Keisuke Sakaguchi

We present a new parallel corpus, JHU FLuency-Extended GUG corpus (JFLEG) for developing and evaluating grammatical error correction (GEC). Expand

We establish a ground truth for GEC by conducting a human evaluation and producing a human ranking of the systems entered into the CoNLL-2014 Shared Task on GEC. Expand

We introduce WinoGrande, a large-scale dataset of 44k problems, inspired by the original WSC design, but adjusted to improve both the scale and the hardness of the dataset. Expand

In this paper, we present the first study that investigates the viability of language-based abductive reasoning. Expand

We propose a word recognition model based on a semi-character level recurrent neural network (scRNN). Expand

We propose a neural encoder-decoder model with reinforcement learning for grammatical error correction (GEC). Expand

The field of grammatical error correction (GEC) has grown substantially in recent years, with research directed at both evaluation metrics and improved system performance against those metrics. Expand

We show that reference-less grammaticality metrics correlate very strongly with human judgments and are competitive with the leading reference-based evaluation metrics. Expand

This paper describes the Universal Decompositional Semantics (Decomp) project, which aims to augments Universal Dependencies (UD) data sets with robust, scalable semantic annotations based in linguistic theory. Expand

The GLEU metric was proposed for evaluating grammatical error corrections using n-gram overlap with a set of reference sentences, as opposed to precision/recall. Expand