We present a large-scale relation extraction (RE) system which learns grammar-based RE rules from the Web by utilizing large numbers of relation instances as seed. Our goal is to obtain rule sets large enough to cover the actual range of linguistic variation, thus tackling the long-tail problem of real-world applications. A variant of distant supervision learns several relations in parallel, en...

We present a novel neural machine translation (NMT) architecture associating visual and textual features for translation tasks with multiple modalities. Transformed global and regional visual features are concatenated with text to form attendable sequences which are dissipated over parallel long short-term memory (LSTM) threads to assist the encoder generating a representation for attention-bas...

Over the years, the field of Language Resources and Technology (LRT) has developed a tremendous amount of resources and tools. However, there is no ready-to-use map that researchers could use to gain a good overview and steadfast orientation when searching for, say corpora or software tools to support their studies. It is rather the case that information is scattered across projector organisati...

Currently most of state-of-the-art methods for Chinese word segmentation are based on supervised learning, whose features aremostly extracted from a local context. Thesemethods cannot utilize the long distance information which is also crucial for word segmentation. In this paper, we propose a novel neural network model for Chinese word segmentation, which adopts the long short-term memory (LST...

In recent years, the increasing propagation of hate speech on social media and the urgent need for effective countermeasures have drawn significant investment from governments, companies, and empirical research. Despite a large number of emerging, scientific studies to address the problem, the performance of existing automated methods at identifying specific types of hate speech as opposed to i...

As long-form spoken documents become more ubiquitous in everyday life, so does the need for automatic discourse segmentation in spoken language processing tasks. Although previous work has focused on broad topic segmentation, detection of finer-grained discourse units, such as paragraphs, is highly desirable for presenting and analyzing spoken content. To better understand how different aspects...

This paper tried to amplify a sense of emotion toward drama. Using Long Short-Term Memory Recurrent Neural Network to model and predict dynamic emotion(Arousal and Valence) recognition. After building model, we transplant whole framework and take results from it on visualizing. We have two demo version: RGB version and Vignette version. RGB version is to modulate the RGB value of frame in video...

In this paper, we discuss the encoding of hieroglyphic text and argue that the set of requirements for an encoding scheme depend on the intended application. Our main claim is that if this application is the development of text corpora with long lifespans and diversity of use, then encoding schemes within the tradition of the Manuel de Codage are unsuitable.

While widely used in industry, recurrent neural networks (RNNs) are known to have deficiencies dealing with long sequences (e.g. slow inference, vanishing gradients etc.). Recent research has attempted accelerate RNN models by developing mechanisms skip irrelevant words input. Due the lack of labelled data, it remains as a challenge decide which skip, especially for low-resource classification ...