Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Recommendation": models, code, and papers

Multiview Variational Graph Autoencoders for Canonical Correlation Analysis

Oct 30, 2020
Yacouba Kaloga, Pierre Borgnat, Sundeep Prabhakar Chepuri, Patrice Abry, Amaury Habrard

We present a novel multiview canonical correlation analysis model based on a variational approach. This is the first nonlinear model that takes into account the available graph-based geometric constraints while being scalable for processing large scale datasets with multiple views. It is based on an autoencoder architecture with graph convolutional neural network layers. We experiment with our approach on classification, clustering, and recommendation tasks on real datasets. The algorithm is competitive with state-of-the-art multiview representation learning techniques.

* 4 pages, 3 figures, submitted 

  Access Paper or Ask Questions

Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions

Jul 13, 2020
Stephen Roller, Y-Lan Boureau, Jason Weston, Antoine Bordes, Emily Dinan, Angela Fan, David Gunning, Da Ju, Margaret Li, Spencer Poff, Pratik Ringshia, Kurt Shuster, Eric Michael Smith, Arthur Szlam, Jack Urbanek, Mary Williamson

We present our view of what is necessary to build an engaging open-domain conversational agent: covering the qualities of such an agent, the pieces of the puzzle that have been built so far, and the gaping holes we have not filled yet. We present a biased view, focusing on work done by our own group, while citing related work in each area. In particular, we discuss in detail the properties of continual learning, providing engaging content, and being well-behaved -- and how to measure success in providing them. We end with a discussion of our experience and learnings, and our recommendations to the community.

  Access Paper or Ask Questions

Building Safer AGI by introducing Artificial Stupidity

Aug 11, 2018
Michaël Trazzi, Roman V. Yampolskiy

Artificial Intelligence (AI) achieved super-human performance in a broad variety of domains. We say that an AI is made Artificially Stupid on a task when some limitations are deliberately introduced to match a human's ability to do the task. An Artificial General Intelligence (AGI) can be made safer by limiting its computing power and memory, or by introducing Artificial Stupidity on certain tasks. We survey human intellectual limits and give recommendations for which limits to implement in order to build a safe AGI.

  Access Paper or Ask Questions

Towards Semantic Modeling of Contradictions and Disagreements: A Case Study of Medical Guidelines

Aug 02, 2017
Wlodek Zadrozny, Hossein Hematialam, Luciana Garbayo

We introduce a formal distinction between contradictions and disagreements in natural language texts, motivated by the need to formally reason about contradictory medical guidelines. This is a novel and potentially very useful distinction, and has not been discussed so far in NLP and logic. We also describe a NLP system capable of automated finding contradictory medical guidelines; the system uses a combination of text analysis and information retrieval modules. We also report positive evaluation results on a small corpus of contradictory medical recommendations.

* 5 pages, 1 figure, accepted at 12th International Conference on Computational Semantics (IWCS-2017) 

  Access Paper or Ask Questions

On the relation between accuracy and fairness in binary classification

May 21, 2015
Indre Zliobaite

Our study revisits the problem of accuracy-fairness tradeoff in binary classification. We argue that comparison of non-discriminatory classifiers needs to account for different rates of positive predictions, otherwise conclusions about performance may be misleading, because accuracy and discrimination of naive baselines on the same dataset vary with different rates of positive predictions. We provide methodological recommendations for sound comparison of non-discriminatory classifiers, and present a brief theoretical and empirical analysis of tradeoffs between accuracy and non-discrimination.

* Accepted for presentation to the 2nd workshop on Fairness, Accountability, and Transparency in Machine Learning (

  Access Paper or Ask Questions

Automatically Restructuring Practice Guidelines using the GEM DTD

Jun 08, 2007
Amanda Bouffier, Thierry Poibeau

This paper describes a system capable of semi-automatically filling an XML template from free texts in the clinical domain (practice guidelines). The XML template includes semantic information not explicitly encoded in the text (pairs of conditions and actions/recommendations). Therefore, there is a need to compute the exact scope of conditions over text sequences expressing the required actions. We present a system developed for this task. We show that it yields good performance when applied to the analysis of French practice guidelines.

* Proceedings of Biomedical Natural Language Processing (BioNLP) (2007) - 

  Access Paper or Ask Questions

Improving Deep Learning Model Robustness Against Adversarial Attack by Increasing the Network Capacity

Apr 24, 2022
Marco Marchetti, Edmond S. L. Ho

Nowadays, we are more and more reliant on Deep Learning (DL) models and thus it is essential to safeguard the security of these systems. This paper explores the security issues in Deep Learning and analyses, through the use of experiments, the way forward to build more resilient models. Experiments are conducted to identify the strengths and weaknesses of a new approach to improve the robustness of DL models against adversarial attacks. The results show improvements and new ideas that can be used as recommendations for researchers and practitioners to create increasingly better DL algorithms.

  Access Paper or Ask Questions

One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia

Mar 24, 2022
Alham Fikri Aji, Genta Indra Winata, Fajri Koto, Samuel Cahyawijaya, Ade Romadhony, Rahmad Mahendra, Kemal Kurniawan, David Moeljadi, Radityo Eko Prasojo, Timothy Baldwin, Jey Han Lau, Sebastian Ruder

NLP research is impeded by a lack of resources and awareness of the challenges presented by underrepresented languages and dialects. Focusing on the languages spoken in Indonesia, the second most linguistically diverse and the fourth most populous nation of the world, we provide an overview of the current state of NLP research for Indonesia's 700+ languages. We highlight challenges in Indonesian NLP and how these affect the performance of current NLP systems. Finally, we provide general recommendations to help develop NLP technology not only for languages of Indonesia but also other underrepresented languages.

* Accepted in ACL 2022 

  Access Paper or Ask Questions

The State of SLIVAR: What's next for robots, human-robot interaction, and (spoken) dialogue systems?

Aug 24, 2021
Casey Kennington

We synthesize the reported results and recommendations of recent workshops and seminars that convened to discuss open questions within the important intersection of robotics, human-robot interaction, and spoken dialogue systems research. The goal of this growing area of research interest is to enable people to more effectively and naturally communicate with robots. To carry forward opportunities networking and discussion towards concrete, potentially fundable projects, we encourage interested parties to consider participating in future virtual and in-person discussions and workshops.

* 6 pages 

  Access Paper or Ask Questions