| Challenge: | Pre-trained contextual language models have improved performance of many NLP tasks. |
| Approach: | They propose to use a pre-trained language model to perform lexical normalisation without UGC resources. |
| Outcome: | The proposed model can perform lexical normalisation without the need for training sentences and 3,000 tokens. |
Similar Papers
Benefits of Data Augmentation for NMT-based Text Normalization of User-Generated Content (D19-55)
Copied to clipboard
| Challenge: | Social media texts are considered important language resources for several NLP tasks, but their use of non-standard words makes it difficult to process and analyze UGC. |
| Approach: | They propose to use a Neural Machine Translation approach to normalize lexical variants to their canonical forms to overcome performance drop in UGC. |
| Outcome: | The proposed approach overcomes a data bottleneck in Dutch, a low-resource language. |
Synthetic Data for English Lexical Normalization: How Close Can We Get to Manually Annotated Data? (2020.lrec-1)
Copied to clipboard
| Challenge: | Social media data is a valuable data resource for natural language processing tasks. |
| Approach: | They propose to adapt input text to a more standard form, a task also referred to as normalization. |
| Outcome: | The proposed system scores 94.29 accuracy on the test data compared to 95.22 when trained on human-annotated data. |
Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task (2022.findings-acl)
Copied to clipboard
| Challenge: | lexically-independent subject-verb number agreement (NA) is performed by transformer-based neural language models (NLMs) . but when as little as one attractor is present, the model fails to perform lexical generalization . |
| Approach: | They propose to disrupt lexical patterns found in naturally occurring stimuli for each targeted structure in a novel fine-grained analysis of BERT's behavior. |
| Outcome: | The proposed model generalizes well for simple templates, but fails to perform lexically-independent generalization when as little as one attractor is present. |
Phonetic Normalization for Machine Translation of User Generated Content (D19-55)
Copied to clipboard
| Challenge: | a method to correct noisy User Generated Content (UGC) in French is proposed . it leverages on the existence of UGC specific noise due to the misuse of words with similar pronunciations. |
| Approach: | They propose a phonetizer-based method to correct noisy User Generated Content (UGC) they use phonetic similarity to generate IPA pronunciations of words . |
| Outcome: | The proposed method improves translation quality of noisy User Generated Content (UGC) in french. |
BERTGen: Multi-task Generation through BERT (2021.acl-long)
Copied to clipboard
| Challenge: | Recent work in unsupervised and self-supervised pre-training has revolutionised the field of natural language understanding (NLU). |
| Approach: | They propose to use multimodal and multilingual pre-trained models to extend BERT by fusing them together for language generation tasks. |
| Outcome: | The proposed model outperforms baseline models in image captioning, machine translation and multimodal machine translation tasks and is competitive with supervised counterparts. |
Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration (2021.emnlp-main)
Copied to clipboard
| Challenge: | Phrase representations derived from pretrained language models often lack lexical similarity to determine semantic relatedness. |
| Approach: | They propose a contrastive fine-tuning objective that enables BERT to produce more powerful phrase embeddings by fine- tuning a dataset of diverse phrasal paraphrases and a large-scale dataset of phrases in context. |
| Outcome: | The proposed model outperforms baseline models across phrase-level similarity tasks while also showing increased lexical diversity between nearest neighbors in the vector space. |
On the Sentence Embeddings from Pre-trained Language Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained contextual representations like BERT have been widely used for NLP tasks. |
| Approach: | They propose to transform anisotropic sentence embedding distribution to smooth and isotropic Gaussian distribution by normalizing flows that are learned with an unsupervised objective. |
| Outcome: | The proposed method achieves significant performance gains over state-of-the-art embeddings on a variety of semantic textual similarity tasks. |
BERTwich: Extending BERT’s Capabilities to Model Dialectal and Noisy Text (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models like BERT deteriorate in the face of dialect variation or noise. |
| Approach: | They propose to sandwich BERT's encoder stack between additional encoder layers trained to perform masked language modeling on noisy text. |
| Outcome: | The proposed approach promotes zero-shot transfer to dialectal text and reduces embedding space between words and noisy counterparts. |
What is the best recipe for character-level encoder-only modelling? (2023.acl-long)
Copied to clipboard
| Challenge: | aims to benchmark recent progress in language understanding models that output contextualised representations at the character level. |
| Approach: | They aim to find the best way to build and train character-level BERT-like models by comparing architectural innovations with pretraining objectives. |
| Outcome: | The proposed model outperforms a token-based model on a set of evaluation tasks with a fixed training procedure. |
BERT-based Lexical Substitution (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to lexical substitution tend to overlook good substitute candidates that are not the synonyms of the target words in the lexicals and fail to take into account the substitution’s influence on the global context of the sentence. |
| Approach: | They propose an end-to-end BERT-based lexical substitution approach which proposes and validates substitute candidates without using annotated data or manually curated resources. |
| Outcome: | The proposed approach performs well in proposing and ranking substitute candidates, achieving the state-of-the-art results in both LS07 and LS14 benchmarks. |