Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleOctober 2023
GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementPages 36–46https://doi.org/10.1145/3583780.3614901Retrieval-enhanced text generation has shown remarkable progress on knowledge-intensive language tasks, such as open-domain question answering and knowledge-enhanced dialogue generation, by leveraging passages retrieved from a large passage corpus for ...
- ArticleOctober 2020
LARQ: Learning to Ask and Rewrite Questions for Community Question Answering
Natural Language Processing and Chinese ComputingPages 318–330https://doi.org/10.1007/978-3-030-60457-8_26AbstractTaking advantage of the rapid growth of community platforms, such as Yahoo Answers, Quora, etc., Community Question Answering (CQA) systems are developed to retrieve semantically equivalent questions when users raise a new query. A typical CQA ...
- research-articleJuly 2019
Content-based table retrieval for web queries
Neurocomputing (NEUROC), Volume 349, Issue CPages 183–189https://doi.org/10.1016/j.neucom.2018.10.033AbstractUnderstanding the connections between unstructured text and semi-structured table is an important yet neglected problem in natural language processing. In this work, we focus on content-based table retrieval. Given a query, the task is ...
- research-articleFebruary 2018
Response selection from unstructured documents for human-computer conversation systems
Knowledge-Based Systems (KNBS), Volume 142, Issue CPages 149–159https://doi.org/10.1016/j.knosys.2017.11.033AbstractThis paper studies response selection for human-computer conversation systems. Existing retrieval-based human-computer conversation systems are intended to reply to user utterances based on existing utterance-response pairs. However, ...