Abstract:There has been relatively little attention to incorporating linguistic prior to neural machine translation. Much of the previous work was further constrained to considering linguistic prior on the source side. In this paper, we propose a hybrid model, called NMT+RNNG, that learns to parse and translate by combining the recurrent neural network grammar into the attention-based neural machine translation. Our approach encourages the neural machine translation model to incorporate linguistic prior during training… Show more
“…In contrast to these approaches, the DSA-LSTM only models the probability of surface strings, albeit with an auxiliary loss that distills the next-word predictive distribution of a syntactic language model. Earlier work has also explored multi-task learning with syntactic objectives as an auxiliary loss in language modelling and machine translation (Luong et al, 2016;Eriguchi et al, 2016;Nadejde et al, 2017;Enguehard et al, 2017;Aharoni and Goldberg, 2017;Eriguchi et al, 2017). Our approach of injecting syntactic bias through a KD objective is orthogonal to this approach, with the primary difference that here the student DSA-LSTM has no direct access to syntactic annotations; it does, however, have access to the teacher RNNG's softmax distribution over the next word.…”
Prior work has shown that, on small amounts of training data, syntactic neural language models learn structurally sensitive generalisations more successfully than sequential language models. However, their computational complexity renders scaling difficult, and it remains an open question whether structural biases are still necessary when sequential models have access to ever larger amounts of training data. To answer this question, we introduce an efficient knowledge distillation (KD) technique that transfers knowledge from a syntactic language model trained on a small corpus to an LSTM language model, hence enabling the LSTM to develop a more structurally sensitive representation of the larger training data it learns from. On targeted syntactic evaluations, we find that, while sequential LSTMs perform much better than previously reported, our proposed technique substantially improves on this baseline, yielding a new state of the art. Our findings and analysis affirm the importance of structural biases, even in models that learn from large amounts of data.
“…In contrast to these approaches, the DSA-LSTM only models the probability of surface strings, albeit with an auxiliary loss that distills the next-word predictive distribution of a syntactic language model. Earlier work has also explored multi-task learning with syntactic objectives as an auxiliary loss in language modelling and machine translation (Luong et al, 2016;Eriguchi et al, 2016;Nadejde et al, 2017;Enguehard et al, 2017;Aharoni and Goldberg, 2017;Eriguchi et al, 2017). Our approach of injecting syntactic bias through a KD objective is orthogonal to this approach, with the primary difference that here the student DSA-LSTM has no direct access to syntactic annotations; it does, however, have access to the teacher RNNG's softmax distribution over the next word.…”
Prior work has shown that, on small amounts of training data, syntactic neural language models learn structurally sensitive generalisations more successfully than sequential language models. However, their computational complexity renders scaling difficult, and it remains an open question whether structural biases are still necessary when sequential models have access to ever larger amounts of training data. To answer this question, we introduce an efficient knowledge distillation (KD) technique that transfers knowledge from a syntactic language model trained on a small corpus to an LSTM language model, hence enabling the LSTM to develop a more structurally sensitive representation of the larger training data it learns from. On targeted syntactic evaluations, we find that, while sequential LSTMs perform much better than previously reported, our proposed technique substantially improves on this baseline, yielding a new state of the art. Our findings and analysis affirm the importance of structural biases, even in models that learn from large amounts of data.
“…We then experiment in a low-resource scenario using the German, Russian and Czech to English training data from the News Commentary v8 corpus, following Eriguchi et al (2017). In all cases we parse the English sentences into constituency trees using the BLLIP parser (Charniak and Johnson, 2005).…”
Section: Experiments and Resultsmentioning
confidence: 99%
“…In parallel and highly related to our work, Eriguchi et al (2017) proposed to model the target syntax in NMT in the form of dependency trees by using an RNNG-based decoder (Dyer et al, 2016), while Nadejde et al (2017) incorporated target syntax by predicting CCG tags serialized into the target translation. Our work differs from those by modeling syntax using constituency trees, as was previously common in the "traditional" syntaxbased machine translation literature.…”
We present a simple method to incorporate syntactic information about the target language in a neural machine translation system by translating into linearized, lexicalized constituency trees. Experiments on the WMT16 German-English news translation task shown improved BLEU scores when compared to a syntax-agnostic NMT baseline trained on the same dataset. An analysis of the translations from the syntax-aware system shows that it performs more reordering during translation in comparison to the baseline. A smallscale human evaluation also showed an advantage to the syntax-aware system.
“…Similarly, [35] incorporate linguistic annotation to semantic role labeling task. [9] combined translation and dependency parsing by sharing the translation encoder hidden states with the buffer hidden states in a shift-reduce parsing model [8]. Aiming at the same goal, [1] proposed a very simple method.…”
The utility of linguistic annotation in neural machine translation seemed to had been established in past papers. The experiments were however limited to recurrent sequence-to-sequence architectures and relatively small data settings.We focus on the state-of-the-art Transformer model and use comparably larger corpora. Specifically, we try to promote the knowledge of source-side syntax using multi-task learning either through simple data manipulation techniques or through a dedicated model component. In particular, we train one of Transformer attention heads to produce source-side dependency tree.Overall, our results cast some doubt on the utility of multi-task setups with linguistic information. The data manipulation techniques, recommended in previous works, prove ineffective in large data settings.The treatment of self-attention as dependencies seems much more promising: it helps in translation and reveals that Transformer model can very easily grasp the syntactic structure. An important but curious result is, however, that identical gains are obtained by using trivial "linear trees" instead of true dependencies. The reason for the gain thus may not be coming from the added linguistic knowledge but from some simpler regularizing effect we induced on self-attention matrices.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.