Dinh Tuyen Hoang

A combination of active learning and self-learning for named entity recognition on Twitter using conditional random fields

Abstract In recent years, many applications in natural language processing (NLP) have been developed using the machine learning approach. Annotating data is an important task in applying machine learning to NLP applications. A common approach to improve the system performance is to train on a large and high-quality set of training data that is annotated by experts. Besides, active learning (AL) and self-learning can be utilized to reduce the annotation costs. The self-learning method discovers highly reliable instances based on a trained classifier, while AL queries the most informative instances based on active query algorithms. This paper proposes a method that combines AL and self-learning to reduce the labeling effort for the named entity recognition task from tweet streams by using both machine-labeled and manually-labeled data. We employ AL queries based on the diversity of the context and content of instances to select the most informative instances. The conditional random fields are also chosen as an underlying model to train a classifier for selecting highly reliable instances. The experiments using Twitter data show that the proposed method achieves good results in reducing the human labeling effort, and it can significantly improve the performance of the systems.

Academic event recommendation based on research similarity and exploring interaction between authors

In this study, a new academic event recommendation method is proposed. This method analyzes author interactions, academic event attendance records, research related, and textual descriptions from attended academic events to measure interaction strength between authors. Experiments on the DBLP dataset and Wiki Calls for Papers (WikiCFP) showed that the proposed method is helpful in improving the accuracy of a recommendation system in comparison with other methods. In addition, this method can be applied to various recommended tasks such as collaboration recommendation, papers recommendation, etc.

A Consensus-Based Method to Enhance a Recommendation System for Research Collaboration

With the development of scientific societies, research problems are increasingly complex, requiring scientists to collaborate to solve them. The quality of collaboration between researchers is a major factor in determining their achievements. This study proposes a collaboration recommendation method that takes into account previous research collaboration and research similarities. Research collaboration is measured by combining the collaboration time and the number of co-authors who already collaborated with an author. Research similarity is based on authors’ previous publications and academic events they attended. In addition, a consensus-based algorithm is proposed to integrate bibliography data from different sources, such as the DBLP Computer Science Bibliography, ResearchGate, CiteSeer, and Google Scholar. The experimental results show that this proposal improves the accuracy of the recommendation systems, in comparison with other methods.

Active Learning-Based Approach for Named Entity Recognition on Short Text Streams

The named entity recognition (NER) problem has an important role in many natural language processing (NLP) applications and is one of the fundamental tasks for building NLP systems. Supervised learning methods can achieve high performance but they require a large amount of training data that is time-consuming and expensive to obtain. Active learning (AL) is well-suited to many problems in NLP, where unlabeled data may be abundant but labeled data is limited. The AL method aims to minimize annotation costs while maximizing the desired performance from the model. This study proposes a method to classify named entities from Tweet streams on Twitter by using an AL method with different query strategies. The samples were queried for labeling by human annotators based on query by committee and diversity-based querying. The experiments evaluated the proposed method on Tweet data and achieved promising results that proved better than the baseline.

A Hybrid Method for Named Entity Recognition on Tweet Streams

Information extraction from microblogs has recently attracted researchers in the fields of knowledge discovery and data mining owing to its short nature. Annotating data is one of the significant issues in applying machine learning approaches to these sources. Active learning (AL) and semi-supervised learning (SSL) are two distinct approaches to reduce annotation costs. The SSL approach exploits high-confidence samples and AL queries the most informative samples. Thus they can produce better results when jointly applied. This paper proposes a combination of AL and SSL to reduce the labeling effort for named entity recognition (NER) from tweet streams by using both machine-labeled and manually-labeled data. The AL query algorithms select the most informative samples to label those done by a human annotator. In addition, Conditional Random Field (CRF) is chosen as an underlying model to select high-confidence samples. The experiment results on a tweet dataset demonstrate that the proposed method achieves promising results in reducing the human labeling effort and that it can significantly improve the performance of NER systems.

