weiwang

Text similarity modeling plays an important role in a variety of applications of Natural Language Processing (NLP), such as information retrieval, text clustering, and plagiarism detection. Moreover, it can work as an automatic evaluation metric in natural language generation, like machine translation and image captioning, so that expensive and time-consuming human labeling can be saved.

Word Mover’s Distance (WMD) [1] is an efficient model to measure the semantic distance of two texts. In WMD, word embedding which learns semantically meaningful representations for words are incorporated in earth mover’s distance. The distance between two texts A and B is the minimum cumulative distance that all words from the text A needs to travel to match exactly the text B.

We try to incorporate syntactic parsing, which brings meaningful structure information, into WMD in our work. There are mainly two parts that can control the flow in WMD. One is the distance matrix and the flow of each word. Firstly, to compute the distance matrix, the original WMD only compares an individual pair of word embeddings to measure the distance between words and doesn’t consider other information in the sentence. To measure the distance between words better, we first form sub-tree structures from the dependency parsing tree. Instead of only comparing the similarity of the word embeddings, we also compare the sub-tree similarity that contains the words. Secondly, A word’s flow can be regarded as the word’s importance. If giving more flow to important words, the most flow will transport between important words. So, the total transportation cost is mainly decided by the similarity of important words. We currently utilize the word’s dependency relation in the parsing tree to assign importance weights for words. In the future, we [...]

2021 has been a fruitful year for MCL. Some members graduated with impressive research work and began a new chapter of life. Some new students joined the MCL family and explored the joy of research. MCL members have made great efforts on their research and published quality research papers on top journals and conferences. We appreciate all efforts to all possibilities! Wish all MCL members a merry Christmas!

Image credits:

Image 1: https://www.freepik.com/free-vector/realistic-christmas-banner-with-branches-red-background_11210304.htm#query=merry%20christmas&position=42&from_view=keyword

Image 2: https://www.backyardcamp.ca/activities/gingerbread-christmas-cookie-trees

Entity type is a very important piece of information in Knowledge Graphs. Researchers have leveraged entity type information to get better results in many Knowledge Graph related tasks such as link prediction. Besides, entity type is also important for Information Extraction tasks including entity linking and relation extraction. However, Knowledge Graph entity type information is often incomplete and noisy. Therefore, there is a need to develop effective algorithms for predicting missing types for entities.

Knowledge Graph (KG) Embeddings in complex vector space have demonstrated superior performance in relation prediction and triple classification. Representing entities and relations in complex space has several advantages than traditional models such as better expressive power, and better capabilities of modeling one-to-many and asymmetric relations. We leverage these characteristics of complex KG Embeddings and formulate the type prediction problem as a complex space regression problem. Experimental results confirm our hypothesis that the expressiveness of embedding models correlates with the performance on type prediction. Our newly proposed method achieves state-of-the-art results in type prediction for many benchmarking datasets.

[1] Sun, Zhiqing, et al. “Rotate: Knowledge graph embedding by relational rotation in complex space.” arXiv preprint arXiv:1902.10197 (2019).

[2] Zhao, Yu, et al. “Connecting embeddings for knowledge graph entity typing.” arXiv preprint arXiv:2007.10873 (2020).

— by Xiou Ge

Misinformation on the Internet and social media, ranging from fake news to fake multimedia such as images and videos, is a significant threat to our society. Effective misinformation detection has become a research focus, driven by commercial and government funding. With the fast-growing deep learning techniques, real-looking fake images can be easily generated using generative adversarial networks (GANs). The problem of fake satellite images detection was recently introduced. Fake satellite images could be generated with the intention of hiding important infrastructure and/or creating fake buildings to deceive others. Although it may be feasible to check whether these images are real or fake using another satellite, the cost is high. Furthermore, the general public and media do not have the proper resource to verify the authenticity of fake satellite images. Consequently, fake satellite images pose serious challenges to our society, as recognized by government organizations concerned about the political and military implications of such technology. Handcrafted features were used for fake satellite image detection, and its best detection performance measured by the F-1 score is 87%. 

A new method, called PSL-DefakeHop, is proposed to detect fake satellite images based on the parallel subspace learning (PSL) framework in this work. The DefakeHop method was developed previously for the detection of Deepfake generated faces under the successive subspace learning (SSL) framework. PSL is proposed to extract features from responses of multiple single-stage filter banks (or called PixelHops), which operate in parallel, and it improves SSL that extracts features from multi-stage cascaded filter banks. PSL has two advantages. First, PSL preserves discriminant features often lie in high-frequency channels, which are however ignored by SSL. Second, decisions from multiple filter banks can be ensembled to further improve detection accuracy. To [...]

Word embeddings, also known as distributed word representations, learn real-valued vectors that encode words’ meaning. They have been widely used in many Natural Language Processing (NLP) tasks, such as text classification, part-of-speech tagging, parsing, and machine translation. Text classification is a task where the input texts have to be classified into different categories based on their content. Word embedding methods have been tailored to text classification for performance improvement.

In this research, two task-specific dependency-based word embedding methods are proposed for Text classification. In contrast with universal word embedding methods that work for generic tasks, we design task-specific word embedding methods to offer better performance in a specific task. Our methods follow the PPMI matrix factorization framework and derive word contexts from the dependency parse tree. As compared linear contexts, dependency-based contexts can find long-range contexts and exclude less informative contexts. One example is shown in Fig. 2, where the target word is ‘found’. Guided by the dependency par-sing tree, its closely related words (e.g. ‘he’, ‘dog’) can be easily identified. In contrast, less related words (e.g. ‘skinny’, ‘fragile’) are gathered by linear contexts.

Firstly, to construct robust and informative contexts, we use dependency relation which represents the word’s syntactic function to locate the keywords in the sentence and treat the keywords and the neighbor words in the dependency parse tree as contexts.

To further increase the text classification performance, we make our word embedding learns from word-context as well as word-class co-occurrence statistics. We combine the word-context and word-class mutual information into a single matrix for factorization.

It is shown by experimental results they outperform several state-of-the-art word embedding methods.

Image credits:

Image showing a simple example algorithm framework for text classification is from https://laptrinhx.com/nlp-multiclass-text-classification-machine-learning-model-using-count-vector-bow-tf-idf-2622024659/