Character Jacobian: Modeling Chinese Character Meanings with Deep Learning Model (2022.coling-1)
Copied to clipboard
| Challenge: | Compounding is a prevalent word-formation process in Chinese morphology, where each character is bound and free when treated as a morpheme. |
| Approach: | They propose a model that learns non-linear relations between constituents and words and a character Jacobians model that describes character’s role in each word. |
| Outcome: | The proposed model predicts embeddings of real words from constituents but helps account for behavioral data of pseudowords. |
Similar Papers
VCWE: Visual Character-Enhanced Word Embeddings (N19-1)
Copied to clipboard
| Challenge: | Currently, word embeddings are playing a pivotal role in many natural language processing tasks. |
| Approach: | They propose a model to learn Chinese word embeddings via three-level composition . they use convolutional neural network to extract intra-character compositionality from character shape . |
| Outcome: | The proposed model performs better on word similarity, sentiment analysis, named entity recognition and part-of-speech tagging tasks. |
Deep Generative Model for Joint Alignment and Word Representation (N18-1)
Copied to clipboard
| Challenge: | EmbedAlign model embeds words in their complete observed context and learns by marginalisation of latent lexical alignments. |
| Approach: | They exploit translation as a distributional context and embed words as posterior probability densities, rather than point estimates, which allows them to compare words in context using a measure of overlap between distributions. |
| Outcome: | The proposed model performs on a range of lexical semantics tasks and achieves competitive results on benchmarks including natural language inference, paraphrasing, and text similarity. |
Sub-Character Tokenization for Chinese Pretrained Language Models (2023.tacl-1)
Copied to clipboard
Chenglei Si, Zhengyan Zhang, Yingfa Chen, Fanchao Qi, Xiaozhi Wang, Zhiyuan Liu, Yasheng Wang, Qun Liu, Maosong Sun
| Challenge: | Existing tokenization methods for Chinese PLMs treat each character as an indivisible token, but ignore the unique feature of the writing system where additional linguistic information exists below the character level. |
| Approach: | They propose to encode Chinese characters into short sequences and construct Chinese vocabulary based on the encoded text. |
| Outcome: | The proposed tokenizers can tokenize inputs into much shorter sequences, improving computational efficiency. |
The Strawberry Problem: Emergence of Character-level Understanding in Tokenized Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models fail at simple character-level tasks due to low mutual information, study finds . authors propose a lightweight architectural modification that improves character- level reasoning . |
| Approach: | They propose a lightweight architectural modification that improves character-level reasoning while preserving the inductive advantages of subword models. |
| Outcome: | The proposed model improves character-level reasoning while preserving the advantages of subword models. |
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. |
How Do Language Models Acquire Character-Level Information? (2026.eacl-long)
Copied to clipboard
| Challenge: | Language models (LMs) implicitly encode character-level information, despite not being explicitly provided during training. |
| Approach: | They analyze how language models acquire character-level knowledge by comparing them to standard settings. |
| Outcome: | The results show that LMs do not treat words as opaque tokens, but instead treat them as tokens. |
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. |
Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens (2022.naacl-main)
Copied to clipboard
| Challenge: | Standard pre-trained language models do not see the characters that compose each token's string representation. |
| Approach: | They probe the embedding layer of pretrained language models and show that models learn the internal character composition of whole word and subword tokens without seeing the characters coupled with the tokens. |
| Outcome: | The embedding layers of RoBERTa and GPT2 hold enough information to accurately spell up to a third of the vocabulary and reach high character ngram overlap across all token types. |
A Deep Factorization of Style and Structure in Fonts (D19-1)
Copied to clipboard
| Challenge: | Using a variational inference procedure, we factor each training glyph into a combination of a character-specific content embedding and a latent font-specific style variable. |
| Approach: | They propose a deep factorization model that disentangles content from style by factorizing each training glyph into a latent content embedding and a learned embeddable character. |
| Outcome: | The proposed model outperforms a strong nearest neighbors baseline and state-of-the-art discriminative model on reconstructing missing glyphs from an unknown font given only a small number of observations. |
Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition Generation (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing definition generation methods take the source word as an indecomposable semantic unit, but in parataxis languages like Chinese, word meanings can be composed using the word formation process. |
| Approach: | They propose to use word formation features to enhance Definition Generation (DG) in Chinese to generate an explanatory text. |
| Outcome: | The proposed model enhances Definition Generation (DG) in Chinese by decomposing the word meaning into different semantic components. |