Abstract
Previous studies combining knowledge graph (KG) with neural machine translation (NMT) have two problems: i) Knowledge under-utilization: they only focus on the entities that appear in both KG and training sentence pairs, making much knowledge in KG unable to be fully utilized. ii) Granularity mismatch: the current KG methods utilize the entity as the basic granularity, while NMT utilizes the sub-word as the granularity, making the KG different to be utilized in NMT. To alleviate above problems, we propose a multi-task learning method on sub-entity granularity. Specifically, we first split the entities in KG and sentence pairs into sub-entity granularity by using joint BPE. Then we utilize the multi-task learning to combine the machine translation task and knowledge reasoning task. The extensive experiments on various translation tasks have demonstrated that our method significantly outperforms the baseline models in both translation quality and handling the entities.
Highlights
Neural machine translation (NMT) based on the encoder-decoder architecture becomes a new state-ofthe-art approach due to its distributed representation and end-to-end learning (Luong et al, 2015; Gehring et al, 2017; Vaswani et al, 2017).During translation, the translation quality of the entities in a sentence has a great influence on the translation quality of the whole sentence
Great efforts have been made to incorporate knowledge graphs (KGs) into NMT, we find the existing methods have the following two problems: Knowledge Under-utilization: Given a KG and a parallel sentence pair dataset, the full entity set U can be divided into four subsets as shown in Fig. 1 (a): 1) K ∩ D entities, which appear in both K and D; 2) D −K entities, which only appear in D; 3) K −D entities, which only appear in K; 4) U −(K ∪D) entities, which are neither in K nor D
The results show that our proposed method is effective on NMT when both source and target KGs are available
Summary
Neural machine translation (NMT) based on the encoder-decoder architecture becomes a new state-ofthe-art approach due to its distributed representation and end-to-end learning (Luong et al, 2015; Gehring et al, 2017; Vaswani et al, 2017).During translation, the translation quality of the entities in a sentence has a great influence on the translation quality of the whole sentence. Some methods aim at incorporating the knowledge graph (KG) to utilize their structured knowledge on entities and improve the entity translation These studies utilize KG to enhance the semantic representing of entities in a sentence (Moussallem et al, 2019; Lu et al, 2018) or extract the important semantic vectors with KG (Shi et al, 2016). Great efforts have been made to incorporate KG into NMT, we find the existing methods have the following two problems: Knowledge Under-utilization: Given a KG (denoted by K) and a parallel sentence pair dataset (denoted by D), the full entity set U can be divided into four subsets as shown in Fig. 1 (a): 1) K ∩ D entities, which appear in both K and D; 2) D −K entities, which only appear in D; 3) K −D entities, which only appear in K; 4) U −(K ∪D) entities, which are neither in K nor D.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.