of cases for whom the source was known, 37 of 57 (72.5%) were secondary to household transmission, 13 (25%) to intra-school transmission and one to community contacts between students in the same school. Conclusion: RADT did not perform well as a screening tool in asymptomatic individuals. Reinforcing policies for symptom screening when entering schools and testing symptomatic individuals with RADT on the spot may avoid subsequent significant exposures in class.
Compositionality— the ability to combine familiar units like words into novel phrases and sentences— has been the focus of intense inter… (see more)est in artificial intelligence in recent years. To test compositional generalization in semantic parsing, Keysers et al. (2020) introduced Compositional Freebase Queries (CFQ). This dataset maximizes the similarity between the test and train distributions over primitive units, like words, while maximizing the compound divergence: the dissimilarity between test and train distributions over larger structures, like phrases. Dependency parsing, however, lacks a compositional generalization benchmark. In this work, we introduce a gold-standard set of dependency parses for CFQ, and use this to analyze the behaviour of a state-of-the art dependency parser (Qi et al., 2020) on the CFQ dataset. We find that increasing compound divergence degrades dependency parsing performance, although not as dramatically as semantic parsing performance. Additionally, we find the performance of the dependency parser does not uniformly degrade relative to compound divergence, and the parser performs differently on different splits with the same compound divergence. We explore a number of hypotheses for what causes the non-uniform degradation in dependency parsing performance, and identify a number of syntactic structures that drive the dependency parser’s lower performance on the most challenging splits.
Empirical science of neural scaling laws is a rapidly growing area of significant importance to the future of machine learning, particularly… (see more) in the light of recent breakthroughs achieved by large-scale pre-trained models such as GPT-3, CLIP and DALL-e. Accurately predicting the neural network performance with increasing resources such as data, compute and model size provides a more comprehensive evaluation of different approaches across multiple scales, as opposed to traditional point-wise comparisons of fixed-size models on fixed-size benchmarks, and, most importantly, allows for focus on the best-scaling, and thus most promising in the future, approaches. In this work, we consider a challenging problem of few-shot learning in image classification, especially when the target data distribution in the few-shot phase is different from the source, training, data distribution, in a sense that it includes new image classes not encountered during training. Our current main goal is to investigate how the amount of pre-training data affects the few-shot generalization performance of standard image classifiers. Our key observations are that (1) such performance improvements are well-approximated by power laws (linear log-log plots) as the training set size increases, (2) this applies to both cases of target data coming from either the same or from a different domain (i.e., new classes) as the training data, and (3) few-shot performance on new classes converges at a faster rate than the standard classification performance on previously seen classes. Our findings shed new light on the relationship between scale and generalization.
Explainability for machine learning models has gained considerable attention within the research community given the importance of deploying… (see more) more reliable machine-learning systems. In computer vision applications, generative counterfactual methods indicate how to perturb a model’s input to change its prediction, providing details about the model’s decision-making. Current methods tend to generate trivial counterfactuals about a model’s decisions, as they often suggest to exaggerate or remove the presence of the attribute being classified. For the machine learning practitioner, these types of counterfactuals offer little value, since they provide no new information about undesired model or data biases. In this work, we identify the problem of trivial counterfactual generation and we propose DiVE to alleviate it. DiVE learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss to uncover multiple valuable explanations about the model’s prediction. Further, we introduce a mechanism to prevent the model from producing trivial explanations. Experiments on CelebA and Synbols demonstrate that our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods. Code is available at https://github.com/ElementAI/beyond-trivial-explanations.
2021-10-10
2021 IEEE/CVF International Conference on Computer Vision (ICCV) (published)
Domain modelling transforms informal requirements written in natural language in the form of problem descriptions into concise and analyzabl… (see more)e domain models. As the manual construction of these domain models is often time-consuming, error-prone, and labor-intensive, several approaches already exist to automate domain modelling. However, the current approaches suffer from lower accuracy of extracted domain models and the lack of support for system-modeller interactions. To better assist modellers, we introduce DoMoBOT, a web-based Domain Modelling BOT. Our proposed bot combines artificial intelligence techniques such as natural language processing and machine learning to extract domain models with higher accuracy. More importantly, our bot incorporates a set of features to bring synergy between automated model extraction and bot-modeller interactions. During these interactions, the bot presents multiple possible solutions to a modeller for modelling scenarios present in a given problem description. The bot further enables modellers to switch to a particular solution and updates the other parts of the domain model proactively. In this tool demo paper, we demonstrate how the implementation and architecture of DoMoBOT support the paradigm of automated and interactive domain modelling for assisting modellers.
