Linguistically Informed Hindi-English Neural Machine Translation

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 3698–3703 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 3698 Linguistically Informed Hindi-English Neural Machine Translation Vikrant Goyal, Pruthwik Mishra, Dipti Misra Sharma Language Technologies Research Center (LTRC) IIIT Hyderabad, India {vikrant.goyal, pruthwik.mishra}@research.iiit.ac.in, dipti@iiit.ac.in Abstract Hindi-English Machine Translation is a challenging problem, owing to multiple factors including the morphological complexity and relatively free word order of Hindi, in addition to the lack of sufficient parallel training data. Neural Machine Translation (NMT) is a rapidly advancing MT paradigm and has shown promising results for many language pairs, especially in large training data scenarios. To overcome the data sparsity issue caused by the lack of large parallel corpora for Hindi-English, we propose a method to employ additional linguistic knowledge which is encoded by different phenomena depicted by Hindi. We generalize the embedding layer of the state-of-the-art Transformer model to incorporate linguistic features like POS tag, lemma and morph features to improve the translation performance. We compare the results obtained on incorporating this knowledge with the baseline systems and demonstrate significant performance improvements. Although, the Transformer NMT models have a strong efficacy to learn language constructs, we show that the usage of specific features further help in improving the translation performance. Keywords: Neural Machine Translation, Transformer, Linguistic Features 1. Introduction In recent years, Neural Machine Translation (Luong et al., 2015; Bahdanau et al., 2014; Johnson et al., 2017; Wu et al., 2017; Vaswani et al., 2017) (NMT) has become the most prominent approach to Machine Translation (MT) due to its simplicity, generality and effectiveness. In NMT, a single neural network often consisting of an encoder and a decoder is used to directly maximize the conditional probabilities of target sentences given the source sentences in an end-to-end paradigm. NMT models have been shown to surpass the performance of previously dominant statistical machine translation (SMT) (Koehn, 2009) on many well-established translation tasks. Unlike SMT, NMT does not rely on sub-modules and explicit linguistic features in crafting the translation . Instead, it learns the translation knowledge directly from parallel sentences without resorting to additional linguistic analysis. Although NMT is a promising approach, it still lacks the ability of modeling deeper semantic and syntactic aspects of the language. In machine translation with a low-resource setting, resolving data sparseness and semantic ambiguity problems can help improve its performance. Addition of explicit linguistic knowledge may be of great benefits to NMT models, potentially reducing language ambiguity and alleviating data sparseness further. Some recent studies have shown that incorporating linguistic features in the NMT model can improve the translation performance (Sennrich and Haddow, 2016; Niehues and Cho, 2017; Li et al., 2018). But most of the previous works have shown the effectiveness of usage of linguistic features with the RNN models. However, it is essential to verify whether the strong learning capability of the current state-of-the-art Transformer models make the explicit linguistic features redundant or if they can be easily incorporated to …

Content truncated to 500 words