08/12/2020

SpanAlign: Sentence Alignment Method based on Cross-Language Span Prediction and ILP

Katsuki Chousa, Masaaki Nagata, Masaaki Nishino

Keywords:

Abstract Paper Similar Papers

Abstract: We propose a novel method of automatic sentence alignment from noisy parallel documents. We first formalize the sentence alignment problem as the independent predictions of spans in the target document from sentences in the source document. We then introduce a total optimization method using integer linear programming to prevent span overlapping and obtain non-monotonic alignments. We implement cross-language span prediction by fine-tuning pre-trained multilingual language models based on BERT architecture and train them using pseudo-labeled data obtained from unsupervised sentence alignment method. While the baseline methods use sentence embeddings and assume monotonic alignment, our method can capture the token-to-token interaction between the tokens of source and target text and handle non-monotonic alignments. In sentence alignment experiments on English-Japanese, our method achieved 70.3 F1 scores, which are +8.0 points higher than the baseline method. In particular, our method improved by +53.9 F1 scores for extracting non-parallel sentences. Our method improved the downstream machine translation accuracy by 4.1 BLEU scores when the extracted bilingual sentences are used for fine-tuning a pre-trained Japanese-to-English translation model.

The video of this talk cannot be embedded. You can watch it here:
https://underline.io/lecture/6334-spanalign-sentence-alignment-method-based-on-cross-language-span-prediction-and-ilp
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at COLING 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 11:13 
 0
 0
 0
 0
 3:51 
 0
 0
 0
 0
 7:46 
 0
 0
 0
 0
 12:44 
 0
 0
 0
 0
 13:44 
 0
 0
 0
 0
 12:07 
 0
 0
 0
 0
 12:00 
 0
 0
 0
 0
 14:32 
 0
 0
 0
 0
 6:31 
 0
 0
 0
 0
 10:57 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 9:45 
 0
 0
 0
 0
 13:01 
 0
 0
 0
 0
 6:56 
 0
 0
 0
 0
 10:48 
 0
 0
 0
 0
 11:56 
 0
 0
 0
 0
 11:45 
 0
 0
 0
 0
 10:34 
 0
 0
 0
 0
 17:06 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 14:39 
 0
 0
 0
 0
 11:16 
 0
 0
 0
 0
 4:49 
 0
 0
 0
 0
 15:01 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 12:23 
 0
 0
 0
 0
 15:18 
 0
 0
 0
 0
 5:13 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 14:50 
 0
 0
 0
 0
 14:59 
 0
 0
 0
 0
 11:30 
 0
 0
 0
 0
 17:39 
 0
 0
 0
 0
 11:42 
 0
 0
 0
 0
 11:54 
 0
 0
 0
 0
 12:24 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 7:09 
 0
 0
 0
 0
 10:38