Generative adversarial networks (GANs) have shown considerable success, especially in the realistic generation of images. In this work, we apply similar techniques for the generation of text. We propose a novel approach to handle the discrete nature of text, during training, using word embeddings. Our method is agnostic to vocabulary size and achieves competitive results relative to methods with various discrete gradient estimators. L = L critic + λEx ∼p(x) [(||∇xD(x)|| 2 − 1) 2 ] (2)

The degree of semantic relatedness (or, closeness in meaning) of two units of language has long been considered fundamental to understanding meaning. Automatically determining relatedness has many applications such as question answering and summarization. However, prior NLP work has largely focused on semantic similarity (a subset of relatedness), because of a lack of relatedness datasets. Here for the first time, we introduce a dataset of semantic relatedness for sentence pairs. This dataset, STR-2021, has 5,500 English sentence pairs manually annotated for semantic relatedness using a comparative annotation framework. We show that the resulting scores have high reliability (repeat annotation correlation of 0.84). We use the dataset to explore a number of questions on what makes two sentences more semantically related. We also evaluate a suite of sentence representation methods on their ability to place pairs that are more related closer to each other in vector space.

No abstract

Learning disentangled representations of texts, which encode information pertaining to different aspects of the text in separate representations, is an active area of research in NLP for controllable and interpretable text generation. These methods have, for the most part, been developed in the context of text style transfer, but are limited in their evaluation. In this work, we look at the motivation behind learning disentangled representations of content and style for texts and at the potential use-cases when compared to end-to-end methods. We then propose evaluation metrics that correspond to these use-cases. We conduct a systematic investigation of previously proposed loss functions for such models and we evaluate them on a highly-structured and synthetic natural language dataset that is well-suited for the task of disentangled representation learning, as well as two other parallel style transfer datasets. Our results demonstrate that current models still require considerable amounts of supervision in order to achieve good performance.

According to the literary theory of Mikhail Bakhtin, a dialogic novel is one in which characters speak in their own distinct voices, rather than serving as mouthpieces for their authors. We use text classification to determine which authors best achieve dialogism, looking at a corpus of plays from the late nineteenth and early twentieth centuries. We find that the SAGE model of text generation, which highlights deviations from a background lexical distribution, is an effective method of weighting the words of characters' utterances. Our results show that it is indeed possible to distinguish characters by their speech in the plays of canonical writers such as George Bernard Shaw, whereas characters are clustered more closely in the works of lesser-known playwrights.