-
Article
Open AccessA Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-oriented Dialogue Policy Learning
Dialogue policy learning (DPL) is a key component in a task-oriented dialogue (TOD) system. Its goal is to decide the next action of the dialogue system, given the dialogue state at each turn based on a learne...
-
Chapter and Conference Paper
Rumor Detection with Hierarchical Recurrent Convolutional Neural Network
Automatic rumor detection for events on online social media has attracted considerable attention in recent years. Usually, the events on social media are divided into several time segments, and for each segmen...
-
Chapter and Conference Paper
A Tensor Factorization Based User Influence Analysis Method with Clustering and Temporal Constraint
User influence analysis in social media has attracted tremendous interest from both the sociology and social data mining. It is becoming a hot topic recently. However, most approaches ignore the temporal chara...
-
Chapter and Conference Paper
The Role of Physical Location in Our Online Social Networks
One of the most important properties of social networking sites is its reachability – no physical location constraint. In addition, all social networking sites allow us to search people with common interests, ...
-
Chapter and Conference Paper
An Iterative Emotion Classification Approach for Microblogs
The typical emotion classification approach adopts one-step single-label classification using intra-sentence features such as unigrams, bigrams and emotion words. However, single-label classifier with intra-se...
-
Chapter and Conference Paper
Trending Sentiment-Topic Detection on Twitter
Twitter plays a significant role in information diffusion and has evolved to an important information resource as well as news feed. People wonder and care about what is happening on Twitter and what news it i...
-
Chapter and Conference Paper
Pests Hidden in Your Fans: An Effective Approach for Opinion Leader Discovery
With the development of Web 2.0, people would like to share opinions on the Web, which are very helpful for other users to make decisions. Especially, some users have more powerful influence to other members o...
-
Chapter and Conference Paper
Weight-Based Boosting Model for Cross-Domain Relevance Ranking Adaptation
Adaptation techniques based on importance weighting were shown effective for RankSVM and RankNet, viz., each training instance is assigned a target weight denoting its importance to the target domain and incorpor...
-
Chapter
Unknown Word Identification
-
Chapter
Chinese Collocations
Collocation is a lexical phenomenon where two or more words are habitually combined together as some conventional way of saying things. For example, in Chinese, 历史/n 包袱/n (historical burden) rather than 历史/n 行...
-
Chapter
Words in Chinese
-
Chapter
Introduction
The world is flat [Friedman 2005]. Globalization has virtually lifted the boundaries between countries. Apparently, the advancement of the Internet is an active catalyst of the globalization process. Today, th...
-
Chapter
Challenges in Chinese Morphological Processing
-
Chapter
Chinese Word Segmentation
-
Chapter
Word Meaning
-
Chapter
Automatic Chinese Collocation Extraction
-
Book
-
Chapter and Conference Paper
Learning MultiLinguistic Knowledge for Opinion Analysis
Most existing opinion analysis techniques used word-level sentiment knowledge but lack the learning capacity on the behaviors of context-dependent opinion words. Meanwhile, the use of collocation-level sentime...
-
Chapter and Conference Paper
Event-Based Summarization Using Time Features
We investigate whether time features help to improve event-based summarization. In this paper, events are defined as event terms and the associated event elements. While event terms represent the actions thems...
-
Book and Conference Proceedings
Computer Processing of Oriental Languages. Beyond the Orient: The Research Challenges Ahead
21st International Conference, ICCPOL 2006, Singapore, December 17-19, 2006. Proceedings