Abstract
We present an analysis of a number of coreference phenomena in English-Croatian human and machine translations. The aim is to shed light on the differences in the way these structurally different languages make use of discourse information and provide insights for discourse-aware machine translation system development. The phenomena are automatically identified in parallel data using annotation produced by parsers and word alignment tools, enabling us to pinpoint patterns of interest in both languages. We make the analysis more fine-grained by including three corpora pertaining to three different registers. In a second step, we create a test set with the challenging linguistic constructions and use it to evaluate the performance of three MT systems. We show that both SMT and NMT systems struggle with handling these discourse phenomena, even though NMT tends to perform somewhat better than SMT. By providing an overview of patterns frequently occurring in actual language use, as well as by pointing out the weaknesses of current MT systems that commonly mistranslate them, we hope to contribute to the effort of resolving the issue of discourse phenomena in MT applications.
Highlights
Every natural language has means of marking elements belonging to the same coreference chain in order to achieve cohesion and coherence in running text
While for individual phenomena SMT invariably performs best on DGT, there is some variation in the NMT systems, with NMT2 notably performing best on SETIMES2 for all three cases of it in subject position and for koji as object
A closer look at the data reveals that the good performance on articles is largely due to NMT producing differently phrased translations, whereas their performance on possessives is explained by the fact that the informal style and overall proliferation of determiners and pronouns frequently make the retention of possessives seem acceptable
Summary
Every natural language has means of marking elements belonging to the same coreference chain in order to achieve cohesion and coherence in running text These discourse phenomena are crucial for understanding texts and their misrepresentation harms text intelligibility. We investigate both human translation and the output of different types of MT systems. While reflections on the relevant linguistic intuitions are given as a reference, the selection of the phenomena chosen for further examination is primarily based on the data obtained from corpora This makes our approach strongly usage-based and provides ample space for making observations unconstrained by a particular theoretical framework
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
