An Error Detection and Correction Framework for Connectomics

Neural Information Processing Systems

We define and study error detection and correction tasks that are useful for 3D reconstruction of neurons from electron microscopic imagery, and for image segmentation more generally. Both tasks take as input the raw image and a binary mask representing a candidate object. For the error detection task, the desired output is a map of split and merge errors in the object. For the error correction task, the desired output is the true object. We call this object mask pruning, because the candidate object mask is assumed to be a superset of the true object.


Reference-less Measure of Faithfulness for Grammatical Error Correction

arXiv.org Artificial Intelligence

We propose {\sc USim}, a semantic measure for Grammatical Error Correction (GEC) that measures the semantic faithfulness of the output to the source, thereby complementing existing reference-less measures (RLMs) for measuring the output's grammaticality. {\sc USim} operates by comparing the semantic symbolic structure of the source and the correction, without relying on manually-curated references. Our experiments establish the validity of {\sc USim}, by showing that (1) semantic annotation can be consistently applied to ungrammatical text; (2) valid corrections obtain a high {\sc USim} similarity score to the source; and (3) invalid corrections obtain a lower score.\footnote{Our code is available in \url{https://github.com/borgr/USim}.


Keisuke Sakaguchi: Robust Text Correction for Grammar and Fluency

#artificialintelligence

Keisuke Sakaguchi Title: "Robust Text Correction for Grammar and Fluency" Abstract: Robustness has always been a desirable property for natural language processing. In many cases, NLP models (e.g., parsing) and downstream applications (e.g., MT) perform poorly when the input contains noise such as spelling errors, grammatical errors, and disfluency. In this talk, I will present three recent results on error correction models: character, word, and sentence level respectively. For character level, I propose semi-character recurrent neural network, which is motivated by a finding in Psycholinguistics, called Cmabrigde Uinervtisy (Cambridge University) effect. For word-level robustness, I propose an error-repair dependency parsing algorithm for ungrammatical texts.


Machine learning tackles quantum error correction

#artificialintelligence

In a new study, they have demonstrated that a type of neural network called a Boltzmann machine can be trained to model the errors in a quantum computing protocol and then devise and implement the best method for correcting the errors. The physicists, Giacomo Torlai and Roger G. Melko at the University of Waterloo and the Perimeter Institute for Theoretical Physics, have published a paper on the new machine learning algorithm in a recent issue of Physical Review Letters. "The idea behind neural decoding is to circumvent the process of constructing a decoding algorithm for a specific code realization (given some approximations on the noise), and let a neural network learn how to perform the recovery directly from raw data, obtained by simple measurements on the code," Torlai told Phys.org. "With the recent advances in quantum technologies and a wave of quantum devices becoming available in the near term, neural decoders will be able to accommodate the different architectures, as well as different noise sources." As the researchers explain, a Boltzmann machine is one of the simplest kinds of stochastic artificial neural networks, and it can be used to analyze a wide variety of data.


Weakly Supervised Grammatical Error Correction using Iterative Decoding

arXiv.org Machine Learning

We describe an approach to Grammatical Error Correction (GEC) that is effective at making use of models trained on large amounts of weakly supervised bitext. We train the Transformer sequence-to-sequence model on 4B tokens of Wikipedia revisions and employ an iterative decoding strategy that is tailored to the loosely-supervised nature of the Wikipedia training corpus. Finetuning on the Lang-8 corpus and ensembling yields an F0.5 of 58.3 on the CoNLL'14 benchmark and a GLEU of 62.4 on JFLEG. The combination of weakly supervised training and iterative decoding obtains an F0.5 of 48.2 on CoNLL'14 even without using any labeled GEC data.