Diachronic word embeddings have been widely used in detecting temporal changes. However, existing methods face the meaning conflation deficiency by representing a word as a single vector at each time period. To address this issue, this paper proposes a sense representation and tracking framework based on deep contextualized embeddings, aiming at answering not only what and when, but also how the word meaning changes. The experiments show that our framework is effective in representing fine-grained word senses, and it brings a significant improvement in word change detection task. Furthermore, we model the word change from an ecological viewpoint, and sketch two interesting sense behaviors in the process of language evolution, i.e. sense competition and sense cooperation.

Natural Language Processing has been perplexed for many years by the problem that multiple semantics are mixed inside a word, even with the help of context. To solve this problem, we propose a prism module to disentangle the semantic aspects of words and reduce noise at the input layer of a model. In the prism module, some words are selectively replaced with task-related semantic aspects, then these denoised word representations can be fed into downstream tasks to make them easier. Besides, we also introduce a structure to train this module jointly with the downstream model without additional data. This module can be easily integrated into the downstream model and significantly improve the performance of baselines on named entity recognition (NER) task. The ablation analysis demonstrates the rationality of the method. As a side effect, the proposed method also provides a way to visualize the contribution of each word.

Dropout is used to avoid overfitting by randomly dropping units from the neural networks during training. Inspired by dropout, this paper presents GI-Dropout, a novel dropout method integrating with global information to improve neural networks for text classification. Unlike the traditional dropout method in which the units are dropped randomly according to the same probability, we aim to use explicit instructions based on global information of the dataset to guide the training process. With GI-Dropout, the model is supposed to pay more attention to inapparent features or patterns. Experiments demonstrate the effectiveness of the dropout with global information on seven text classification tasks, including sentiment analysis and topic classification.

Analogical reasoning is effective in capturing linguistic regularities. This paper proposes an analogical reasoning task on Chinese. After delving into Chinese lexical knowledge, we sketch 68 implicit morphological relations and 28 explicit semantic relations. A big and balanced dataset CA8 is then built for this task, including 17813 questions. Furthermore, we systematically explore the influences of vector representations, context features, and corpora on analogical reasoning. With the experiments, CA8 is proved to be a reliable benchmark for evaluating Chinese word embeddings.

The existing word representation methods mostly limit their information source to word co-occurrence statistics. In this paper, we introduce ngrams into four representation methods: SGNS, GloVe, PPMI matrix, and its SVD factorization. Comprehensive experiments are conducted on word analogy and similarity tasks. The results show that improved word representations are learned from ngram co-occurrence statistics. We also demonstrate that the trained ngram representations are useful in many aspects such as finding antonyms and collocations. Besides, a novel approach of building co-occurrence matrix is proposed to alleviate the hardware burdens brought by ngrams.

Convolutional Neural Networks (CNNs) are widely used in NLP tasks. This paper presents a novel weight initialization method to improve the CNNs for text classification. Instead of randomly initializing the convolutional filters, we encode semantic features into them, which helps the model focus on learning useful features at the beginning of the training. Experiments demonstrate the effectiveness of the initialization technique on seven text classification tasks, including sentiment analysis and topic classification.