Manabu Okumura

Discourse-Aware Hierarchical Attention Network for Extractive Single-Document Summarization

2019

Discourse relations between sentences are often represented as a tree, and the tree structure provides important information for summarizers to create a short and coherent summary. However, current neural network-based summarizers treat the source document …

DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation

2024 · arXiv (Cornell University)

Dataset distillation aims to compress a training dataset by creating a small number of informative synthetic samples such that neural networks trained on them perform as well as those trained on the original training dataset. …

Considering Length Diversity in Retrieval-Augmented Summarization

2025 · arXiv (Cornell University)

This study investigates retrieval-augmented summarization by specifically examining the impact of exemplar summary lengths under length constraints, not covered by previous work. We propose a Diverse Length-aware Maximal Marginal Relevance (DL-MMR) algorithm to better control …

Controlling Output Length in Neural Encoder-Decoders

2016

Neural encoder-decoder models have shown great success in many sequence generation tasks. However, previous work has not investigated situations in which we would like to control the length of encoder-decoder outputs. This capability is crucial …