Related papers: Stronger Baselines for Grammatical Error Correctio…
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…
Currently available grammatical error correction (GEC) datasets are compiled using well-formed written text, limiting the applicability of these datasets to other domains such as informal writing and dialog. In this paper, we present a…
The task of Grammatical Error Correction (GEC) aims to automatically correct grammatical errors in natural texts. Almost all previous works treat annotated training data equally, but inherent discrepancies in data are neglected. In this…
Previously, neural methods in grammatical error correction (GEC) did not reach state-of-the-art results compared to phrase-based statistical machine translation (SMT) baselines. We demonstrate parallels between neural GEC and low-resource…
This work presents a general unsupervised learning method to improve the accuracy of sequence to sequence (seq2seq) models. In our method, the weights of the encoder and decoder of a seq2seq model are initialized with the pretrained weights…
Pretraining sentence encoders with language modeling and related unsupervised tasks has recently been shown to be very effective for language understanding tasks. By supplementing language model-style pretraining with further training on…
Automatic evaluation in grammatical error correction (GEC) is crucial for selecting the best-performing systems. Currently, reference-based metrics are a popular choice, which basically measure the similarity between hypothesis and…
Grammatical error correction (GEC) is the task of correcting typos, spelling, punctuation and grammatical issues in text. Approaching the problem as a sequence-to-sequence task, we compare the use of a common subword unit vocabulary and…
This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning framework, we introduce two pre-training tasks for the…
With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling. However, relying on corrupting the…
The recent development of language models has shown promising results by achieving state-of-the-art performance on various natural language tasks by fine-tuning pretrained models. In task-oriented dialogue (ToD) systems, language models can…
General-purpose pretrained sentence encoders such as BERT are not ideal for real-world conversational AI applications; they are computationally heavy, slow, and expensive to train. We propose ConveRT (Conversational Representations from…
Grammatical feedback is crucial for L2 learners, teachers, and testers. Spoken grammatical error correction (GEC) aims to supply feedback to L2 learners on their use of grammar when speaking. This process usually relies on a cascaded…
Gender bias has been found in existing coreference resolvers. In order to eliminate gender bias, a gender-balanced dataset Gendered Ambiguous Pronouns (GAP) has been released and the best baseline model achieves only 66.9% F1. Bidirectional…
BERT (Bidirectional Encoder Representations from Transformers) has revolutionized the field of natural language processing through its exceptional performance on numerous tasks. Yet, the majority of researchers have mainly concentrated on…
Over the past few decades, Artificial Intelligence(AI) has progressed from the initial machine learning stage to the deep learning stage, and now to the stage of foundational models. Foundational models have the characteristics of…
Lexically constrained text generation aims to control the generated text by incorporating some pre-specified keywords into the output. Previous work injects lexical constraints into the output by controlling the decoding process or refining…
The Transformer architecture deeply changed the natural language processing, outperforming all previous state-of-the-art models. However, well-known Transformer models like BERT, RoBERTa, and GPT-2 require a huge compute budget to create a…
The increasingly large size of modern pretrained language models not only makes them inherit more human-like biases from the training corpora, but also makes it computationally expensive to mitigate such biases. In this paper, we…
We propose a character-based nonautoregressive GEC approach, with automatically generated character transformations. Recently, per-word classification of correction edits has proven an efficient, parallelizable alternative to current…