Pu-Jen Cheng

TL;DR: The feasibility of exploiting the context to learn user reformulation behavior for boosting prediction performance is investigated and a supervised approach to query auto-completion is proposed, where three kinds of reformulation-related features are considered, including term-level, query-level and session-level features.

TL;DR: An online translation approach to determine effective translations for unknown query terms via mining of bilingual search-result pages obtained from Web search engines is proposed.

TL;DR: The experimental results have shown the feasibility of the proposed transitive translation approach in efficiently generating translation equivalents of various terms not covered by general translation dictionaries and revealed that the created translation lexicons can reflect different cultural aspects across regions such as Taiwan, Hong Kong and mainland China.

TL;DR: A novel graph-based framework for timeline summarization, the task of creating different summaries for different timestamps but for the same topic, is presented, which outperform several competitive baselines both in terms of ROUGE and when assessed by human evaluators.

TL;DR: A Web-based term translation approach to determine effective translations for unknown query terms by mining bilingual search-result pages obtained from a real Web search engine can enhance the construction of a domain-specific bilingual lexicon and benefit CLIR services in a digital library that only has monolingual document collections.