arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1603.06127cs.CLcs.AIcs.LGcs.NE
收藏

句对评分:语篇理解的统一框架

Sentence Pair Scoring: Towards Unified Framework for Text Comprehension

FEE CTU Prague(捷克理工大学布拉格分校电气工程学院)

Petr Baudiš, Jan Pichl, Tomáš Vyskočil, Jan Šedivý

摘要:

我们回顾了句子对评分的任务,在文献中以各种形式流行-被视为回答句子选择,语义文本评分,下一个话语排名,识别文本蕴涵,释义或例如记忆网络的一个组成部分。我们认为,从模型的角度来看,所有这些任务都是相似的,并通过在许多句子对评分任务和数据集上比较常见的IR指标和流行的卷积、循环和基于注意力的神经模型的性能,提出了新的基线。我们讨论了评估随机模型的问题,提出了一种基于统计的方法,并试图通过发布新的数据集来改善比较,这些数据集比目前使用的一些经过充分探索的基准要难得多。我们引入了一个统一的开源软件框架,具有易于插入的模型和任务,这使我们能够实验训练句子模型的多任务可重用性。我们在Ubuntu Dialogue数据集上设置了一个新的最先进的性能。

英文摘要:

We review the task of Sentence Pair Scoring, popular in the literature in various forms - viewed as Answer Sentence Selection, Semantic Text Scoring, Next Utterance Ranking, Recognizing Textual Entailment, Paraphrasing or e.g. a component of Memory Networks. We argue that all such tasks are similar from the model perspective and propose new baselines by comparing the performance of common IR metrics and popular convolutional, recurrent and attention-based neural models across many Sentence Pair Scoring tasks and datasets. We discuss the problem of evaluating randomized models, propose a statistically grounded methodology, and attempt to improve comparisons by releasing new datasets that are much harder than some of the currently used well explored benchmarks. We introduce a unified open source software framework with easily pluggable models and tasks, which enables us to experiment with multi-task reusability of trained sentence model. We set a new state-of-art in performance on the Ubuntu Dialogue dataset.

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。

↑