Reasoning with Multimodal Sarcastic Tweets via Modeling Cross-Modality Contrast and Semantic Association

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 358–364 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 358 Content Word Aware Neural Machine Translation Kehai Chen, Rui Wang∗, Masao Utiyama, and Eiichiro Sumita National Institute of Information and Communications Technology (NICT), Kyoto, Japan {khchen, wangrui, mutiyama, eiichiro.sumita}@nict.go.jp Abstract Neural machine translation (NMT) encodes the source sentence in a universal way to generate the target sentence word-by- word. However, NMT does not consider the importance of word in the sentence meaning, for example, some words (i.e., content words) express more important meaning than others (i.e., function words). To address this limitation, we first utilize word frequency information to distinguish between content and function words in a sentence, and then design a content word-aware NMT to improve translation performance. Empirical results on the WMT14 English-to-German, WMT14 English-to-French, and WMT17 Chinese- to-English translation tasks show that the proposed methods can significantly improve the performance of Transformer-based NMT. 1 Introduction Neural machine translation (NMT) models (Sutskever et al., 2014; Bahdanau et al., 2015; Vaswani et al., 2017) often utilize the global neural networks to encode all words for learning the sentence representation and the context vector, and computes the accuracy of each generated target word in a universal manner. Meanwhile, each generated target word makes the same contribution to the optimization of the NMT model, regardless of its importance. Actually, there lacks a mechanism to guarantee that NMT captures the information related to word importance when predicting translations. Intuitively, content words express more impor- tant meanings than function words, which indicates their comparative significance. To evaluate this, we randomly masked content or function words with UNK in a source sentence. Figure 1 shows that the BLEU scores of the test set decreased much ∗Corresponding author 0 1 2 3 4 5 6 7 8 9 10 10 20 30 Number BLEU Transformer (base) -Function Words -Content Words Figure 1: “Number” denotes the number of content or function words that were randomly masked in each sentence of the WMT14 English-to-German translation task. more substantially when parts of content words were randomly replaced with UNK on the WMT14 English-to-German task, which is in line with the findings in He et al. (2019)’s work. To address this limitation, we propose a content word-aware NMT model that exploits the results of translation using a sequence of content words learned by a simple content word recognition method. Inspired by the works of (Setiawan et al., 2007, 2009; Zhang and Zhao, 2013), we first divide words in a sentence into content words and other function words depending on term frequency- inverse document frequency (TF-IDF) constraints. Two methods are designed to utilize the sequence of content word on the source and target sides: 1) We encode the content words of the source sentence as a new source representation, and learn an additional content word context vector based on it to improve translation performance; 2) A specific loss for content words of the target sentence …

Content truncated to 500 words