Fang-Fang Zhang

Also published as: Fangfang Zhang


On the Abstractiveness of Neural Document Summarization
Fangfang Zhang | Jin-ge Yao | Rui Yan
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Many modern neural document summarization systems based on encoder-decoder networks are designed to produce abstractive summaries. We attempted to verify the degree of abstractiveness of modern neural abstractive summarization systems by calculating overlaps in terms of various types of units. Upon the observation that many abstractive systems tend to be near-extractive in practice, we also implemented a pure copy system, which achieved comparable results as abstractive summarizers while being far more computationally efficient. These findings suggest the possibility for future efforts towards more efficient systems that could better utilize the vocabulary in the original document.


A Speech-in List-out Approach to Spoken User Interfaces
Vijay Divi | C. Forlines | Jan Van Gemert | Bhiksha Raj | B. Schmidt-Nielsen | Kent Wittenburg | Joseph Woelfel | Fang-Fang Zhang
Proceedings of HLT-NAACL 2004: Short Papers