2021-10-10
2021 ACM/IEEE International Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C) (published)
We investigate the impact of aliasing on generalization in Deep Convolutional Networks and show that data augmentation schemes alone are una… (see more)ble to prevent it due to structural limitations in widely used architectures. Drawing insights from frequency analysis theory, we take a closer look at ResNet and EfficientNet architectures and review the trade-off between aliasing and information loss in each of their major components. We show how to mitigate aliasing by inserting non-trainable low-pass filters at key locations, particularly where networks lack the capacity to learn them. These simple architectural changes lead to substantial improvements in generalization on i.i.d. and even more on out-of-distribution conditions, such as image classification under natural corruptions on ImageNet-C [11] and few-shot learning on Meta-Dataset [26]. State-of-the art results are achieved on both datasets without introducing additional trainable parameters and using the default hyper-parameters of open source codebases.
2021-10-10
2021 IEEE/CVF International Conference on Computer Vision (ICCV) (published)
Model‐based development is a popular development approach in which software is implemented and verified based on a model of the required s… (see more)ystem. Finite state machines (FSMs) are widely used as models for systems in several domains. Validating that a model accurately represents the required behaviour involves the generation and execution of a large number of input sequences, which is often an expensive and time‐consuming process. In this paper, we speed up the execution of input sequences for FSM validation, by leveraging the high degree of parallelism of modern graphics processing units (GPUs) for the automatic execution of FSM input sequences in parallel on the GPU threads. We expand our existing work by providing techniques that improve the performance and scalability of this approach. We conduct extensive empirical evaluation using 15 large FSMs from the networking domain and measure GPU speed‐up over a 16‐core CPU, taking into account total GPU time, which includes both data transfer and kernel execution time. We found that GPUs execute FSM input sequences up to 9.28× faster than a 16‐core CPU, with an average speed‐up of 4.53× across all subjects. Our optimizations achieve an average improvement over existing work of 58.95% for speed‐up and scalability to large FSMs with over 2K states and 500K transitions. We also found that techniques aimed at reducing the number of required input sequences for large FSMs with high density were ineffective when applied to all‐transition pair coverage, thus emphasizing the need for approaches like ours that speed up input execution.
2021-10-08
Software Testing, Verification and Reliability (published)
Model‐based development is a popular development approach in which software is implemented and verified based on a model of the required s… (see more)ystem. Finite state machines (FSMs) are widely used as models for systems in several domains. Validating that a model accurately represents the required behaviour involves the generation and execution of a large number of input sequences, which is often an expensive and time‐consuming process. In this paper, we speed up the execution of input sequences for FSM validation, by leveraging the high degree of parallelism of modern graphics processing units (GPUs) for the automatic execution of FSM input sequences in parallel on the GPU threads. We expand our existing work by providing techniques that improve the performance and scalability of this approach. We conduct extensive empirical evaluation using 15 large FSMs from the networking domain and measure GPU speed‐up over a 16‐core CPU, taking into account total GPU time, which includes both data transfer and kernel execution time. We found that GPUs execute FSM input sequences up to 9.28× faster than a 16‐core CPU, with an average speed‐up of 4.53× across all subjects. Our optimizations achieve an average improvement over existing work of 58.95% for speed‐up and scalability to large FSMs with over 2K states and 500K transitions. We also found that techniques aimed at reducing the number of required input sequences for large FSMs with high density were ineffective when applied to all‐transition pair coverage, thus emphasizing the need for approaches like ours that speed up input execution.
We introduce the problem of jointly increasing school capacities and finding a student-optimal assignment in the expanded market. Due to the… (see more) impossibility of efficiently solving the problem with classical methods, we generalize existent mathematical programming formulations of stability constraints to our setting, most of which result in integer quadratically-constrained programs. In addition, we propose a novel mixed-integer linear programming formulation that is exponentially large on the problem size. We show that its stability constraints can be separated by exploiting the objective function, leading to an effective cutting-plane algorithm. We conclude the theoretical analysis of the problem by discussing some mechanism properties. On the computational side, we evaluate the performance of our approaches in a detailed study, and we find that our cutting-plane method outperforms our generalization of existing mixed-integer approaches. We also propose two heuristics that are effective for large instances of the problem. Finally, we use the Chilean school choice system data to demonstrate the impact of capacity planning under stability conditions. Our results show that each additional seat can benefit multiple students and that we can effectively target the assignment of previously unassigned students or improve the assignment of several students through improvement chains. These insights empower the decision-maker in tuning the matching algorithm to provide a fair application-oriented solution.