预料意外：利用句子完成进行讽刺检测
Expect the unexpected: Harnessing Sentence Completion for Sarcasm Detection
AI总结：
本文将讽刺检测建模为观察词与预期词的不协调识别，利用基于双向 LSTM 的 Context2Vec 预测预期词，并提出全词与仅不协调词两种方法，验证了句子完成用于讽刺检测的潜力。
摘要：
三元组“I love being”预期后面会接“happy”等积极词汇。然而，在讽刺句中，可能会出现“ignored”一词。因此，预期词与观察到的词之间存在不协调。我们将讽刺检测建模为检测观察词与预期词之间不协调的任务。为了获得预期词，我们使用 Context2Vec，这是一个基于双向 LSTM 的句子完成库。然而，由于这种不协调发生的确切词可能无法提前知道，我们提出了两种方法：全词方法（对每个实词查询句子完成）和仅不协调词方法（对最不协调的50%实词查询句子完成）。这些方法在推文上优于已报告的结果，但在讨论论坛帖子上并非如此。这可能是因为对讨论论坛帖子进行了冗余的句子完成查询。因此，我们考虑一种 oracle 情形，即在过去工作报告的语料库中手动标注确切的不协调词。在这种情形下，性能高于全词方法。这为使用句子完成进行讽刺检测确立了前景。
英文摘要：
The trigram `I love being' is expected to be followed by positive words such as `happy'. In a sarcastic sentence, however, the word `ignored' may be observed. The expected and the observed words are, thus, incongruous. We model sarcasm detection as the task of detecting incongruity between an observed and an expected word. In order to obtain the expected word, we use Context2Vec, a sentence completion library based on Bidirectional LSTM. However, since the exact word where such an incongruity occurs may not be known in advance, we present two approaches: an All-words approach (which consults sentence completion for every content word) and an Incongruous words-only approach (which consults sentence completion for the 50% most incongruous content words). The approaches outperform reported values for tweets but not for discussion forum posts. This is likely to be because of redundant consultation of sentence completion for discussion forum posts. Therefore, we consider an oracle case where the exact incongruous word is manually labeled in a corpus reported in past work. In this case, the performance is higher than the all-words approach. This sets up the promise for using sentence completion for sarcasm detection.
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。
