Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications, where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art GNNs into four categories, namely, recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial–temporal GNNs. We further discuss the applications of GNNs across various domains and summarize the open-source codes, benchmark data sets, and model evaluation of GNNs. Finally, we propose potential research directions in this rapidly growing field.

/pdf/a-comprehensive-survey-on-graph-neural-networks-4lw9i4v183.pdf

A Comprehensive Survey on Graph Neural Networks

Disambiguating named entities in natural-language text maps mentions of ambiguous names onto canonical entities like people or places, registered in a knowledge base such as DBpedia or YAGO. This paper presents a robust method for collective disambiguation, by harnessing context from knowledge bases and using a new form of coherence graph. It unifies prior approaches into a comprehensive framework that combines three measures: the prior probability of an entity being mentioned, the similarity between the contexts of a mention and a candidate entity, as well as the coherence among candidate entities for all mentions together. The method builds a weighted graph of mentions and candidate entities, and computes a dense subgraph that approximates the best joint mention-entity mapping. Experiments show that the new method significantly outperforms prior methods in terms of accuracy, with robust behavior across a variety of inputs.

/pdf/robust-disambiguation-of-named-entities-in-text-2nql8lmxop.pdf

Robust Disambiguation of Named Entities in Text

Disambiguating concepts and entities in a context sensitive way is a fundamental problem in natural language processing. The comprehensiveness of Wikipedia has made the online encyclopedia an increasingly popular target for disambiguation. Disambiguation to Wikipedia is similar to a traditional Word Sense Disambiguation task, but distinct in that the Wikipedia link structure provides additional information about which disambiguations are compatible. In this work we analyze approaches that utilize this information to arrive at coherent sets of disambiguations for a given document (which we call "global" approaches), and compare them to more traditional (local) approaches. We show that previous approaches for global disambiguation can be improved, but even then the local disambiguation provides a baseline which is very hard to beat.

Local and Global Algorithms for Disambiguation to Wikipedia

The large number of potential applications from bridging web data with knowledge bases have led to an increase in the entity linking research. Entity linking is the task to link entity mentions in text with their corresponding entities in a knowledge base. Potential applications include information extraction, information retrieval, and knowledge base population. However, this task is challenging due to name variations and entity ambiguity. In this survey, we present a thorough overview and analysis of the main approaches to entity linking, and discuss various applications, the evaluation of entity linking systems, and future directions.

/pdf/entity-linking-with-a-knowledge-base-issues-techniques-and-2ds9mn4o8g.pdf

Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions

Sentiment analysis is the computational study of people's opinions, sentiments, emotions, moods, and attitudes. This fascinating problem offers numerous research challenges, but promises insight useful to anyone interested in opinion analysis and social media analysis. This comprehensive introduction to the topic takes a natural-language-processing point of view to help readers understand the underlying structure of the problem and the language constructs commonly used to express opinions, sentiments, and emotions. The book covers core areas of sentiment analysis and also includes related topics such as debate analysis, intention mining, and fake-opinion detection. It will be a valuable resource for researchers and practitioners in natural language processing, computer science, management sciences, and the social sciences.In addition to traditional computational methods, this second edition includes recent deep learning methods to analyze and summarize sentiments and opinions, and also new material on emotion and mood analysis techniques, emotion-enhanced dialogues, and multimodal emotion analysis.

Sentiment Analysis: Mining Opinions, Sentiments, and Emotions

Entity Linking (EL) is the task of linking name mentions in Web text with their referent entities in a knowledge base. Traditional EL methods usually link name mentions in a document by assuming them to be independent. However, there is often additional interdependence between different EL decisions, i.e., the entities in the same document should be semantically related to each other. In these cases, Collective Entity Linking, in which the name mentions in the same document are linked jointly by exploiting the interdependence between them, can improve the entity linking accuracy. This paper proposes a graph-based collective EL method, which can model and exploit the global interdependence between different EL decisions. Specifically, we first propose a graph-based representation, called Referent Graph, which can model the global interdependence between different EL decisions. Then we propose a collective inference algorithm, which can jointly infer the referent entities of all name mentions by exploiting the interdependence captured in Referent Graph. The key benefit of our method comes from: 1) The global interdependence model of EL decisions; 2) The purely collective nature of the inference algorithm, in which evidence for related EL decisions can be reinforced into high-probability decisions. Experimental results show that our method can achieve significant performance improvement over the traditional EL methods.

