| Challenge: | Word embeddings have been successfully trained in many languages, but evaluations in lesser-resourced languages have been cursory and highly variable. |
| Approach: | They propose to build a word embedding model suitable for the Semitic language of Amharic (Ethiopia) it is morphologically rich and written as an alphasyllabary rather than an alphabet . |
| Outcome: | The proposed model performs on word analogy tasks on the Semitic language of Amharic (Ethiopia) it is morphologically rich and written as an alphasyllabary rather than an alphabet . |
Similar Papers
Morphology-Aware Meta-Embeddings for Tamil (2021.naacl-srw)
Copied to clipboard
| Challenge: | In this work, we focus on producing morphologically enhanced word embeddings for Tamil, a highly agglutinative South Indian language with rich morphology that remains low-resource with regards to NLP tasks. |
| Approach: | They present a first-ever word analogy dataset for Tamil using a rules-based segmenter and meta-embedding techniques. |
| Outcome: | The proposed embeddings outperform baselines on the word analogy task by 16% and appear to mitigate a trade-off between semantic and morphological accuracy. |
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. |
Evaluating Word Embeddings in Extremely Under-Resourced Languages: A Case Study in Bribri (2022.coling-1)
Copied to clipboard
| Challenge: | a case study of word embeddings in an under-resourced context is presented . Embeddings are critical for many NLP tasks, but their evaluation in actual under-sourced settings needs further investigation. |
| Approach: | They adapt word embeddings to an under-resourced indigenous language in Bribri . they find that the best models find the appropriate semantic target 60% of the time . |
| Outcome: | The proposed models were adapted to an under-resourced English language . the best models found the appropriate semantic target 60% of the time . |
Evaluating Performance of Pre-trained Word Embeddings on Assamese, a Low-resource Language (2024.lrec-main)
Copied to clipboard
| Challenge: | Word embeddings are not explored in high-resource languages such as Assamese, where resources are limited. |
| Approach: | They propose to use assamese pre-trained word embeddings for sequence labeling tasks such as Parts-of-speech and Named Entity Recognition to evaluate their performance. |
| Outcome: | The proposed embeddings outperform the existing methods on Parts-of-speech and Named Entity Recognition tasks. |
Do Pretrained Contextual Language Models Distinguish between Hebrew Homograph Analyses? (2023.eacl-main)
Copied to clipboard
| Challenge: | Semitic morphologically-rich languages are characterized by extreme word ambiguity . many of the words are homographs with multiple possible analyses . |
| Approach: | They evaluate existing models for Hebrew homographs using word-piece embeddings . they find they are more effective when the number of word-part splits is limited . |
| Outcome: | The proposed models outperform non-contextualized embeddings on Hebrew homograph challenge sets. |
Addressing Noise in Multidialectal Word Embeddings (P18-2)
Copied to clipboard
| Challenge: | Dialectal Arabic (DA) is problematically noisy and lacks a large corpus of non-noisy words. |
| Approach: | They propose to use word embedding tools to maximize the informative content leveraged in each training sentence and analyze methods for representing disparate dialects in one embeddable space. |
| Outcome: | The proposed methods improve performance on low and high frequency words while preserving accuracy on low frequency forms. |
Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for multilingual and cross-lingual retrieval are lacking in low-resource, morphologically rich languages such as Amharic. |
| Approach: | They propose to train Amharic-specific dense retrieval models based on pre-trained Amharican BERT and RoBERTa backbones. |
| Outcome: | The proposed model achieves 17.6% improvement in MRR@10 and 9.86% gain in Recall@10 over the strongest multilingual baseline, Arctic Embed 2.0. |
Toward Qualitative Evaluation of Embeddings for Arabic Sentiment Analysis (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing studies on Arabic sentiment analysis (SA) tasks focus on word embeddings to capture semantic and syntactic similarities, but Arabic language is characterized by its agglutination and morphological richness contributing to great sparsity. |
| Approach: | They propose several protocols to evaluate specific embeddings for Arabic sentiment analysis task. |
| Outcome: | The proposed embeddings are based on words and lemmas in Arabic sentiment analysis (SA) task. |
Show Some Love to Your n-grams: A Bit of Progress and Stronger n-gram Language Modeling Baselines (N19-1)
Copied to clipboard
| Challenge: | Experimental results show that standalone n-gram models lend themselves as natural choices for resource-lean or morphologically rich languages. |
| Approach: | They run experiments on 50 languages covering all morphological language families to compare n-gram models with lstm models. |
| Outcome: | The proposed extension outperforms an lstm language model on 42 languages while its extension which explicitly injects linguistic knowledge outperformed the character-aware neural model on 8 languages. |
Embedding Recycling for Language Models (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies on embedding recycling have not adequately account for overhead costs. |
| Approach: | They propose to reuse contextualized embeddings from previous runs to speed training and inference of future ones. |
| Outcome: | The proposed technique speeds training and inference with no impact on accuracy. |