In this work, we design an end-to-end model for poetry generation based on conditioned recurrent neural network (RNN) language models whose goal is to learn stylistic features (poem length, sentiment, alliteration, and rhyming) from examples alone. W
e show this model successfully learns the meaning' of length and sentiment, as we can control it to generate longer or shorter as well as more positive or more negative poems. However, the model does not grasp sound phenomena like alliteration and rhyming, but instead exploits low-level statistical cues. Possible reasons include the size of the training data, the relatively low frequency and difficulty of these sublexical phenomena as well as model biases. We show that more recent GPT-2 models also have problems learning sublexical phenomena such as rhyming from examples alone.
Learning authors representations from their textual productions is now widely used to solve multiple downstream tasks, such as classification, link prediction or user recommendation. Author embedding methods are often built on top of either Doc2Vec (
Mikolov et al. 2014) or the Transformer architecture (Devlin et al. 2019). Evaluating the quality of these embeddings and what they capture is a difficult task. Most articles use either classification accuracy or authorship attribution, which does not clearly measure the quality of the representation space, if it really captures what it has been built for. In this paper, we propose a novel evaluation framework of author embedding methods based on the writing style. It allows to quantify if the embedding space effectively captures a set of stylistic features, chosen to be the best proxy of an author writing style. This approach gives less importance to the topics conveyed by the documents. It turns out that recent models are mostly driven by the inner semantic of authors' production. They are outperformed by simple baselines, based on state-of-the-art pretrained sentence embedding models, on several linguistic axes. These baselines can grasp complex linguistic phenomena and writing style more efficiently, paving the way for designing new style-driven author embedding models.
Style is an integral part of natural language. However, evaluation methods for style measures are rare, often task-specific and usually do not control for content. We propose the modular, fine-grained and content-controlled similarity-based STyle Eva
Luation framework (STEL) to test the performance of any model that can compare two sentences on style. We illustrate STEL with two general dimensions of style (formal/informal and simple/complex) as well as two specific characteristics of style (contrac'tion and numb3r substitution). We find that BERT-based methods outperform simple versions of commonly used style measures like 3-grams, punctuation frequency and LIWC-based approaches. We invite the addition of further tasks and task instances to STEL and hope to facilitate the improvement of style-sensitive measures.
Style transfer aims to rewrite a source text in a different target style while preserving its content. We propose a novel approach to this task that leverages generic resources, and without using any task-specific parallel (source--target) data outpe
rforms existing unsupervised approaches on the two most popular style transfer tasks: formality transfer and polarity swap. In practice, we adopt a multi-step procedure which builds on a generic pre-trained sequence-to-sequence model (BART). First, we strengthen the model's ability to rewrite by further pre-training BART on both an existing collection of generic paraphrases, as well as on synthetic pairs created using a general-purpose lexical resource. Second, through an iterative back-translation approach, we train two models, each in a transfer direction, so that they can provide each other with synthetically generated pairs, dynamically in the training process. Lastly, we let our best resulting model generate static synthetic pairs to be used in a supervised training regime. Besides methodology and state-of-the-art results, a core contribution of this work is a reflection on the nature of the two tasks we address, and how their differences are highlighted by their response to our approach.
While the field of style transfer (ST) has been growing rapidly, it has been hampered by a lack of standardized practices for automatic evaluation. In this paper, we evaluate leading automatic metrics on the oft-researched task of formality style tra
nsfer. Unlike previous evaluations, which focus solely on English, we expand our focus to Brazilian-Portuguese, French, and Italian, making this work the first multilingual evaluation of metrics in ST. We outline best practices for automatic evaluation in (formality) style transfer and identify several models that correlate well with human judgments and are robust across languages. We hope that this work will help accelerate development in ST, where human evaluation is often challenging to collect.
Current language models are usually trained using a self-supervised scheme, where the main focus is learning representations at the word or sentence level. However, there has been limited progress in generating useful discourse-level representations.
In this work, we propose to use ideas from predictive coding theory to augment BERT-style language models with a mechanism that allows them to learn suitable discourse-level representations. As a result, our proposed approach is able to predict future sentences using explicit top-down connections that operate at the intermediate layers of the network. By experimenting with benchmarks designed to evaluate discourse-related knowledge using pre-trained sentence representations, we demonstrate that our approach improves performance in 6 out of 11 tasks by excelling in discourse relationship detection.
In this paper, we present a new verification style reading comprehension dataset named VGaokao from Chinese Language tests of Gaokao. Different from existing efforts, the new dataset is originally designed for native speakers' evaluation, thus requir
ing more advanced language understanding skills. To address the challenges in VGaokao, we propose a novel Extract-Integrate-Compete approach, which iteratively selects complementary evidence with a novel query updating mechanism and adaptively distills supportive evidence, followed by a pairwise competition to push models to learn the subtle difference among similar text pieces. Experiments show that our methods outperform various baselines on VGaokao with retrieved complementary evidence, while having the merits of efficiency and explainability. Our dataset and code are released for further research.
The style transfer task (here style is used in a broad authorial'' sense with many aspects including register, sentence structure, and vocabulary choice) takes text input and rewrites it in a specified target style preserving the meaning, but alterin
g the style of the source text to match that of the target. Much of the existing research on this task depends on the use of parallel datasets. In this work we employ recent results in unsupervised cross-lingual language modeling (XLM) and machine translation to effect style transfer while treating the input data as unaligned. First, we show that adding content embeddings'' to the XLM which capture human-specified groupings of subject matter can improve performance over the baseline model. Evaluation of style transfer has often relied on metrics designed for machine translation which have received criticism of their suitability for this task. As a second contribution, we propose the use of a suite of classical stylometrics as a useful complement for evaluation. We select a few such measures and include these in the analysis of our results.
This paper reviews and summarizes human evaluation practices described in 97 style transfer papers with respect to three main evaluation aspects: style transfer, meaning preservation, and fluency. In principle, evaluations by human raters should be t
he most reliable. However, in style transfer papers, we find that protocols for human evaluations are often underspecified and not standardized, which hampers the reproducibility of research in this field and progress toward better human and automatic evaluation methods.
Learning a good latent representation is essential for text style transfer, which generates a new sentence by changing the attributes of a given sentence while preserving its content. Most previous works adopt disentangled latent representation learn
ing to realize style transfer. We propose a novel text style transfer algorithm with entangled latent representation, and introduce a style classifier that can regulate the latent structure and transfer style. Moreover, our algorithm for style transfer applies to both single-attribute and multi-attribute transfer. Extensive experimental results show that our method generally outperforms state-of-the-art approaches.
