Structural and Topical Dimensions in Multi-Task Patent Translation

Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pages 818–828, Avignon, France, April 23 - 27 2012. c⃝2012 Association for Computational Linguistics Structural and Topical Dimensions in Multi-Task Patent Translation Katharina W¨aschle and Stefan Riezler Department of Computational Linguistics Heidelberg University, Germany {waeschle,riezler}@cl.uni-heidelberg.de Abstract Patent translation is a complex problem due to the highly specialized technical vocab- ulary and the peculiar textual structure of patent documents. In this paper we analyze patents along the orthogonal dimensions of topic and textual structure. We view differ- ent patent classes and different patent text sections such as title, abstract, and claims, as separate translation tasks, and investi- gate the influence of such tasks on machine translation performance. We study multi- task learning techniques that exploit com- monalities between tasks by mixtures of translation models or by multi-task meta- parameter tuning. We find small but sig- nificant gains over task-specific training by techniques that model commonalities through shared parameters. A by-product of our work is a parallel patent corpus of 23 million German-English sentence pairs. 1 Introduction Patents are an important tool for the protection of intellectual property and also play a significant role in business strategies in modern economies. Patent translation is an enabling technique for patent prior art search which aims to detect a patent’s novelty and thus needs to be cross-lingual for a multitude of languages. Patent translation is complicated by a highly specialized vocabulary, consisting of technical terms specific to the field of invention the patent relates to. Patents are writ- ten in a sophisticated legal jargon (“patentese”) that is not found in everyday language and ex- hibits a complex textual structure. Also, patents are often intentionally ambiguous or vague in or- der to maximize the coverage of the claims. In this paper, we analyze patents with respect to the orthogonal dimensions of topic – the tech- nical field covered by the patent – and structure – a patent’s text sections –, with respect to their influence on machine translation performance. The topical dimension of patents is charac- terized by the International Patent Classification (IPC)1 which categorizes patents hierarchically into 8 sections, 120 classes, 600 subclasses, down to 70,000 subgroups at the leaf level. Table 1 shows the 8 top level sections. A Human Necessities B Performing Operations, Transporting C Chemistry, Metallurgy D Textiles, Paper E Fixed Constructions F Mechanical Engineering, Lighting, Heating, Weapons G Physics H Electricity Table 1: IPC top level sections. Orthogonal to the patent classification, patent documents can be sub-categorized along the di- mension of textual structure. Article 78.1 of the European Patent Convention (EPC) lists all sec- tions required in a patent document2: ”A European patent application shall contain: (a) a request for the grant of a Euro- pean patent; 1http://www.wipo.int/classifications/ ipc/en/ 2Highlights by the authors. 818 (b) a description of the invention; (c) one or more claims; (d) any drawings referred to in the de- scription or the claims; (e) an abstract, and satisfy the requirements laid …

Content truncated to 500 words