Publications

Can a Gorilla Ride a Camel? Learning Semantic Plausibility from Text
Ian Porada
Kaheer Suleman
Jackie CK Cheung
2019-10-31
Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing (published)
doi.org
arxiv.org
CoQA: A Conversational Question Answering Challenge
Siva Reddy
Danqi Chen
Christopher D Manning
Humans gather information through conversations involving a series of interconnected questions and answers. For machines to assist in inform… (see more)ation gathering, it is therefore essential to enable them to answer conversational questions. We introduce CoQA, a novel dataset for building Conversational Question Answering systems. Our dataset contains 127k questions with answers, obtained from 8k conversations about text passages from seven diverse domains. The questions are conversational, and the answers are free-form text with their corresponding evidence highlighted in the passage. We analyze CoQA in depth and show that conversational questions have challenging phenomena not present in existing reading comprehension datasets (e.g., coreference and pragmatic reasoning). We evaluate strong dialogue and reading comprehension models on CoQA. The best system obtains an F1 score of 65.4%, which is 23.4 points behind human performance (88.8%), indicating that there is ample room for improvement. We present CoQA as a challenge to the community at https://stanfordnlp.github.io/coqa.
2019-10-31
Transactions of the Association for Computational Linguistics (published)
doi.org
arxiv.org
Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses
Matt Grenander
Yue Dong
Jackie CK Cheung
Annie Priyadarshini Louis
Sentence position is a strong feature for news summarization, since the lead often (but not always) summarizes the key points of the article… (see more). In this paper, we show that recent neural systems excessively exploit this trend, which although powerful for many inputs, is also detrimental when summarizing documents where important content should be extracted from later parts of the article. We propose two techniques to make systems sensitive to the importance of content in different parts of the article. The first technique employs ‘unbiased’ data; i.e., randomly shuffled sentences of the source document, to pretrain the model. The second technique uses an auxiliary ROUGE-based loss that encourages the model to distribute importance scores throughout a document by mimicking sentence-level ROUGE scores on the training data. We show that these techniques significantly improve the performance of a competitive reinforcement learning based extractive system, with the auxiliary loss being more powerful than pretraining.
2019-10-31
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (published)
doi.org
arxiv.org
Fear in Hebrew
Tal Arbel
2019-10-31
Historical Studies in the Natural Sciences (published)
doi.org
How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG
Paul Trichelair
Ali Emami
Adam Trischler
Kaheer Suleman
Jackie CK Cheung
Recent studies have significantly improved the state-of-the-art on common-sense reasoning (CSR) benchmarks like the Winograd Schema Challeng… (see more)e (WSC) and SWAG. The question we ask in this paper is whether improved performance on these benchmarks represents genuine progress towards common-sense-enabled systems. We make case studies of both benchmarks and design protocols that clarify and qualify the results of previous work by analyzing threats to the validity of previous experimental designs. Our protocols account for several properties prevalent in common-sense benchmarks including size limitations, structural regularities, and variable instance difficulty.
2019-10-31
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (published)
doi.org
arxiv.org
Interactive Language Learning by Question Answering
Xingdi Yuan
Marc-Alexandre Côté
Jie Fu
Zhouhan Lin
Christopher Pal
Yoshua Bengio
Adam Trischler
Humans observe and interact with the world to acquire knowledge. However, most existing machine reading comprehension (MRC) tasks miss the i… (see more)nteractive, information-seeking component of comprehension. Such tasks present models with static documents that contain all necessary information, usually concentrated in a single short substring. Thus, models can achieve strong performance through simple word- and phrase-based pattern matching. We address this problem by formulating a novel text-based question answering task: Question Answering with Interactive Text (QAit). In QAit, an agent must interact with a partially observable text-based environment to gather information required to answer questions. QAit poses questions about the existence, location, and attributes of objects found in the environment. The data is built using a text-based game generator that defines the underlying dynamics of interaction with the environment. We propose and evaluate a set of baseline models for the QAit task that includes deep reinforcement learning agents. Experiments show that the task presents a major challenge for machine reading systems, while humans solve it with relative ease.
