Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

We propose a hierarchical attention network for document classification. Our model has two distinctive characteristics: (i) it has a hierarchical structure that mirrors the hierarchical structure of documents; (ii) it has two levels of attention mechanisms applied at the wordand sentence-level, enabling it to attend differentially to more and less important content when constructing the document representation. Experiments conducted on six large scale text classification tasks demonstrate that the proposed architecture outperform previous methods by a substantial margin. Visualization of the attention layers illustrates that the model selects qualitatively informative words and sentences.

/pdf/hierarchical-attention-networks-for-document-classification-2f4ul5pyx3.pdf

Hierarchical Attention Networks for Document Classification

Deep learning methods employ multiple processing layers to learn hierarchical representations of data, and have produced state-of-the-art results in many domains. Recently, a variety of model designs and methods have blossomed in the context of natural language processing (NLP). In this paper, we review significant deep learning related models and methods that have been employed for numerous NLP tasks and provide a walk-through of their evolution. We also summarize, compare and contrast the various models and put forward a detailed understanding of the past, present and future of deep learning in NLP.

Recent Trends in Deep Learning Based Natural Language Processing [Review Article]

/pdf/neural-networks-and-deep-learning-3ccs3ain8p.pdf

Neural Networks and Deep Learning

Knowledge graph (KG) embedding is to embed components of a KG including entities and relations into continuous vector spaces, so as to simplify the manipulation while preserving the inherent structure of the KG. It can benefit a variety of downstream tasks such as KG completion and relation extraction, and hence has quickly gained massive attention. In this article, we provide a systematic review of existing techniques, including not only the state-of-the-arts but also those with latest trends. Particularly, we make the review based on the type of information used in the embedding task. Techniques that conduct embedding using only facts observed in the KG are first introduced. We describe the overall framework, specific model design, typical training procedures, as well as pros and cons of such techniques. After that, we discuss techniques that further incorporate additional information besides facts. We focus specifically on the use of entity types, relation paths, textual descriptions, and logical rules. Finally, we briefly introduce how KG embedding can be applied to and benefit a wide variety of downstream tasks such as KG completion, relation extraction, question answering, and so forth.

Knowledge Graph Embedding: A Survey of Approaches and Applications

Text classification is a foundational task in many NLP applications. Traditional text classifiers often rely on many human-designed features, such as dictionaries, knowledge bases and special tree kernels. In contrast to traditional methods, we introduce a recurrent convolutional neural network for text classification without human-designed features. In our model, we apply a recurrent structure to capture contextual information as far as possible when learning word representations, which may introduce considerably less noise compared to traditional window-based neural networks. We also employ a max-pooling layer that automatically judges which words play key roles in text classification to capture the key components in texts. We conduct experiments on four commonly used datasets. The experimental results show that the proposed method outperforms the state-of-the-art methods on several datasets, particularly on document-level datasets.

/pdf/recurrent-convolutional-neural-networks-for-text-1vxjlhvkh6.pdf

Recurrent convolutional neural networks for text classification

Knowledge graphs are useful resources for numerous AI applications, but they are far from completeness. Previous work such as TransE, TransH and TransR/CTransR regard a relation as translation from head entity to tail entity and the CTransR achieves state-of-the-art performance. In this paper, we propose a more fine-grained model named TransD, which is an improvement of TransR/CTransR. In TransD, we use two vectors to represent a named symbol object (entity and relation). The first one represents the meaning of a(n) entity (relation), the other one is used to construct mapping matrix dynamically. Compared with TransR/CTransR, TransD not only considers the diversity of relations, but also entities. TransD has less parameters and has no matrix-vector multiplication operations, which makes it can be applied on large scale graphs. In Experiments, we evaluate our model on two typical tasks including triplets classification and link prediction. Evaluation results show that our approach outperforms state-of-the-art methods.

/pdf/knowledge-graph-embedding-via-dynamic-mapping-matrix-47hy37ecjx.pdf

Knowledge Graph Embedding via Dynamic Mapping Matrix

Traditional approaches to the task of ACE event extraction primarily rely on elaborately designed features and complicated natural language processing (NLP) tools. These traditional approaches lack generalization, take a large amount of human effort and are prone to error propagation and data sparsity problems. This paper proposes a novel event-extraction method, which aims to automatically extract lexical-level and sentence-level features without using complicated NLP tools. We introduce a word-representation model to capture meaningful semantic regularities for words and adopt a framework based on a convolutional neural network (CNN) to capture sentence-level clues. However, CNN can only capture the most important information in a sentence and may miss valuable facts when considering multiple-event sentences. We propose a dynamic multi-pooling convolutional neural network (DMCNN), which uses a dynamic multi-pooling layer according to event triggers and arguments, to reserve more crucial information. The experimental results show that our approach significantly outperforms other state-of-the-art methods.

/pdf/event-extraction-via-dynamic-multi-pooling-convolutional-3a6d5ebdhk.pdf

Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks

We analyze three critical components of word embedding training: the model, the corpus, and the training parameters. We systematize existing neural-network-based word embedding algorithms and compare them using the same corpus. We evaluate each word embedding in three ways: analyzing its semantic properties, using it as a feature for supervised tasks and using it to initialize neural networks. We also provide several simple guidelines for training word embeddings. First, we discover that corpus domain is more important than corpus size. We recommend choosing a corpus in a suitable domain for the desired task, after that, using a larger corpus yields better results. Second, we find that faster models provide sufficient performance in most cases, and more complex models can be used if the training corpus is sufficiently large. Third, the early stopping metric for iterating should rely on the development set of the desired task rather than the validation loss of training embedding.

How to Generate a Good Word Embedding

This paper proposes a novel approach to extract opinion targets based on word-based translation model (WTM). At first, we apply WTM in a monolingual scenario to mine the associations between opinion targets and opinion words. Then, a graph-based algorithm is exploited to extract opinion targets, where candidate opinion relevance estimated from the mined associations, is incorporated with candidate importance to generate a global measure. By using WTM, our method can capture opinion relations more precisely, especially for long-span relations. In particular, compared with previous syntax-based methods, our method can effectively avoid noises from parsing errors when dealing with informal texts in large Web corpora. By using graph-based algorithm, opinion targets are extracted in a global process, which can effectively alleviate the problem of error propagation in traditional bootstrap-based methods, such as Double Propagation. The experimental results on three real world datasets in different sizes and languages show that our approach is more effective and robust than state-of-art methods.

/pdf/opinion-target-extraction-using-word-based-translation-model-1yscjto9v8.pdf

Liheng Xu

Papers

Recurrent convolutional neural networks for text classification

Knowledge Graph Embedding via Dynamic Mapping Matrix

Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks

How to Generate a Good Word Embedding

Opinion Target Extraction Using Word-Based Translation Model