Challenge: Pretrained language models rely on subword tokenization to process text as a sequence of subwords.
Approach: They propose a character-subword language model that integrates character and subword modalities into one model.
Outcome: The proposed model outperforms its backbone language models on English sequence labeling and classification tasks.

Similar Papers

Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention (N18-1)

Copied to clipboard

Challenge: Neural machine translation models learn to map from source language sentences to target language sentences via continuous-space intermediate representations.
Approach: They propose an encoder with character attention which augments the (sub)word-level representation with character-level information and a decoder with multiple attentions that enable the representations from different levels of granularity to control the translation cooperatively.
Outcome: The proposed model outperforms the standard word-based model, subword-based models, and strong character-based ones on translation tasks.
From Characters to Words: Hierarchical Pre-trained Language Model for Open-vocabulary Language Understanding (2023.acl-long)

Copied to clipboard

Challenge: Current models for natural language understanding require a preprocessing step to convert raw text into discrete tokens.
Approach: They propose a hierarchical open-vocabulary language model that adopts a shallow Transformer architecture to learn word representations from their characters and a deep inter-word Transformer module that contextualizes each word representation by attending to the entire word sequence.
Outcome: The proposed model outperforms baselines on various downstream tasks and is robust to textual corruption and domain shift.
What do tokens know about their characters and how do they know it? (2022.naacl-main)

Copied to clipboard

Challenge: Pre-trained language models that use subword tokenization schemes can succeed at a variety of language tasks that require character-level information.
Approach: They propose to use word tokenization schemes to probe what word pieces encode . they show that larger models can encode character-level information .
Outcome: The proposed models can encode character-level information and perform better on non-Latin alphabets.
From Bytes to Subwords: Challenges of Input Representations in NLP (2026.findings-acl)

Copied to clipboard

Challenge: Traditionally, characters or words have been used, but recently, subwords have become the standard.
Approach: They examine the current use of tokenizers and examine the weaknesses of character normalization . they propose proof of concept alternatives focused on fairness and efficiency .
Outcome: The proposed model is based on a systematic review of current tokenizers and character encodings.
A Systematic Study of Leveraging Subword Information for Learning Word Representations (N19-1)

Copied to clipboard

Challenge: Existing word representation models for morphologically rich languages use subword-level information, but their systematic comparative analysis across typologically diverse languages and tasks is still missing.
Approach: They propose a framework for learning subword-informed word representations that allows for easy experimentation with different segmentation and composition components.
Outcome: The proposed framework allows for easy experimentation with different segmentation and composition components, as well as advanced techniques based on position embeddings and self-attention.
CharBERT: Character-aware Pre-trained Language Model (2020.coling-main)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) construct word representations at subword level with Byte-Pair Encoding (BPE) or its variations . but these methods split a word into subword units and make it incomplete and fragile .
Approach: They propose a character-aware pre-trained language model to tackle OOV problems . they construct contextual word embedding for each token from sequential character representations .
Outcome: The proposed model improves on the existing models on multiple NLP benchmarks.
Bi-Granularity Contrastive Learning for Post-Training in Few-Shot Scene (2021.findings-acl)

Copied to clipboard

Challenge: Existing approaches to fine-tune pre-trained models to downstream tasks are limited by labeled examples.
Approach: They propose to apply post-training on unlabeled task data before fine-tuning by contrastive learning that considers either token-level or sequence-level similarity.
Outcome: Empirical results show that contrastive masked language modeling surpasses other methods in few-shot settings without the need for data augmentation.
Learning Better Internal Structure of Words for Sequence Labeling (D18-1)

Copied to clipboard

Challenge: a gap exists between methods for learning representations of sentences and words . authors propose a convolutional neural architecture with no down-sampling for learning words based on character embeddings .
Approach: They propose a funnel-shaped wide convolutional neural architecture with no down-sampling for learning words' internal structure.
Outcome: The proposed model outperforms other character embedding models on six sequence labeling datasets.
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.
Disentangling Representations of Text by Masking Transformers (2021.emnlp-main)

Copied to clipboard

Challenge: Large pretrained models such as BERT encode a range of features into monolithic vectors, providing strong predictive accuracy across downstream tasks.
Approach: They explore whether it is possible to learn disentangled representations by identifying existing subnetworks within pretrained models that encode distinct, complementary aspects.
Outcome: The proposed method disentangles sentiment from genre in movie reviews, toxicity from dialect in Tweets, and syntax from semantics.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations