Neural network based methods have obtained great progress on a variety of natural language processing tasks. However, it is still a challenge task to model long texts, such as sentences and documents. In this paper, we propose a multi-timescale long short-term memory (MT-LSTM) neural network to model long texts. MT-LSTM partitions the hidden states of the standard LSTM into several groups. Each group is activated at different time periods. Thus, MT-LSTM can model very long documents as well as short sentences. Experiments on four benchmark datasets show that our model outperforms the other neural models in text classification task.
Recently, neural network based sentence modeling methods have achieved great progress. Among these methods, the recursive neural networks (RecNNs) can effectively model the combination of the words in sentence. However, RecNNs need a given external topological structure, like syntactic tree. In this paper, we propose a gated recursive neural network (GRNN) to model sentences, which employs a full binary tree (FBT) structure to control the combinations in recursive structure. By introducing two kinds of gates, our model can better model the complicated combinations of features. Experiments on three text classification datasets show the effectiveness of our model.
In this paper, we give an overview for the shared task at the 4th CCF Conference on Natural Language Processing & Chinese Computing (NLPCC 2015): Chinese word segmentation and part-of-speech (POS) tagging for micro-blog texts. Different with the popular used newswire datasets, the dataset of this shared task consists of the relatively informal micro-texts. The shared task has two sub-tasks: (1) individual Chinese word segmentation and (2) joint Chinese word segmentation and POS Tagging. Each subtask has three tracks to distinguish the systems with different resources. We first introduce the dataset and task, then we characterize the different approaches of the participating systems, report the test results, and provide a overview analysis of these results. An online system is available for open registration and evaluation at http://nlp.fudan.edu.cn/nlpcc2015.
Via a 90-min classroom experiment, this study examined the effects of interactive reading on EFL students’ content and vocabulary learning. Specifically, two intact Chinese college EFL classes with the same level of English proficiency participated in this study. One was taught with a “read plus intra/inter-group discussion” (Read-Discuss) approach and the other was instructed with a traditional approach involving no student-student interaction. After the experiment, the students took two immediate posttests (one on content and one on vocabulary) and, three weeks later, retook the same tests (delayed posttests). The results of statistical analyses indicate that whereas in the immediate posttests both classes attained a similar level of learning on both the content and vocabulary tests, in the delayed posttests, the Read-Discuss class significantly outperformed the traditional class, demonstrating that the Read-Discuss approach produced significantly better consolidated learning/retention in both content and vocabulary. Pedagogical/research implications of the results are also discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.