Decipherment of homophonic substitution ciphers using language models (LMs) is a wellstudied task in NLP. Previous work in this topic scores short local spans of possible plaintext decipherments using n-gram LMs. The most widely used technique is the use of beam search with n-gram LMs proposed by Nuhn et al. (2013). We propose a beam search algorithm that scores the entire candidate plaintext at each step of the decipherment using a neural LM. We augment beam search with a novel rest cost estimation that exploits the prediction power of a neural LM. We compare against the state of the art n-gram based methods on many different decipherment tasks. On challenging ciphers such as the Beale cipher we provide significantly better error rates with much smaller beam sizes.
BackgroundDNA oligonucleotides are a very useful tool in biology. The best algorithms for designing good DNA oligonucleotides are filtering out unsuitable regions using a seeding approach. Determining the quality of the seeds is crucial for the performance of these algorithms.ResultsWe present a sound framework for evaluating the quality of seeds for oligonucleotide design. The F - score is used to measure the accuracy of each seed. A number of natural candidates are tested: contiguous (BLAST-like), spaced, transitions-constrained, and multiple spaced seeds. Multiple spaced seeds are the best, with more seeds providing better accuracy. Single spaced and transition seeds are very close whereas, as expected, contiguous seeds come last. Increased accuracy comes at the price of reduced efficiency. An exception is that single spaced and transitions-constrained seeds are both more accurate and more efficient than contiguous ones.ConclusionsOur work confirms another application where multiple spaced seeds perform the best. It will be useful in improving the algorithms for oligonucleotide design.
Current word alignment models do not distinguish between different types of alignment links. In this paper, we provide a new probabilistic model for word alignment where word alignments are associated with linguistically motivated alignment types. We propose a novel task of joint prediction of word alignment and alignment types and propose novel semi-supervised learning algorithms for this task. We also solve a sub-task of predicting the alignment type given an aligned word pair. In our experimental results, the generative models we introduce to model alignment types significantly outperform the models without alignment types.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.