No abstract

In order to simulate human language capacity, natural language processing systems must be able to reason about the dynamics of everyday situations, including their possible causes and effects. Moreover, they should be able to generalise the acquired world knowledge to new languages, modulo cultural differences. Advances in machine reasoning and cross-lingual transfer depend on the availability of challenging evaluation benchmarks. Motivated by both demands, we introduce Cross-lingual Choice of Plausible Alternatives (XCOPA), a typologically diverse multilingual dataset for causal commonsense reasoning in 11 languages, which includes resource-poor languages like Eastern Apurímac Quechua and Haitian Creole. We evaluate a range of state-of-the-art models on this novel dataset, revealing that the performance of current methods based on multilingual pretraining and zero-shot fine-tuning falls short compared to translation-based transfer. Finally, we propose strategies to adapt multilingual models to out-of-sample resource-lean languages where only a small corpus or a bilingual dictionary is available, and report substantial improvements over the random baseline. The XCOPA dataset is freely available at github.com/cambridgeltl/xcopa.

No abstract

In this paper, we present a thorough investigation on methods that align pre-trained contextualized embeddings into shared crosslingual context-aware embedding space, providing strong reference benchmarks for future context-aware crosslingual models. We propose a novel and challenging task, Bilingual Token-level Sense Retrieval (BTSR). It specifically evaluates the accurate alignment of words with the same meaning in crosslingual non-parallel contexts, currently not evaluated by existing tasks such as Bilingual Contextual Word Similarity and Sentence Retrieval. We show how the proposed BTSR task highlights the merits of different alignment methods. In particular, we find that using context average type-level alignment is effective in transferring monolingual contextualized embeddings cross-lingually especially in non-parallel contexts, and at the same time improves the monolingual space. Furthermore, aligning independently trained models yields better performance than aligning multilingual embeddings with shared vocabulary.

PurposeThe purpose of this paper is to demonstrate the preliminary work on using laser cladding technology for the restoration of structural integrity.Design/methodology/approachThe primary methodology used in this research is to develop a laser cladding‐based metal deposition technique to articulate restoration of structural geometry affected by corrosion damages. Following from this method, it is planned to undertake further work to use the laser cladding process to restore geometry and the associated static/fatigue strength.FindingsThis work has found that it is possible to use laser cladding as a repair technology to improve structural integrity in aluminium alloy aircraft structures in terms of corrosion reduction and geometrical restoration. Initial results have indicated a reduction of static and fatigue resistance with respect to substrate. But more recent works (yet to be published) have revealed improved fatigue strength as measured in comparison to the substrate structural properties.Originality/valueThe research is based on an acceptable materials processing technique.