arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.10096cs.CL
收藏

带测量词的简单句子选择算法在句子压缩算法黑盒优化中的应用

With Measured Words: Simple Sentence Selection for Black-Box Optimization of Sentence Compression Algorithms

Yotam Shichel, Meir Kalech, Oren Tsur

摘要:

句子压缩是生成给定句子的较短但合乎语法的版本的任务,保留原始句子的本质。本文提出了一个黑盒优化压缩(B-BOC):给定一个黑盒压缩算法,并假设不是所有的句子都需要压缩-找到最好的候选压缩,以最大限度地提高压缩率和质量。给定所需的压缩比,我们考虑两种情况:(i)单句压缩,以及(ii)句子序列压缩。在第一种情况下,我们的优化器经过训练,以预测每个句子在满足指定比率要求的同时可以压缩的程度。在后者中,将期望的压缩比应用于句子序列(例如,一个段落)作为一个整体,而不是在每一个单独的句子。为了实现这一目标,我们使用B-BOC为每个句子分配最佳压缩比,然后将其转换为背包问题,我们使用有界动态规划解决。我们在三个数据集上对这两种情况下的B-BOC进行了评估,表明与直接应用其他压缩算法相比,我们的优化器提高了准确性和Rouge-F1分数。

英文摘要:

Sentence Compression is the task of generating a shorter, yet grammatical version of a given sentence, preserving the essence of the original sentence. This paper proposes a Black-Box Optimizer for Compression (B-BOC): given a black-box compression algorithm and assuming not all sentences need be compressed -- find the best candidates for compression in order to maximize both compression rate and quality. Given a required compression ratio, we consider two scenarios: (i) single-sentence compression, and (ii) sentences-sequence compression. In the first scenario, our optimizer is trained to predict how well each sentence could be compressed while meeting the specified ratio requirement. In the latter, the desired compression ratio is applied to a sequence of sentences (e.g., a paragraph) as a whole, rather than on each individual sentence. To achieve that, we use B-BOC to assign an optimal compression ratio to each sentence, then cast it as a Knapsack problem, which we solve using bounded dynamic programming. We evaluate B-BOC on both scenarios on three datasets, demonstrating that our optimizer improves both accuracy and Rouge-F1-score compared to direct application of other compression algorithms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