Learning to Recognize Dialect Features (2021.naacl-main)

Copied to clipboard

Challenge: linguistics do not characterize dialects as simple categories, but as collections of correlated features.
Approach: They propose two multitask learning approaches based on pretrained transformers to detect dialect features in speech and text.
Outcome: The proposed models learn to recognize many features with high accuracy on 22 dialect features of Indian English.

Similar Papers

Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers (2024.naacl-short)

Copied to clipboard

Challenge: Identifying linguistic differences between dialects of a language often requires expert knowledge and meticulous human analysis.
Approach: They propose a method to extract distinguishing lexical features of dialects by utilizing interpretable dialect classifiers in the absence of human experts.
Outcome: The proposed method extracts key language-specific lexical features that contribute to dialectal variations.
Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness (2024.findings-acl)

Copied to clipboard

Challenge: Existing studies have studied dialect-related fairness for aspects like hate speech, but other aspects of biased language remain unexplored.
Approach: They propose a multitask learning approach that models dialect language as an auxiliary task to incorporate syntactic and lexical variations.
Outcome: The proposed approach improves dialect learning and detects biases more reliably.
Adversarial Multitask Learning for Joint Multi-Feature and Multi-Dialect Morphological Modeling (P19-1)

Copied to clipboard

Challenge: Morphological tagging is challenging for morphologically rich languages due to the large combined target space and the need for more training data to minimize model sparsity.
Approach: They propose to use multitask learning and adversarial training to address morphological richness and dialectal variations in the context of full morphology.
Outcome: The proposed model achieves state-of-the-art for two dialectal variants: Modern Standard Arabic (high-resource “dialect”) and Egyptian Arabic (low-resourced dialect).
Quantifying the Dialect Gap and its Correlates Across Languages (2023.findings-emnlp)

Copied to clipboard

Challenge: Historically, studies investigating minority variants of languages have been limited to a select few languages.
Approach: They evaluate state-of-the-art large language models for regional dialects of several high- and low-resource languages and analyze how regional dialect gap is correlated with economic, social, and linguistic factors.
Outcome: The proposed model is compared with two high-use applications and shows that it can solve the regional dialect gap.
Spanish Dialect Classification: A Comparative Study of Linguistically Tailored Features, Unigrams and BERT Embeddings (2025.acl-srw)

Copied to clipboard

Challenge: Existing models for automatic dialect classification use bag-of-words unigram features instead of linguistic knowledge.
Approach: They propose to use dialect-specific unigram features to train machine learning models . they also use a transformer-based model to find potentially useful dialect-related features .
Outcome: The proposed model outperforms existing models but sacrifices explainability and interpretability.
Task-Agnostic Low-Rank Adapters for Unseen English Dialects (2023.emnlp-main)

Copied to clipboard

Challenge: a recent study found that LLMs are trained on corpora disproportionally weighted in favor of Standard American English . prior work on dialect struggle with generalizing to evolving and emerging dialects in a scalable manner.
Approach: They propose a method that leverages linguistic knowledge to enable resource-efficient adaptation . their method disentangles dialect-specific and cross-dialectal information .
Outcome: a new method improves generalization to unseen dialects in a task-agnostic fashion . it achieves the best or most competitive performance across 5 dialects .
A Checkpoint on Multilingual Misogyny Identification (2022.acl-srw)

Copied to clipboard

Challenge: a study on hate speech against minorities in Italian tweets found that 1 women are the most targeted group.
Approach: They propose to train monolingual transformers and multilingual transformer models with monolingual data in English, Italian, and Spanish to detect misogyny in tweets.
Outcome: The proposed model achieves state-of-the-art on English, Italian, and Spanish.
Creating dialect sub-corpora by clustering: a case in Japanese for an adaptive method (L18-1)

Copied to clipboard

Challenge: a mixed corpus composed of different dialects is sufficiently resourced to cluster them into dialects.
Approach: They propose a pipeline to derive clusters of dialects from a mixed corpus when their standard counterpart is sufficiently resourced.
Outcome: The proposed pipeline can identify dialectal content when its standard counterpart is sufficiently resourced and can then cluster it into four dialects.
Joint Learning of Syntactic Features Helps Discourse Segmentation (2020.lrec-1)

Copied to clipboard

Challenge: Discourse segmentation is a task of fragmenting text into minimal disjoint chunks of text called Elementary Discourse Units (EDUs).
Approach: They propose a framework for multi-lingual discourse segmentation with BERT . they cast the problem as a token classification problem and jointly learn syntactic features like part-of-speech tags and dependency relations.
Outcome: Experiments in English, Dutch, German, Portuguese Brazilian and Basque show that the proposed model performs better across languages.
Dialect Clustering with Character-Based Metrics: in Search of the Boundary of Language and Dialect (2020.lrec-1)

Copied to clipboard

Challenge: 'A language is a dialect with an army and navy' is attributed to sociologist Max Weinrich.
Approach: They propose a universal character-based method for representing sentences so that one can calculate the distance between any two sentence pairs.
Outcome: The proposed method can be used to calculate distance between two sentences by clustering a dialect/sub-language mixed corpus into sub-groups and to partially answer the question of what separates languages from dialects.

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