Neural Networks require large amounts of memory and compute to process high resolution images, even when only a small part of the image is actually informative for the task at hand. We propose a method based on a differentiable Top-K operator to select the most relevant parts of the input to efficiently process high resolution images. Our method may be interfaced with any downstream neural network, is able to aggregate information from different patches in a flexible way, and allows the whole model to be trained end-to-end using backpropagation. We show results for traffic sign recognition, inter-patch relationship reasoning, and fine-grained recognition without using object/part bounding box annotations during training.

Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed representations that do not capture the compositional properties of natural scenes. In this paper, we present the Slot Attention module, an architectural component that interfaces with perceptual representations such as the output of a convolutional neural network and produces a set of task-dependent abstract representations which we call slots. These slots are exchangeable and can bind to any object in the input by specializing through a competitive procedure over multiple rounds of attention. We empirically demonstrate that Slot Attention can extract object-centric representations that enable generalization to unseen compositions when trained on unsupervised object discovery and supervised property prediction tasks.

Recent development of large-scale question answering (QA) datasets triggered a substantial amount of research into end-toend neural architectures for QA.Increasingly complex systems have been conceived without comparison to simpler neural baseline systems that would justify their complexity.In this work, we propose a simple heuristic that guides the development of neural baseline systems for the extractive QA task.We find that there are two ingredients necessary for building a high-performing neural QA system: first, the awareness of question words while processing the context and second, a composition function that goes beyond simple bag-of-words modeling, such as recurrent neural networks.Our results show that FastQA, a system that meets these two requirements, can achieve very competitive performance compared with existing models.We argue that this surprising finding puts results of previous systems and the complexity of recent QA datasets into perspective.

Factoid question answering (QA) has recently benefited from the development of deep learning (DL) systems.Neural network models outperform traditional approaches in domains where large datasets exist, such as SQuAD (≈ 100, 000 questions) for Wikipedia articles.However, these systems have not yet been applied to QA in more specific domains, such as biomedicine, because datasets are generally too small to train a DL system from scratch.For example, the BioASQ dataset for biomedical QA comprises less then 900 factoid (single answer) and list (multiple answers) QA instances.In this work, we adapt a neural QA system trained on a large open-domain dataset (SQuAD, source) to a biomedical dataset (BioASQ, target) by employing various transfer learning techniques.Our network architecture is based on a state-of-theart QA system, extended with biomedical word embeddings and a novel mechanism to answer list questions.In contrast to existing biomedical QA systems, our system does not rely on domain-specific ontologies, parsers or entity taggers, which are expensive to create.Despite this fact, our systems achieve state-of-the-art results on factoid questions and competitive results on list questions.

Coreference resolution for event mentions enables extraction systems to process document-level information.Current systems in this area base their decisions on rich semantic features from various knowledge bases, thus restricting them to domains where such external sources are available.We propose a model for this task which does not rely on such features but instead utilizes sentential features coming from convolutional neural networks.Two such networks first process coreference candidates and their respective context, thereby generating latent-feature representations which are tuned towards event aspects relevant for a linking decision.These representations are augmented with lexicallevel and pairwise features, and serve as input to a trainable similarity function producing a coreference score.Our model achieves state-of-the-art performance on two datasets, one of which is publicly available.An error analysis points out directions for further research.

In this paper, we present a novel approach to joint word sense disambiguation (WSD) and entity linking (EL) that combines a set of complementary objectives in an extensible multi-objective formalism. During disambiguation the system performs continuous optimization to find optimal probability distributions over candidate senses. The performance of our system on nominal WSD as well as EL improves state-ofthe-art results on several corpora. These improvements demonstrate the importance of combining complementary objectives in a joint model for robust disambiguation.

BACKGROUND: This article provides an overview of the first BIOASQ challenge, a competition on large-scale biomedical semantic indexing and question answering (QA), which took place between March and September 2013. BIOASQ assesses the ability of systems to semantically index very large numbers of biomedical scientific articles, and to return concise and user-understandable answers to given natural language questions by combining information from biomedical articles and ontologies. RESULTS: The 2013 BIOASQ competition comprised two tasks, Task 1a and Task 1b. In Task 1a participants were asked to automatically annotate new PUBMED documents with MESH headings. Twelve teams participated in Task 1a, with a total of 46 system runs submitted, and one of the teams performing consistently better than the MTI indexer used by NLM to suggest MESH headings to curators. Task 1b used benchmark datasets containing 29 development and 282 test English questions, along with gold standard (reference) answers, prepared by a team of biomedical experts from around Europe and participants had to automatically produce answers. Three teams participated in Task 1b, with 11 system runs. The BIOASQ infrastructure, including benchmark datasets, evaluation mechanisms, and the results of the participants and baseline methods, is publicly available. CONCLUSIONS: A publicly available evaluation infrastructure for biomedical semantic indexing and QA has been developed, which includes benchmark datasets, and can be used to evaluate systems that: assign MESH headings to published articles or to English questions; retrieve relevant RDF triples from ontologies, relevant articles and snippets from PUBMED Central; produce "exact" and paragraph-sized "ideal" answers (summaries). The results of the systems that participated in the 2013 BIOASQ competition are promising. In Task 1a one of the systems performed consistently better from the NLM's MTI indexer. In Task 1b the systems received high scores in the manual evaluation of the "ideal" answers; hence, they produced high quality summaries as answers. Overall, BIOASQ helped obtain a unified view of how techniques from text classification, semantic indexing, document and passage retrieval, question answering, and text summarization can be combined to allow biomedical experts to obtain concise, user-understandable answers to questions reflecting their real information needs.