Neural Machine Translation (NMT) brings promising improvements in translation quality, but until recently, these models rely on large-scale parallel corpora. As such corpora only exist on a handful of language pairs, the translation performance is far from the desired effect in the majority of low-resource languages. Thus, developing low-resource language translation techniques is crucial and it has become a popular research field in neural machine translation. In this article, we make an overall review of existing deep learning techniques in low-resource NMT. We first show the research status as well as some widely used low-resource datasets. Then, we categorize the existing methods and show some representative works detailedly. Finally, we summarize the common characters among them and outline the future directions in this field.

Emotion cause extraction (ECE) task that aims at extracting potential trigger events of certain emotions has attracted extensive attention recently. However, current work neglects the implicit emotion expressed without any explicit emotional keywords, which appears more frequently in application scenarios. The lack of explicit emotion information makes it extremely hard to extract emotion causes only with the local context. Moreover, an entire event is usually across multiple clauses, while existing work merely extracts cause events at clause level and cannot effectively capture complete cause event information. To address these issues, the events are first redefined at the tuple level and a span‐based tuple‐level algorithm is proposed to extract events from different clauses. Based on it, a corpus for implicit emotion cause extraction that tries to extract causes of implicit emotions is constructed. The authors propose a knowledge‐enriched joint‐learning model of implicit emotion recognition and implicit emotion cause extraction tasks (KJ‐IECE), which leverages commonsense knowledge from ConceptNet and NRC_VAD to better capture connections between emotion and corresponding cause events. Experiments on both implicit and explicit emotion cause extraction datasets demonstrate the effectiveness of the proposed model.

With the development of social network, group emotion analysis on social media such as Facebook, Twitter and Weibo becomes a new trend in recent years. Many different methods have been proposed for group emotion analysis, including traditional methods like SVM and NB and deep learning methods like RNN and CNN. This paper proposes a CNN model with multi-features. We first analyze the characteristic of weibos to collect features including basic features, user-based features and content-based features. We introduce these features to our CNN model to analyze emotions for Weibo events, which has been proved in experiment that it is effective to get the accurate sentiment of weibos. We crawl 5,319,687 weibos about 724 events from Sina Weibo and apply several feature matrices to classify them to 4 types. We use the new model to analyze 4 kinds of events to get the group emotion. The results suggest that the classification we suggested can capture the emotions within different event group.