Driven by the increasingly larger deep learning models, neural language generation (NLG) has enjoyed unprecedentedly improvement and is now able to generate a diversity of human-like texts on demand, granting itself the capability of serving as a human writing assistant. Text attribute transfer is one of the most important NLG tasks, which aims to control certain attributes that people may expect the texts to possess, such as sentiment, tense, emotion, political position, etc. It has a long history in Natural Language Processing but recently gains much more attention thanks to the promising performance brought by deep learning models. In this article, we present a systematic survey on these works for neural text attribute transfer. We collect all related academic works since the first appearance in 2017. We then select, summarize, discuss, and analyze around 65 representative works in a comprehensive way. Overall, we have covered the task formulation, existing datasets and metrics for model development and evaluation, and all methods developed over the last several years. We reveal that existing methods are indeed based on a combination of several loss functions with each of which serving a certain goal. Such a unique perspective we provide could shed light on the design of new methods. We conclude our survey with a discussion on open issues that need to be resolved for better future development.
Aspect-based sentiment analysis (ABSA) aims to predict the sentiment towards a specific aspect in the text. However, existing ABSA test sets cannot be used to probe whether a model can distinguish the sentiment of the target aspect from the non-target aspects. To solve this problem, we develop a simple but effective approach to enrich ABSA test sets. Specifically, we generate new examples to disentangle the confounding sentiments of the non-target aspects from the target aspect's sentiment. Based on the SemEval 2014 dataset, we construct the Aspect Robustness Test Set (ARTS) as a comprehensive probe of the aspect robustness of ABSA models. Over 92% data of ARTS show high fluency and desired sentiment on all aspects by human evaluation. Using ARTS, we analyze the robustness of nine ABSA models, and observe, surprisingly, that their accuracy drops by up to 69.73%. We explore several ways to improve aspect robustness, and find that adversarial training can improve models' performance on ARTS by up to 32.85%. Our code and new test set are available at https://github.com/zhijing-jin/ARTS_TestSet
Two important tasks at the intersection of knowledge graphs and natural language processing are graph-to-text (G2T) and text-to-graph (T2G) conversion. Due to the difficulty and high cost of data collection, the supervised data available in the two fields are usually on the magnitude of tens of thousands, for example, 18K in the WebNLG dataset, which is far fewer than the millions of data for other tasks such as machine translation. Consequently, deep learning models in these two fields suffer largely from scarce training data. This work presents the first attempt to unsupervised learning of T2G and G2T via cycle training. We present CycleGT, an unsupervised training framework that can bootstrap from fully non-parallel graph and text datasets, iteratively back translate between the two forms, and use a novel pretraining strategy. Experiments on the benchmark WebNLG dataset show that, impressively, our unsupervised model trained on the same amount of data can achieve performance on par with the supervised models. This validates our framework as an effective approach to overcome the data scarcity problem in the fields of G2T and T2G.
In natural language, often multiple entities appear in the same text. However, most previous works in Relation Extraction (RE) limit the scope to identifying the relation between two entities at a time. Such an approach induces a quadratic computation time, and also overlooks the interdependency between multiple relations, namely the relation of relations (RoR). Due to the significance of RoR in existing datasets, we propose a new paradigm of RE that considers as a whole the predictions of all relations in the same context. Accordingly, we develop a data-driven approach that does not require hand-crafted rules but learns by itself the RoR, using Graph Neural Networks and a relation matrix transformer. Experiments show that our model outperforms the state-of-the-art approaches by +1.12\% on the ACE05 dataset and +2.55\% on SemEval 2018 Task 7.2, which is a substantial improvement on the two competitive benchmarks.
Current summarization systems only produce plain, factual headlines, but do not meet the practical needs of creating memorable titles to increase exposure. We propose a new task, Stylistic Headline Generation (SHG), to enrich the headlines with three style options (humor, romance and clickbait), in order to attract more readers. With no style-specific article-headline pair (only a standard headline summarization dataset and mono-style corpora), our method TitleStylist generates style-specific headlines by combining the summarization and reconstruction tasks into a multitasking framework. We also introduced a novel parameter sharing scheme to further disentangle the style from the text. Through both automatic and human evaluation, we demonstrate that TitleStylist can generate relevant, fluent headlines with three target styles: humor, romance, and clickbait. The attraction score of our model generated headlines surpasses that of the state-of-the-art summarization model by 9.68%, and even outperforms human-written references.
State-of-the-art neural machine translation (NMT) systems are data-hungry and perform poorly on domains with little supervised data. As data collection is expensive and infeasible in many cases, unsupervised domain adaptation methods are needed. We apply an Iterative Back Translation (IBT) training scheme on in-domain monolingual data, which repeatedly uses a Transformer-based NMT model to create in-domain pseudo-parallel sentence pairs in one translation direction on the fly and then use them to train the model in the other direction. Evaluated on three domains of German-to-English translation task with no supervised data, this simple technique alone (without any out-of-domain parallel data) can already surpass all previous domain adaptation methods---up to +9.48 BLEU over the strongest previous method, and up to +27.77 BLEU over the unadapted baseline. Moreover, given available supervised out-of-domain data on German-to-English and Romanian-to-English language pairs, we can further enhance the performance and obtain up to +19.31 BLEU improvement over the strongest baseline, and +47.69 BLEU increment against the unadapted model.