1 |
AUTOLEX: An Automatic Framework for Linguistic Exploration ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
SD-QA: Spoken Dialectal Question Answering for the Real World ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Machine Translation into Low-resource Language Varieties ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Code to Comment Translation: A Comparative Study on Model Effectiveness & Errors ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Systematic Inequalities in Language Technology Performance across the World's Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Towards More Equitable Question Answering Systems: How Much More Data Do You Need? ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Cross-Lingual Text Classification of Transliterated Hindi and Malayalam ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Evaluating the Morphosyntactic Well-formedness of Generated Texts ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Lexically Aware Semi-Supervised Learning for OCR Post-Correction ...
|
|
|
|
Abstract:
Much of the existing linguistic data in many languages of the world is locked away in non-digitized books and documents. Optical character recognition (OCR) can be used to produce digitized text, and previous work has demonstrated the utility of neural post-correction methods that improve the results of general-purpose OCR systems on recognition of less-well-resourced languages. However, these methods rely on manually curated post-correction data, which are relatively scarce compared to the non-annotated raw images that need to be digitized. In this paper, we present a semi-supervised learning method that makes it possible to utilize these raw images to improve performance, specifically through the use of self-training, a technique where a model is iteratively trained on its own outputs. In addition, to enforce consistency in the recognized vocabulary, we introduce a lexically-aware decoding method that augments the neural post-correction model with a count-based language model constructed from the ... : Accepted to the Transactions of the Association for Computational Linguistics (TACL) ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2111.02622 https://dx.doi.org/10.48550/arxiv.2111.02622
|
|
BASE
|
|
Hide details
|
|
13 |
When is Wall a Pared and when a Muro? -- Extracting Rules Governing Lexical Selection ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Towards Minimal Supervision BERT-based Grammar Error Correction ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
It's not a Non-Issue: Negation as a Source of Error in Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Automatic Extraction of Rules Governing Morphological Agreement ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
A Summary of the First Workshop on Language Technology for Language Documentation and Revitalization ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Universal Phone Recognition with a Multilingual Allophone System ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|