Every natural text is written in some style. The style is formed by a complex combination of different stylistic factors, including formality markers, emotions, metaphor, etc. Some factors implicitly reflect the author's personality, while others are explicitly controlled by the author's choices in order to achieve some personal or social goal. One cannot form a complete understanding of a text and its author without considering these factors. The factors combine and co-vary in complex ways to form styles. Studying the nature of the covarying combinations sheds light on stylistic language in general, sometimes called crossstyle language understanding. This paper provides a benchmark corpus (xSLUE) with an online platform (http://xslue.com) for crossstyle language understanding and evaluation. The benchmark contains text in 15 different styles and 23 classification tasks. For each task, we provide the fine-tuned classifier for further analysis. Our analysis shows that some styles are highly dependent on each other (e.g., impoliteness and offense), and some domains (e.g., tweets, political debates) are stylistically more diverse than others (e.g., academic manuscripts). We discuss the technical challenges of cross-style understanding and potential directions for future research: crossstyle modeling which shares the internal representation for low-resource or low-performance styles and other applications such as crossstyle generation.

No abstract

This paper investigates the ability of artificial neural networks to judge the grammatical acceptability of a sentence. Machine learning research of this kind is well placed to answer important open questions about the role of prior linguistic bias in language acquisition by providing a test for the Poverty of the Stimulus Argument. In service of this goal, we introduce the Corpus of Linguistic Acceptability (CoLA), a set of 10,657 English sentences labeled as grammatical or ungrammatical from published linguistics literature. As baselines, we train several recurrent neural network models for acceptability classification. These models show promise on the task, and error-analysis on specific grammatical phenomena reveals that they learn some systematic generalizations like subject-verbobject word order without any grammatical supervision. However, human-like performance across a wide range of grammatical constructions remains far off.

Studies have shown that a dominant class of questions asked by visually impaired users on images of their surroundings involves reading text in the image. But today's VQA models can not read! Our paper takes a first step towards addressing this problem. First, we introduce a new "TextVQA" dataset to facilitate progress on this important problem. Existing datasets either have a small proportion of questions about text (e.g., the VQA dataset) or are too small (e.g., the VizWiz dataset). TextVQA contains 45,336 questions on 28,408 images that require reasoning about text to answer. Second, we introduce a novel model architecture that reads text in the image, reasons about it in the context of the image and the question, and predicts an answer which might be a deduction based on the text and the image or is composed of the strings found in the image. Consequently, we call our approach Look, Read, Reason & Answer (LoRRA) 1 . We show that LoRRA outperforms existing state-of-the-art VQA models on our TextVQA dataset. We find that the gap between human performance and machine performance is significantly larger on TextVQA than on VQA 2.0, suggesting that TextVQA is well-suited to benchmark progress along directions complementary to VQA 2.0. VQA ComponentSimilar to many VQA models [7,17], we first embed the question words w 1 , w 2 , . . . , w L of the question q with a pre-trained embedding function (e.g. GloVe [36]) and then encode the resultant word embeddings iteratively with a re-

No abstract

No abstract

No abstract

No abstract