Long document summarization poses obstacles to current generative transformer-based models because of the broad context to process and understand. Indeed, detecting long-range dependencies is still challenging for today’s state-of-the-art solutions, usually requiring model expansion at the cost of an unsustainable demand for computing and memory capacities. This paper introduces Emma, a novel efficient memory-enhanced transformer-based architecture. By segmenting a lengthy input into multiple text fragments, our model stores and compares the current chunk with previous ones, gaining the capability to read and comprehend the entire context over the whole document with a fixed amount of GPU memory. This method enables the model to deal with theoretically infinitely long documents, using less than 18 and 13 GB of memory for training and inference, respectively. We conducted extensive performance analyses and demonstrate that Emma achieved competitive results on two datasets of different domains while consuming significantly less GPU memory than competitors do, even in low-resource settings.

Analyzing and evaluating legal case reports are labor-intensive tasks for judges and lawyers, who usually base their decisions on report abstracts, legal principles, and commonsense reasoning. Thus, summarizing legal documents is time-consuming and requires excellent human expertise. Moreover, public legal corpora of specific languages are almost unavailable. This paper proposes a transfer learning approach with extractive and abstractive techniques to cope with the lack of labeled legal summarization datasets, namely a low-resource scenario. In particular, we conducted extensive multi- and cross-language experiments. The proposed work outperforms the state-of-the-art results of extractive summarization on the Australian Legal Case Reports dataset and sets a new baseline for abstractive summarization. Finally, syntactic and semantic metrics assessments have been carried out to evaluate the accuracy and the factual consistency of the machine-generated legal summaries.

The quadratic memory complexity of transformers prevents long document summarization in low computational resource scenarios. State-of-the-art models need to apply input truncation, thus discarding and ignoring potential summary-relevant contents, leading to a performance drop. Furthermore, this loss is generally destructive for semantic text analytics in high-impact domains such as the legal one. In this paper, we propose a novel semantic self-segmentation (Se3) approach for long document summarization to address the critical problems of low-resource regimes, namely to process inputs longer than the GPU memory capacity and produce accurate summaries despite the availability of only a few dozens of training instances. Se3 segments a long input into semantically coherent chunks, allowing transformers to summarize very long documents without truncation by summarizing each chunk and concatenating the results. Experimental outcomes show the approach significantly improves the performance of abstractive summarization transformers, even with just a dozen of labeled data, achieving new state-of-the-art results on two legal datasets of different domains and contents. Finally, we report ablation studies to evaluate each contribution of the components of our method to the performance gain.

Gianluca Moro, Luca Ragazzi, Lorenzo Valgimigli, Davide Freddi. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Generative transformer-based models have reached cutting-edge performance in long document summarization. Nevertheless, this task is witnessing a paradigm shift in developing ever-increasingly computationally-hungry solutions, focusing on effectiveness while ignoring the economic, environmental, and social costs of yielding such results. Accordingly, such extensive resources impact climate change and raise barriers to small and medium organizations distinguished by low-resource regimes of hardware and data. As a result, this unsustainable trend has lifted many concerns in the community, which directs the primary efforts on the proposal of tools to monitor models' energy costs. Despite their importance, no evaluation measure considering models' eco-sustainability exists yet. In this work, we propose Carburacy, the first carbon-aware accuracy measure that captures both model effectiveness and eco-sustainability. We perform a comprehensive benchmark for long document summarization, comparing multiple state-of-the-art quadratic and linear transformers on several datasets under eco-sustainable regimes. Finally, thanks to Carburacy, we found optimal combinations of hyperparameters that let models be competitive in effectiveness with significantly lower costs.