Adaptative Bilingual Aligning Using Multilingual Sentence Embedding
This addresses a challenge in machine translation and NLP for researchers and practitioners by improving alignment in non-ideal text pairs, though it is incremental as it builds on existing embedding-based methods.
The paper tackles the problem of aligning bilingual texts with fragmentary and non-monotonic parallelism by introducing AIlign, an adaptive system that uses sentence embeddings to guide alignment, achieving state-of-the-art results with quasi-linear complexity.
In this paper, we present an adaptive bitextual alignment system called AIlign. This aligner relies on sentence embeddings to extract reliable anchor points that can guide the alignment path, even for texts whose parallelism is fragmentary and not strictly monotonic. In an experiment on several datasets, we show that AIlign achieves results equivalent to the state of the art, with quasi-linear complexity. In addition, AIlign is able to handle texts whose parallelism and monotonicity properties are only satisfied locally, unlike recent systems such as Vecalign or Bertalign.