Document-level MT models are still far from satisfactory. Existing work extend translation unit
from single sentence to multiple sentences. However, study shows that when we further …

The availability of a tremendous amount of online information bringing about a broad
interest in extracting relevant information in a compact and meaningful way, prompted the …

Existing summarization systems mostly generate summaries purely relying on the content of
the source document. However, even for humans, we usually need some references or …

Document-level machine translation faces the challenge of data sparsity due to its long input
length and a small amount of training data, increasing the risk of learning spurious patterns …

Human experts write summaries using different techniques, including extracting a sentence
from the document and rewriting it, or fusing various information from the document to …

The rewriting method for text summarization combines the advantage of extractive and
abstractive approaches, improving the conciseness and readability of extractive summaries …

Standard extractive systems suffer from the lack of gold training signals since existing
corpora solely provide document and human-written summary pairs while disregarding …

Several recently developed neural network models have shown their potential for automated
text summarization. However, the evaluation results of these models on summarization of …

Abstractive summarization methods typically follow the autoregressive paradigm using the
causal masks in the decoder for training and inference efficiency. However, this approach …

Human experts write summaries using different techniques, including extracting a sentence
from the document and rewriting it, or fusing various information from the document to …