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.)?
Publications
Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus
The ability to ask questions is important in both human and machine intelligence. Learning to ask questions helps knowledge acquisition, imp… (see more)roves question-answering and machine reading comprehension tasks, and helps a chatbot to keep the conversation flowing with a human. Existing question generation models are ineffective at generating a large amount of high-quality question-answer pairs from unstructured text, since given an answer and an input passage, question generation is inherently a one-to-many mapping. In this paper, we propose Answer-Clue-Style-aware Question Generation (ACS-QG), which aims at automatically generating high-quality and diverse question-answer pairs from unlabeled text corpus at scale by imitating the way a human asks questions. Our system consists of: i) an information extractor, which samples from the text multiple types of assistive information to guide question generation; ii) neural question generators, which generate diverse and controllable questions, leveraging the extracted assistive information; and iii) a neural quality controller, which removes low-quality generated data based on text entailment. We compare our question generation models with existing approaches and resort to voluntary human evaluation to assess the quality of the generated question-answer pairs. The evaluation results suggest that our system dramatically outperforms state-of-the-art neural question generation models in terms of the generation quality, while being scalable in the meantime. With models trained on a relatively smaller amount of data, we can generate 2.8 million quality-assured question-answer pairs from a million sentences found in Wikipedia.
2020-04-20
Proceedings of The Web Conference 2020 (published)
The problem of selecting a subset of nodes with greatest influence in a graph, commonly known as influence maximization, has been well studi… (see more)ed over the past decade. This problem has real world applications which can potentially affect lives of individuals. Algorithmic decision making in such domains raises concerns about their societal implications. One of these concerns, which surprisingly has only received limited attention so far, is algorithmic bias and fairness. We propose a flexible framework that extends and unifies the existing works in fairness-aware influence maximization. This framework is based on an integer programming formulation of the influence maximization problem. The fairness requirements are enforced by adding linear constraints or modifying the objective function. Contrary to the previous work which designs specific algorithms for each variant, we develop a formalism which is general enough for specifying different notions of fairness. A problem defined in this formalism can be then solved using efficient mixed integer programming solvers. The experimental evaluation indicates that our framework not only is general but also is competitive with existing algorithms.
2020-04-20
Companion Proceedings of the Web Conference 2020 (published)
In this paper, we develop a metric designed to assess and rank uncertainty measures for the task of brain tumour sub-tissue segmentation in … (see more)the BraTS 2019 sub-challenge on uncertainty quantification. The metric is designed to: (1) reward uncertainty measures where high confidence is assigned to correct assertions, and where incorrect assertions are assigned low confidence and (2) penalize measures that have higher percentages of under-confident correct assertions. Here, the workings of the components of the metric are explored based on a number of popular uncertainty measures evaluated on the BraTS 2019 dataset.
We develop clustering procedures for longitudinal trajectories based on a continuous-time hidden Markov model (CTHMM) and a generalized line… (see more)ar observation model. Specifically in this paper, we carry out infinite mixture model-based clustering for CTHMM and achieve inference using Markov chain Monte Carlo (MCMC). Specifically, for Bayesian nonparametric inference using a Dirichlet process mixture model, we utilize restricted Gibbs sampling split-merge proposals to expedite the MCMC algorithm. We employ the proposed algorithm to the simulated data as well as a large real data example, and the results demonstrate the desired performance of the new sampler.
Accurate detection and segmentation of new lesional activity in longitudinal Magnetic Resonance Images (MRIs) of patients with Multiple Scle… (see more)rosis (MS) is important for monitoring disease activity, as well as for assessing treatment effects. In this work, we present the first deep learning framework to automatically detect and segment new and enlarging (NE) T2w lesions from longitudinal brain MRIs acquired from relapsing-remitting MS (RRMS) patients. The proposed framework is an adapted 3D U-Net [1] which includes as inputs the reference multi-modal MRI and T2-weighted lesion maps, as well an attention mechanism based on the subtraction MRI (between the two timepoints) which serves to assist the network in learning to differentiate between real anatomical change and artifactual change, while constraining the search space for small lesions. Experiments on a large, proprietary, multi -center, multi-modal, clinical trial dataset consisting of 1677 multi-modal scans illustrate that network achieves high overall detection accuracy (detection AUC=.95), outperforming (1) a U-Net without an attention mechanism (de-tection AUC=.93), (2) a framework based on subtracting independent T2-weighted segmentations (detection AUC=.57), and (3) DeepMedic (detection AUC=.84) [2], particularly for small lesions. In addition, the method was able to accurately classify patients as active/inactive with (sensitivities of. 69 and specificities of. 97).
2020-04-03
2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI) (published)
We propose a novel dialogue modeling framework, the first-ever nonparametric kernel functions based approach for dialogue modeling, which le… (see more)arns hashcodes as text representations; unlike traditional deep learning models, it handles well relatively small datasets, while also scaling to large ones. We also derive a novel lower bound on mutual information, used as a model-selection criterion favoring representations with better alignment between the utterances of participants in a collaborative dialogue setting, as well as higher predictability of the generated responses. As demonstrated on three real-life datasets, including prominently psychotherapy sessions, the proposed approach significantly outperforms several state-of-art neural network based dialogue systems, both in terms of computational efficiency, reducing training time from days or weeks to hours, and the response quality, achieving an order of magnitude improvement over competitors in frequency of being chosen as the best model by human evaluators.
2020-04-03
AAAI Conference on Artificial Intelligence (published)
Temporal abstraction refers to the ability of an agent to use behaviours of controllers which act for a limited, variable amount of time. Th… (see more)e options framework describes such behaviours as consisting of a subset of states in which they can initiate, an internal policy and a stochastic termination condition. However, much of the subsequent work on option discovery has ignored the initiation set, because of difficulty in learning it from data. We provide a generalization of initiation sets suitable for general function approximation, by defining an interest function associated with an option. We derive a gradient-based learning algorithm for interest functions, leading to a new interest-option-critic architecture. We investigate how interest functions can be leveraged to learn interpretable and reusable temporal abstractions. We demonstrate the efficacy of the proposed approach through quantitative and qualitative results, in both discrete and continuous environments.
2020-04-03
Proceedings of the AAAI Conference on Artificial Intelligence (published)
Traceability between published scientific breakthroughs and their implementation is essential, especially in the case of Open Source Softwar… (see more)e implements bleeding edge science into its code. However, aligning the link between GitHub repositories and academic papers can prove difficult, and the link impact remains unknown. This paper investigates the role of academic paper references contained in these repositories. We conducted a large-scale study of 20 thousand GitHub repositories to establish prevalence of references to academic papers. We use a mixed-methods approach to identify Open Access (OA), traceability and evolutionary aspects of the links. Although referencing a paper is not typical, we find that a vast majority of referenced academic papers are OA. In terms of traceability, our analysis revealed that machine learning is the most prevalent topic of repositories. These repositories tend to be affiliated with academic communities. More than half of the papers do not link back to any repository. A case study of referenced arXiv paper shows that most of these papers are high-impact and influential and do align with academia, referenced by repositories written in different programming languages. From the evolutionary aspect, we find very few changes of papers being referenced and links to them.