/pdf/collective-entity-linking-in-web-text-a-graph-based-method-mb9u3pldk3.pdf

Collective entity linking in web text: a graph-based method

Name ambiguity problem has raised an urgent demand for efficient, high-quality named entity disambiguation methods. The key problem of named entity disambiguation is to measure the similarity between occurrences of names. The traditional methods measure the similarity using the bag of words (BOW) model. The BOW, however, ignores all the semantic relations such as social relatedness between named entities, associative relatedness between concepts, polysemy and synonymy between key terms. So the BOW cannot reflect the actual similarity. Some research has investigated social networks as background knowledge for disambiguation. Social networks, however, can only capture the social relatedness between named entities, and often suffer the limited coverage problem. To overcome the previous methods' deficiencies, this paper proposes to use Wikipedia as the background knowledge for disambiguation, which surpasses other knowledge bases by the coverage of concepts, rich semantic information and up-to-date content. By leveraging Wikipedia's semantic knowledge like social relatedness between named entities and associative relatedness between concepts, we can measure the similarity between occurrences of names more accurately. In particular, we construct a large-scale semantic network from Wikipedia, in order that the semantic knowledge can be used efficiently and effectively. Based on the constructed semantic network, a novel similarity measure is proposed to leverage Wikipedia semantic knowledge for disambiguation. The proposed method has been tested on the standard WePS data sets. Empirical results show that the disambiguation performance of our method gets 10.7% improvement over the traditional BOW based methods and 16.7% improvement over the traditional social network based methods.

/pdf/named-entity-disambiguation-by-leveraging-wikipedia-semantic-ii4l86ubam.pdf

Named entity disambiguation by leveraging wikipedia semantic knowledge

Linking entities with knowledge base (entity linking) is a key issue in bridging the textual data with the structural knowledge base. Due to the name variation problem and the name ambiguity problem, the entity linking decisions are critically depending on the heterogenous knowledge of entities. In this paper, we propose a generative probabilistic model, called entity-mention model, which can leverage heterogenous entity knowledge (including popularity knowledge, name knowledge and context knowledge) for the entity linking task. In our model, each name mention to be linked is modeled as a sample generated through a three-step generative story, and the entity knowledge is encoded in the distribution of entities in document P(e), the distribution of possible names of a specific entity P(s\e), and the distribution of possible contexts of a specific entity P(c\e). To find the referent entity of a name mention, our method combines the evidences from all the three distributions P(e), P(s\e) and P(c\e). Experimental results show that our method can significantly outperform the traditional methods.

A Generative Entity-Mention Model for Linking Entities with Knowledge Base

In this paper, we introduce the \textbf{C}hinese \textbf{AI} and \textbf{L}aw challenge dataset (CAIL2018), the first large-scale Chinese legal dataset for judgment prediction. \dataset contains more than $2.6$ million criminal cases published by the Supreme People's Court of China, which are several times larger than other datasets in existing works on judgment prediction. Moreover, the annotations of judgment results are more detailed and rich. It consists of applicable law articles, charges, and prison terms, which are expected to be inferred according to the fact descriptions of cases. For comparison, we implement several conventional text classification baselines for judgment prediction and experimental results show that it is still a challenge for current models to predict the judgment results of legal cases, especially on prison terms. To help the researchers make improvements on legal judgment prediction, both \dataset and baselines will be released after the CAIL competition\footnote{this http URL}.

CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction

Entity Linking (EL) has received considerable attention in recent years Given many name mentions in a document, the goal of EL is to predict their referent entities in a knowledge base Traditionally, there have been two distinct directions of EL research: one focusing on the effects of mention's context compatibility, assuming that "the referent entity of a mention is reflected by its context"; the other dealing with the effects of document's topic coherence, assuming that "a mention's referent entity should be coherent with the document's main topics" In this paper, we propose a generative model -- called entity-topic model, to effectively join the above two complementary directions together By jointly modeling and exploiting the context compatibility, the topic coherence and the correlation between them, our model can accurately link all mentions in a document using both the local information (including the words and the mentions in a document) and the global knowledge (including the topic knowledge, the entity context knowledge and the entity name knowledge) Experimental results demonstrate the effectiveness of the proposed model

Xianpei Han

Papers

Collective entity linking in web text: a graph-based method

Named entity disambiguation by leveraging wikipedia semantic knowledge

A Generative Entity-Mention Model for Linking Entities with Knowledge Base

CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction

An Entity-Topic Model for Entity Linking