Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that involve not just recognizing, but reasoning about our visual world. However, models used to tackle the rich content in images for cognitive tasks are still being trained using the same datasets designed for perceptual tasks. To achieve success at cognitive tasks, models need to understand the interactions and relationships between objects in an image. When asked "What vehicle is the person riding?", computers will need to identify the objects in an image as well as the relationships riding(man, carriage) and pulling(horse, carriage) to answer correctly that "the person is riding a horse-drawn carriage." In this paper, we present the Visual Genome dataset to enable the modeling of such relationships. We collect dense annotations of objects, attributes, and relationships within each image to learn these models. Specifically, our dataset contains over 108K images where each image has an average of $$35$$35 objects, $$26$$26 attributes, and $$21$$21 pairwise relationships between objects. We canonicalize the objects, attributes, relationships, and noun phrases in region descriptions and questions answer pairs to WordNet synsets. Together, these annotations represent the densest and largest dataset of image descriptions, objects, attributes, relationships, and question answer pairs.

/pdf/visual-genome-connecting-language-and-vision-using-15ih2ylk6r.pdf

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

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]

Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that involve not just recognizing, but reasoning about our visual world. However, models used to tackle the rich content in images for cognitive tasks are still being trained using the same datasets designed for perceptual tasks. To achieve success at cognitive tasks, models need to understand the interactions and relationships between objects in an image. When asked "What vehicle is the person riding?", computers will need to identify the objects in an image as well as the relationships riding(man, carriage) and pulling(horse, carriage) in order to answer correctly that "the person is riding a horse-drawn carriage". 
In this paper, we present the Visual Genome dataset to enable the modeling of such relationships. We collect dense annotations of objects, attributes, and relationships within each image to learn these models. Specifically, our dataset contains over 100K images where each image has an average of 21 objects, 18 attributes, and 18 pairwise relationships between objects. We canonicalize the objects, attributes, relationships, and noun phrases in region descriptions and questions answer pairs to WordNet synsets. Together, these annotations represent the densest and largest dataset of image descriptions, objects, attributes, relationships, and question answers.

Relation classification is an important semantic processing task in the field of natural language processing (NLP). State-ofthe-art systems still rely on lexical resources such as WordNet or NLP systems like dependency parser and named entity recognizers (NER) to get high-level features. Another challenge is that important information can appear at any position in the sentence. To tackle these problems, we propose Attention-Based Bidirectional Long Short-Term Memory Networks(AttBLSTM) to capture the most important semantic information in a sentence. The experimental results on the SemEval-2010 relation classification task show that our method outperforms most of the existing methods, with only word vectors.

Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification

Neural language representation models such as BERT pre-trained on large-scale corpora can well capture rich semantic patterns from plain text, and be fine-tuned to consistently improve the performance of various NLP tasks. However, the existing pre-trained language models rarely consider incorporating knowledge graphs (KGs), which can provide rich structured knowledge facts for better language understanding. We argue that informative entities in KGs can enhance language representation with external knowledge. In this paper, we utilize both large-scale textual corpora and KGs to train an enhanced language representation model (ERNIE), which can take full advantage of lexical, syntactic, and knowledge information simultaneously. The experimental results have demonstrated that ERNIE achieves significant improvements on various knowledge-driven tasks, and meanwhile is comparable with the state-of-the-art model BERT on other common NLP tasks. The code and datasets will be available in the future.

ERNIE: Enhanced Language Representation with Informative Entities

The state-of-the-art methods used for relation classification are primarily based on statistical machine learning, and their performance strongly depends on the quality of the extracted features. The extracted features are often derived from the output of pre-existing natural language processing (NLP) systems, which leads to the propagation of the errors in the existing tools and hinders the performance of these systems. In this paper, we exploit a convolutional deep neural network (DNN) to extract lexical and sentence level features. Our method takes all of the word tokens as input without complicated pre-processing. First, the word tokens are transformed to vectors by looking up word embeddings 1 . Then, lexical level features are extracted according to the given nouns. Meanwhile, sentence level features are learned using a convolutional approach. These two level features are concatenated to form the final extracted feature vector. Finally, the features are fed into a softmax classifier to predict the relationship between two marked nouns. The experimental results demonstrate that our approach significantly outperforms the state-of-the-art methods.

/pdf/relation-classification-via-convolutional-deep-neural-1v77s8v4mm.pdf

Relation Classification via Convolutional Deep Neural Network

Two problems arise when using distant supervision for relation extraction. First, in this method, an already existing knowledge base is heuristically aligned to texts, and the alignment results are treated as labeled data. However, the heuristic alignment can fail, resulting in wrong label problem. In addition, in previous approaches, statistical models have typically been applied to ad hoc features. The noise that originates from the feature extraction process can cause poor performance. In this paper, we propose a novel model dubbed the Piecewise Convolutional Neural Networks (PCNNs) with multi-instance learning to address these two problems. To solve the first problem, distant supervised relation extraction is treated as a multi-instance problem in which the uncertainty of instance labels is taken into account. To address the latter problem, we avoid feature engineering and instead adopt convolutional architecture with piecewise max pooling to automatically learn relevant features. Experiments show that our method is effective and outperforms several competitive baseline methods.

/pdf/distant-supervision-for-relation-extraction-via-piecewise-2zx0d5jsk9.pdf

Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks

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

The relational facts in sentences are often complicated. Different relational triplets may have overlaps in a sentence. We divided the sentences into three types according to triplet overlap degree, including Normal, EntityPairOverlap and SingleEntiyOverlap. Existing methods mainly focus on Normal class and fail to extract relational triplets precisely. In this paper, we propose an end-to-end model based on sequence-to-sequence learning with copy mechanism, which can jointly extract relational facts from sentences of any of these classes. We adopt two different strategies in decoding process: employing only one united decoder or applying multiple separated decoders. We test our models in two public datasets and our model outperform the baseline method significantly.

/pdf/extracting-relational-facts-by-an-end-to-end-neural-model-2ycqfaql5q.pdf

Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism

Recently, many researchers have concentrated on using neural networks to learn features for Distant Supervised Relation Extraction (DSRE). These approaches generally use a softmax classifier with cross-entropy loss, which inevitably brings the noise of artificial class NA into classification process. To address the shortcoming, the classifier with ranking loss is employed to DSRE. Uniformly randomly selecting a relation or heuristically selecting the highest score among all incorrect relations are two common methods for generating a negative class in the ranking loss function. However, the majority of the generated negative class can be easily discriminated from positive class and will contribute little towards the training. Inspired by Generative Adversarial Networks (GANs), we use a neural network as the negative class generator to assist the training of our desired model, which acts as the discriminator in GANs. Through the alternating optimization of generator and discriminator, the generator is learning to produce more and more discriminable negative classes and the discriminator has to become better as well. This framework is independent of the concrete form of generator and discriminator. In this paper, we use a two layers fully-connected neural network as the generator and the Piecewise Convolutional Neural Networks (PCNNs) as the discriminator. Experiment results show that our proposed GAN-based method is effective and performs better than state-of-the-art methods.

Daojian Zeng

Papers

Relation Classification via Convolutional Deep Neural Network

Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks

Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks

Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism

Adversarial learning for distant supervised relation extraction