No abstract

Part-of-Speech (POS) tagging for Twitter has received considerable attention in recent years. Because most POS tagging methods are based on supervised models, they usually require a large amount of labeled data for training. However, the existing labeled datasets for Twitter are much smaller than those for newswire text. Hence, to help POS tagging for Twitter, most domain adaptation methods try to leverage newswire datasets by learning the shared features between the two domains. However, from a linguistic perspective, Twitter users not only tend to mimic the formal expressions of traditional media, like news, but they also appear to be developing linguistically informal styles. Therefore, POS tagging for the formal Twitter context can be learned together with the newswire dataset, while POS tagging for the informal Twitter context should be learned separately. To achieve this task, in this work, we propose a hypernetworkbased method to generate different parameters to separately model contexts with different expression styles. Experimental results on three different datasets show that our approach achieves better performance than state-of-theart methods in most cases.

Natural language inference aims to predict whether a premise sentence can infer another hypothesis sentence. Existing methods typically have framed the reasoning problem as a semantic matching task. The both sentences are encoded and interacted symmetrically and in parallel. However, in the process of reasoning, the role of the two sentences is obviously different, and the sentence pairs for NLI are asymmetrical corpora. In this paper, we propose an asynchronous deep interaction network (ADIN) to complete the task. ADIN is a neural network structure stacked with multiple inference sub-layers, and each sub-layer consists of two local inference modules in an asymmetrical manner. Different from previous methods, this model deconstructs the reasoning process and implements the asynchronous and multi-step reasoning. Experiment results show that ADIN achieves competitive performance and outperforms strong baselines on three popular benchmarks: SNLI, MultiNLI, and SciTail.

No abstract

Familiar strangers, pairs of individuals who encounter repeatedly but never know each other, have been discovered for four decades yet lack an effective method to identify. Here we propose a novel method called familiar stranger classifier (FSC) to identify familiar strangers from three empirical datasets, and classify human relationships into four types, i.e., familiar stranger (FS), in-role (IR), friend (F) and stranger (S). The analyses of the human encounter networks show that the average number of FS one may encounter is finite but larger than the Dunbar Number, and their encounters are structurally more stable and denser than those of S, indicating the encounters of FS are not limited by the social capacity, and more robust than the random scenario. Moreover, the temporal statistics of encounters between FS over the whole time span show strong periodicity, which are diverse from the bursts of encounters within one day, suggesting the significance of longitudinal patterns of human encounters. The proposed method to identify FS in this paper provides a valid framework to understand human encounter patterns and analyse complex human social behaviors.