Related papers: Spelling Correction with Denoising Transformer
The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or…
Fine-tuning is the de facto way to leverage large pretrained language models to perform downstream tasks. However, it modifies all the language model parameters and therefore necessitates storing a full copy for each task. In this paper, we…
The problem of categorizing short speech sentences according to their semantic features with high accuracy is a subject studied in natural language processing. In this study, a data set created with samples classified in 46 different…
This paper presents a new approach to the problem of correcting speech recognition errors by means of post-editing. It consists of using a neural sequence tagger that learns how to correct an ASR (Automatic Speech Recognition) hypothesis…
Handwritten Text Recognition (HTR) is still a challenging problem because it must deal with two important difficulties: the variability among writing styles, and the scarcity of labelled data. To alleviate such problems, synthetic data…
Handwriting recognition is a challenging and critical problem in the fields of pattern recognition and machine learning, with applications spanning a wide range of domains. In this paper, we focus on the specific issue of recognizing…
One of the strongest signals for automated matching of ontologies and knowledge graphs are the textual descriptions of the concepts. The methods that are typically applied (such as character- or token-based comparisons) are relatively…
Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-tuning stages. However, fine-tuning a pre-trained debiased…
Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to transform biased model outputs (or original texts) into more…
Lexical substitution (LS) aims at finding appropriate substitutes for a target word in a sentence. Recently, LS methods based on pretrained language models have made remarkable progress, generating potential substitutes for a target word…
We present a new method for automatically providing feedback for introductory programming problems. In order to use this method, we need a reference implementation of the assignment, and an error model consisting of potential corrections to…
In this paper, we introduce a novel natural language generation task, termed as text morphing, which targets at generating the intermediate sentences that are fluency and smooth with the two input sentences. We propose the Morphing Networks…
Speech synthesis is the artificial production of human speech. A typical text-to-speech system converts a language text into a waveform. There exist many English TTS systems that produce mature, natural, and human-like speech synthesizers.…
Scheduled sampling is a technique for avoiding one of the known problems in sequence-to-sequence generation: exposure bias. It consists of feeding the model a mix of the teacher forced embeddings and the model predictions from the previous…
This work proposes a simple training-free prompt-free approach to leverage large language models (LLMs) for the Chinese spelling correction (CSC) task, which is totally different from all previous CSC approaches. The key idea is to use an…
Text classification has become widely used in various natural language processing applications like sentiment analysis. Current applications often use large transformer-based language models to classify input texts. However, there is a lack…
Quality of data plays an important role in most deep learning tasks. In the speech community, transcription of speech recording is indispensable. Since the transcription is usually generated artificially, automatically finding errors in…
Spelling correction is one of the main tasks in the field of Natural Language Processing. Contrary to common spelling errors, real-word errors cannot be detected by conventional spelling correction methods. The real-word correction model…
Attribute-controlled text rewriting, also known as text style-transfer, has a crucial role in regulating attributes and biases of textual training data and a machine generated text. In this work we present SimpleStyle, a minimalist yet…
Human language is a combination of elemental languages/domains/styles that change across and sometimes within discourses. Language models, which play a crucial role in speech recognizers and machine translation systems, are particularly…