2019-10-31
Conference on Empirical Methods in Natural Language Processing and International Joint Conference on Natural Language Processing (published)
doi.org
arxiv.org
Referring Expression Generation Using Entity Profiles
Meng Cao
Jackie Chi Kit Cheung
Meng Cao, Jackie Chi Kit Cheung. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th Internat… (see more)ional Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
2019-10-31
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (published)
doi.org
arxiv.org
Structure Learning for Neural Module Networks
Vardaan Pahuja
Jie Fu
A. Chandar
Christopher Pal
Neural Module Networks, originally proposed for the task of visual question answering, are a class of neural network architectures that invo… (see more)lve human-specified neural modules, each designed for a specific form of reasoning. In current formulations of such networks only the parameters of the neural modules and/or the order of their execution is learned. In this work, we further expand this approach and also learn the underlying internal structure of modules in terms of the ordering and combination of simple and elementary arithmetic operators. We utilize a minimum amount of prior knowledge from the human-specified neural modules in the form of different input types and arithmetic operators used in these modules. Our results show that one is indeed able to simultaneously learn both internal module structure and module sequencing without extra supervisory signals for module execution sequencing. With this approach, we report performance comparable to models using hand-designed modules. In addition, we do a analysis of sensitivity of the learned modules w.r.t. the arithmetic operations and infer the analytical expressions of the learned modules.
2019-10-31
Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN) (published)
doi.org
arxiv.org
Fluoroquinolone Use and Seasonal Patterns of Ciprofloxacin Resistance in Community-Acquired Urinary Escherichia coli Infection in a Large Urban Center
Jean-Paul R Soucy
Alexandra M. Schmidt
Caroline Quach
David L Buckeridge
2019-10-28
American Journal of Epidemiology (published)
doi.org
Ordered Memory
Yikang Shen
Shawn Tan
Arian Hosseini
Zhouhan Lin
Alessandro Sordoni
Aaron Courville
Stack-augmented recurrent neural networks (RNNs) have been of interest to the deep learning community for some time. However, the difficulty… (see more) of training memory models remains a problem obstructing the widespread use of such models. In this paper, we propose the Ordered Memory architecture. Inspired by Ordered Neurons (Shen et al., 2018), we introduce a new attention-based mechanism and use its cumulative probability to control the writing and erasing operation of the memory. We also introduce a new Gated Recursive Cell to compose lower-level representations into higher-level representation. We demonstrate that our model achieves strong performance on the logical inference task (Bowman et al., 2015)and the ListOps (Nangia and Bowman, 2018) task. We can also interpret the model to retrieve the induced tree structure, and find that these induced structures align with the ground truth. Finally, we evaluate our model on the Stanford SentimentTreebank tasks (Socher et al., 2013), and find that it performs comparatively with the state-of-the-art methods in the literature.
2019-10-28
ArXiv (preprint)
doi.org
arxiv.org
A deep learning framework for neuroscience
Blake Aaron Richards
Timothy P Lillicrap
Philippe Beaudoin
Yoshua Bengio
Rafal Bogacz
Amelia Christensen
Claudia Clopath
Rui Ponte Costa
Archy de Berker
Surya Ganguli
Colleen J Gillon
Danijar Hafner
Adam Kepecs
Nikolaus Kriegeskorte
Peter Latham
Grace W. Lindsay
Kenneth D. Miller
Richard Naud
Christopher C. Pack
Panayiota Poirazi … (see 12 more)
Pieter Roelfsema
João Sacramento
Andrew Saxe
Benjamin Scellier
Anna C. Schapiro
Walter Senn
Greg Wayne
Daniel Yamins
Friedemann Zenke
Joel Zylberberg
Denis Therien
Konrad Paul Kording
2019-10-27
Nature Neuroscience (published)
doi.org
Collegiality as political work: Professions in today’s world of organizations
Jean-Louis Denis
Gianluca Veronesi
Catherine Régis
Sabrina Germain
Collegiality is frequently portrayed as an inherent characteristic of professions, associated with normative expectations autonomously deter… (see more)mined and regulated among peers. However, in advanced modernity other modes of governance responding to societal expectations and increasing state reliance on professional expertise often appear in tension with conditions of collegiality. This article argues that collegiality is not an immutable and inherent characteristic of the governance of professional work and organizations; rather, it is the result of the ability of a profession to operationalize the normative, relational, and structural requirements of collegiality at work. This article builds on different streams of scholarship to present a dynamic approach to collegiality based on political work by professionals to protect, maintain, and reformulate collegiality as a core set of principles governing work. Productive resistance and co-production are explored for their contribution to collegiality in this context, enabling accommodation between professions and organizations to achieve collective objectives and serving as a vector of change and adaptation of professional work in contemporary organizations. Engagement in co-production influences the ability to materialize collegiality at work, just as the maintenance and transformation of collegiality will operate in a context where professions participate and negotiate compromises with others legitimate modes of governance. Our arguments build on recent studies and hypotheses concerning the interface of professions and organizations to reveal the political work that underlies the affirmation and re-affirmation of collegiality as a mode of governance of work based on resistance and co-production.
2019-10-23
Journal of Professions and Organization (published)
doi.org