Lan, Wuwei and Xu, Wei, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) 2018/07/24 自然言語処理 修士1年 勝田 哲弘
2015) ◦ paraphrase identification (Dolan et al., 2004; Xu et al., 2015) ◦ natural language inference (Bowman et al., 2015), etc. • out-of-vocabularyの割合がしばしば20%を超えるソーシャル メディアドメインではカバレッジが悪い(Baldwin et al., 2013). 3
et al., 2016; He and Lin, 2016; Liu et al., 2016; Tomar et al., 2017; Wang et al., 2017; Shen et al., 2017, etc) • contextualized word vectors generated via Bi-LSTM, CNN, or attention • soft or hard word alignment and interactions across sentences • and the output classification layer. 2つの文の間の意味関係は主にチャンクの対応関係に依存する(Agirre et al., 2016) 5
Lin, 2016) and (Lan et al., 2017) • Embedding ◦ 300-dimensional GloVe ◦ 27 billion words from Twitter (vocabulary size of 1.2 million words) ◦ without pretraining : random samples [0.05, 0.05] • 学習データ ◦ MSRP 840 billion words (vocabulary size of 2.2 million words) 10