In this paper, we present CorefQA, an accurate and extensible approach for the coreference resolution task.We formulate the problem as a span prediction task, like in question answering: A query is generated for each candidate mention using its surrounding context, and a span prediction module is employed to extract the text spans of the coreferences within the document using the generated query.This formulation comes with the following key advantages: (1) The span prediction strategy provides the flexibility of retrieving mentions left out at the mention proposal stage; (2) In the question answering framework, encoding the mention and its context explicitly in a query makes it possible to have a deep and thorough examination of cues embedded in the context of coreferent mentions; and (3) A plethora of existing question answering datasets can be used for data augmentation to improve the model's generalization capability.Experiments demonstrate significant performance boost over previous models, with 83.1 (+3.5)F1 score on the CoNLL-2012 benchmark and 87.5 (+2.5)F1 score on the GAP benchmark.1

Modeling visual search not only offers an opportunity to predict the usability of an interface before actually testing it on real users but also advances scientific understanding about human behavior. In this work, we first conduct a set of analyses on a large-scale dataset of visual search tasks on realistic webpages. We then present a deep neural network that learns to predict the scannability of webpage content, i.e., how easy it is for a user to find a specific target. Our model leverages both heuristic-based features such as target size and unstructured features such as raw image pixels. This approach allows us to model complex interactions that might be involved in a realistic visual search task, which can not be achieved by traditional analytical models. We analyze the model behavior to offer our insights into how the salience map learned by the model aligns with human intuition.

Segmenting a chunk of text into words is usually the first step of processing Chinese text, but its necessity has rarely been explored.In this paper, we ask the fundamental question of whether Chinese word segmentation (CWS) is necessary for deep learning-based Chinese Natural Language Processing.We benchmark neural word-based models which rely on word segmentation against neural char-based models which do not involve word segmentation in four end-to-end NLP benchmark tasks: language modeling, machine translation, sentence matching/paraphrase and text classification.Through direct comparisons between these two types of models, we find that charbased models consistently outperform wordbased models.Based on these observations, we conduct comprehensive experiments to study why wordbased models underperform char-based models in these deep learning-based NLP tasks.We show that it is because word-based models are more vulnerable to data sparsity and the presence of out-of-vocabulary (OOV) words, and thus more prone to overfitting.We hope this paper could encourage researchers in the community to rethink the necessity of word segmentation in deep learning-based Chinese Natural Language Processing. 1

In this paper, we propose a new paradigm for the task of entity-relation extraction.We cast the task as a multi-turn question answering problem, i.e., the extraction of entities and relations is transformed to the task of identifying answer spans from the context.This multi-turn QA formalization comes with several key advantages: firstly, the question query encodes important information for the entity/relation class we want to identify; secondly, QA provides a natural way of jointly modeling entity and relation; and thirdly, it allows us to exploit the well developed machine reading comprehension (MRC) models.Experiments on the ACE and the CoNLL04 corpora demonstrate that the proposed paradigm significantly outperforms previous best models.We are able to obtain the stateof-the-art results on all of the ACE04, ACE05 and CoNLL04 datasets, increasing the SOTA results on the three datasets to 49.4 (+1.0), 60.2 (+0.6) and 68.9 (+2.1), respectively.Additionally, we construct a newly developed dataset RESUME in Chinese, which requires multi-step reasoning to construct entity dependencies, as opposed to the single-step dependency extraction in the triplet exaction in previous datasets.The proposed multi-turn QA model also achieves the best performance on the RESUME dataset. 1

In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models is not well understood. In this paper we propose a framework to systematically investigate bias and generalization in deep generative models of images by probing the learning algorithm with carefully designed training datasets. By measuring properties of the learned distribution, we are able to find interesting patterns of generalization. We verify that these patterns are consistent across datasets, common models and architectures.