AI Seminar Series 2022: Puyuan Liu

The AI Seminar is a weekly meeting at the University of Alberta where researchers interested in artificial intelligence (AI) can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics can be related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems.

On August 26, Puyuan Liu — an MSc student from the University of Alberta — presented "Non-Autoregressive Unsupervised Summarization with Length-Control Algorithms" at the AI Seminar.

Text summarization aims to generate a short summary for an input text and has extensive real-world applications such as headline generation. State-of-the-art summarization models are mainly supervised; they require large labeled training corpora and thus cannot be applied to less popular areas, where paired data are rare, e.g., less spoken languages.

In this seminar, Liu presents a non-autoregressive unsupervised summarization model, which does not require parallel data for training. The approach first performs edit-based search towards a heuristically-defined score, and generates a summary as pseudo-groundtruth. Then, she trains an encoder-only non-autoregressive Transformer based on the search results. Further, Liu's team designs two length-control algorithms for the model, which perform dynamic programming on the model output and are able to explicitly control the number of words and characters in the generated summary, respectively.

Experiments on two benchmark datasets show that the approach achieves state-of-the-art performance for unsupervised summarization, yet largely improves inference efficiency. Further, the length-control algorithms are able to perform length-transfer generation, i.e., generating summaries of different lengths than the training target.

Watch the full presentation below:

Keep up-to-date on the AI Seminar Series by signing up for the mailing list.

Learn how Amii advances world-leading artificial intelligence and machine learning research: visit our Research page.