Compositionality of Complex Graphemes in the Undeciphered Proto-Elamite Script using Image and Text Embedding Models (2021.findings-acl)
Copied to clipboard
| Challenge: | a language model over sign images produces more interpretable results than a model over text . a new language model is developed to abstract from human annotators . |
| Approach: | They propose a language modeling architecture which operates over sequences of images or over multimodal sequences with associated labels. |
| Outcome: | The proposed language model can interpret signs in the undeciphered proto-Elamite script . it also provides a novel way to abstract away from biases introduced by human annotators. |
Similar Papers
Grapheme-level Awareness in Word Embeddings for Morphologically Rich Languages (L18-1)
Copied to clipboard
| Challenge: | a study of inflectional and non-alphabetic languages shows word vectors are sparse in data sparsity due to the morphological system of a language and its syllables. |
| Approach: | They propose a grapheme-level coding procedure for neural word embedding that uses syllable characters to represent word-internal features. |
| Outcome: | The proposed model is more capable of representing functional and semantic similarities than syllable-level and word-level models. |
Unicode Normalization and Grapheme Parsing of Indic Languages (2024.lrec-main)
Copied to clipboard
Nazmuddoha Ansary, Quazi Adibur Rahman Adib, Tahsin Reasat, Asif Shahriyar Sushmit, Ahmed Imtiaz Humayun, Sazia Mehnaz, Kanij Fatema, Mohammad Mamun Or Rashid, Farig Sadeque
| Challenge: | Indic writing systems encode words as linear sequences of Unicode characters . authors propose a grapheme parser for Abugida text to normalize inconsistencies . |
| Approach: | They propose a normalizer for normalizing inconsistencies caused by Unicode encoding schemes . grapheme parser for Abugida deconstructs words into visually distinct orthographic syllables . |
| Outcome: | The proposed library is more efficient than the previously used IndicNLP normalizer . it deconstructs words into visually distinct orthographic syllables or complex graphemes . |
Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings (2021.eacl-main)
Copied to clipboard
| Challenge: | Neural network models are difficult to understand and are considered "black boxes". |
| Approach: | They use grapheme–color synesthesia to study character embeddings in English . they compare graphemes to phonemes to find the most human-like character embeds . |
| Outcome: | The results show that grapheme-to-phoneme conversion results in the most human-like character embeddings. |
Seeing Through Words, Speaking Through Pixels: Deep Representational Alignment Between Vision and Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show that deep vision-only and language-only models project inputs into a partially aligned representational space. |
| Approach: | They investigate whether a model's representational code is semantically shared . they find that alignment peaks in mid-to-late layers of both model types . |
| Outcome: | a forced-choice "Pick-a-Pic" task shows human preferences for image-caption matches are mirrored in embedding spaces across vision-language model pairs. |
Does BERT Recognize an Agent? Modeling Dowty’s Proto-Roles with Contextual Embeddings (2022.coling-1)
Copied to clipboard
| Challenge: | Contextual embeddings build multidimensional representations of word tokens based on their context of occurrence. |
| Approach: | They propose to map the verb embeddings to an interpretable space of semantic properties built from a linguistic dataset and test their ability to model the semantic properties of the agent of the verbs participating in the alternation. |
| Outcome: | The proposed models can model the semantic properties of the verbs participating in the so-called causative alternation. |
Quantifying Compositionality of Classic and State-of-the-Art Embeddings (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Static word embeddings make strong claims about compositionality, but the SOTA generative models go too far in the other direction. |
| Approach: | a new study evaluates the compositionality of word embeddings by canonical correlation analysis . strong compositional signals are observed in later training stages across data modalities . |
| Outcome: | a new evaluation of compositional models shows that they exploit access meanings when justified . strong compositional signals are observed in later training stages and in deeper layers of the transformer-based model before a decline at the top layer. |
The Emergence of Compositional Languages in Multi-entity Referential Games: from Image to Graph Representations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Language Emergence research uses jointly trained artificial agents to solve a task. |
| Approach: | They propose a multi-entity game in which targets include multiple entities that are spatially related. |
| Outcome: | The proposed multi-entity game shows that the emergent languages exhibit a considerable degree of compositionality, but not over all features. |
Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Understanding unexplored data is a slow process, and there is no labeled data at hand. |
| Approach: | They propose to use unsupervised methods to reveal rules which cluster unexplored corpus by its prominent categories to help domain experts understand their texts. |
| Outcome: | The proposed rules can be bootstrapped to identify target categories and deepen understanding of the data. |
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. |
What if This Modified That? Syntactic Interventions with Counterfactual Embeddings (2021.findings-acl)
Copied to clipboard
| Challenge: | Prior art aims to uncover meaningful properties within model representations, but it is unclear how faithfully such probes portray information that the models actually use. |
| Approach: | They propose a technique for generating counterfactual embeddings within models . they produce evidence that some models use a tree-distancelike representation of syntax . |
| Outcome: | The proposed technique produces evidence that some models use tree-distancelike representations of syntax in downstream prediction tasks. |