Improving Academic Event Recommendation Using Research Similarity and Interaction Strength Between Authors

ABSTRACT The scientific community is growing very quickly. Every year a huge number of academic events (conferences, workshops, symposiums, etc.) are organized over the world. Therefore, it is difficult for researchers to find related information about the events in which they may be interested. In this study, we present an improvement to existing academic event recommendation methods by taking into account research similarity and interaction strength between authors. By means of experimental analysis on data from the DBLP Computer Science Bibliography and Wiki Calls for Papers (WikiCFP), we will show that the proposed method improves the accuracy of the recommendations in comparison with other methods.

A Group Recommender System for Selecting Experts to Review a Specific Problem

With the increase in the number of publications and scientific projects, its quality requirements are increasingly needed. Reviewing is the most important step in accrediting the quality of scientific work. Criteria such as independence, competence, and lack of conflicts of interest in an expert are essential in the reviewer selection process. However, we also know that experts have limited knowledge, experience, and opinions about the work of others, so they might misunderstand the viewpoints of the authors, which may lead to rejection of an excellent scientific work or an implicitly successful project proposal. Manually selecting reviewers can be a biased and time-consuming process. In order to solve these problems, we developed a recommender system to choose a group of experts to evaluate a specific problem, such as a research proposal or paper. Our recommender system consists of three main modules: data collection, expert detection, and expert prediction. The data collection module is to collect data from various sources to create a database of scientist profiles. The expert detection module is used to determine the experts on each particular topic. The expert prediction module is to provide a list of experts to answer the query. We conducted experiments with the DBLP Computer Science Bibliography dataset, and the results show that our system is an up-and-coming selection process.

Tweet Integration by Finding the Shortest Paths on a Word Graph

Twitter is a well-known social network service. Every second, users post a large number of tweets on different topics, which leads to a significant problem-it is time-consuming for users to get useful information for their individual purposes. It is difficult for a user to receive necessary information from all topics with high accuracy. Thus, integrating the tweets to create summaries is very convenient solution for users. There are some previous works trying to solve the problem of tweet integration. However, they did not consider automatic grouping tweets into small clusters according to topic. Moreover, the tweets have not analyzed for sentiment mining before summarization. In this study, we propose an approach to integrate tweets by taking into account techniques such as topic modeling to automatically determine the number of topics as well as the tweets inside each topic, plus sentiment analysis to classify the attitudes of the users. The experimental results show that the proposed model achieves promising results.

An Approach for Recommending Group Experts on Question and Answering Sites

Question-and-answer (Q&A) sites can be understood as information systems where users generate and answer questions. Also, they can determine the top answers using the number of positive and negative votes from crowd knowledge and experts. Knowledge sharing sites have been rapidly growing in recent years. It is difficult for a user to find experts who can write great answers to their questions. Recent approaches have focused on recommendations from a single expert. However, a question may contain several topics. Thus, finding the experts group to answer the questions is the best solution. In this paper, we propose a new expert group-recommendation method for Q&A systems. First, the users’ profiles are built to determine experts and non-experts. Second, a topic modeling method is used to identify the topic of the question and matches it to corresponding experts. Third, a social graph is generated to find expert groups. In order to increase knowledge and avoid following the crowd, we require that the members of expert groups not only match the skill requirements to answer the questions but also be diverse. Diversity is an essential factor to promote the development of Q&A sites. Experimenting on Quora dataset shows that the method achieves promising results.

Social Network-Based Event Recommendation

The number of events generated on social networks has been growing quickly in recent years. It is difficult for users to find events that most suitably match their favorites. As a solution, the recommender system appears to solve this problem. However, event recommendation is significantly different from traditional recommendations, such as products and movies. Social events are created continuously, and only valid for a short time, so recommending a past event is meaningless. In this paper, we proposed a new even recommendation method based on social networks. First, the behavior of users be detected in order to build the user’s profile. Then the users’ relationship is extracted to measure the interaction strength between them. That is a fundamental factor affecting a decision of a user to attend events. In addition, the opinions about attended events are taken into account to evaluate the satisfaction of attendees by using deep learning method. Twitter is used as a case study for the method. The experiment shows that the method achieves promising results in comparison to other methods.