SML: a new Semantic Embedding Alignment Transformer for efficient cross-lingual Natural Language Inference

The ability of Transformers to perform with precision a variety of tasks such as question answering, Natural Language Inference (NLI) or summarising, have enable them to be ranked as one of the best paradigms to address this kind of tasks at present. NLI is one of the best scenarios to test these architectures, due to the knowledge required to understand complex sentences and established a relation between a hypothesis and a premise. Nevertheless, these models suffer from incapacity to generalise to other domains or difficulties to face multilingual scenarios. The leading pathway in the literature to address these issues involve designing and training extremely large architectures, which leads to unpredictable behaviours and to establish barriers which impede broad access and fine tuning. In this paper, we propose a new architecture, siamese multilingual transformer (SML), to efficiently align multilingual embeddings for Natural Language Inference. SML leverages siamese pre-trained multi-lingual transformers with frozen weights where the two input sentences attend each other to later be combined through a matrix alignment method. The experimental results carried out in this paper evidence that SML allows to reduce drastically the number of trainable parameters while still achieving state-of-the-art performance.