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 ST automatic metrics on the oft-researched task of formality style transfer. 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.
The task of news article image captioning aims to generate descriptive and informative captions for news article images. Unlike conventional image captions that simply describe the content of the image in general terms, news image captions follow journalistic guidelines and rely heavily on named entities to describe the image content, often drawing context from the whole article they are associated with. In this work, we propose a new approach to this task, motivated by caption guidelines that journalists follow. Our approach, Journalistic Guidelines Aware News Image Captioning (JoGANIC), leverages the structure of captions to improve the generation quality and guide our representation design. Experimental results, including detailed ablation studies, on two large-scale publicly available datasets show that JoGANIC substantially outperforms state-of-the-art methods both on caption generation and named entity related metrics.
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 the 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.
Recent works show that the graph structure of sentences, generated from dependency parsers, has potential for improving event detection. However, they often only leverage the edges (dependencies) between words, and discard the dependency labels (e.g., nominal-subject), treating the underlying graph edges as homogeneous. In this work, we propose a novel framework for incorporating both dependencies and their labels using a recently proposed technique called Graph Transformer Networks (GTN). We integrate GTNs to leverage dependency relations on two existing homogeneous-graph-based models, and demonstrate an improvement in the F1 score on the ACE dataset.
We take the first step towards multilingual style transfer by creating and releasing XFORMAL, a benchmark of multiple formal reformulations of informal text in Brazilian Portuguese, French, and Italian. Results on XFORMAL suggest that state-of-the-art style transfer approaches perform close to simple baselines, indicating that style transfer is even more challenging when moving multilingual.
News articles, image captions, product reviews and many other texts mention people and organizations whose name recognition could vary for different audiences. In such cases, background information about the named entities could be provided in the form of an appositive noun phrase, either written by a human or generated automatically. We expand on the previous work in appositive generation with a new, more realistic, end-to-end definition of the task, instantiated by a dataset that spans four languages (English, Spanish, German and Polish), two entity types (person and organization) and two domains (Wikipedia and News). We carry out an extensive analysis of the data and the task, pointing to the various modeling challenges it poses. The results we obtain with standard language generation methods show that the task is indeed non-trivial, and leaves plenty of room for improvement.
Computational models of argument quality (AQ) have focused primarily on assessing the overall quality or just one specific characteristic of an argument, such as its convincingness or its clarity. However, previous work has claimed that assessment based on theoretical dimensions of argumentation could benefit writers, but developing such models has been limited by the lack of annotated data. In this work, we describe GAQCorpus, the first large, domain-diverse annotated corpus of theory-based AQ. We discuss how we designed the annotation task to reliably collect a large number of judgments with crowdsourcing, formulating theory-based guidelines that helped make subjective judgments of AQ more objective. We demonstrate how to identify arguments and adapt the annotation task for three diverse domains. Our work will inform research on theory-based argumentation annotation and enable the creation of more diverse corpora to support computational AQ assessment.
Social media has quickly grown into an essential tool for people to communicate and express their needs during crisis events. Prior work in analyzing social media data for crisis management has focused primarily on automatically identifying actionable (or, informative) crisis-related messages. In this work, we show that recent advances in Deep Learning and Natural Language Processing outperform prior approaches for the task of classifying informativeness and encourage the field to adopt them for their research or even deployment. We also extend these methods to two sub-tasks of informativeness and find that the Deep Learning methods are effective here as well.
Grammar error correction (GEC) systems have become ubiquitous in a variety of software applications, and have started to approach human-level performance for some datasets. However, very little is known about how to efficiently personalize these systems to the user's characteristics, such as their proficiency level and first language, or to emerging domains of text. We present the first results on adapting a general-purpose neural GEC system to both the proficiency level and the first language of a writer, using only a few thousand annotated sentences. Our study is the broadest of its kind, covering five proficiency levels and twelve different languages, and comparing three different adaptation scenarios: adapting to the proficiency level only, to the first language only, or to both aspects simultaneously. We show that tailoring to both scenarios achieves the largest performance improvement (3.6 F0.5) relative to a strong baseline.