| Challenge: | Existing methods for decipherment of lost languages are limited by limited data and scarce quantities of ancient text. |
| Approach: | They propose a neural approach for automatic decipherment of lost languages . they use an expressive sequence-to-sequence model to capture character-level correspondences between cognates . |
| Outcome: | The proposed approach improves on the decipherment of Ugaritic and Linear B in ancient Greek . the proposed approach is highly customized for a given language pair and does not generalize to other lost languages. |
Similar Papers
Neural Unsupervised Reconstruction of Protolanguage Word Forms (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for reconstructing ancient word forms use expectation-maximization . past work has used this method to predict simple phonological changes . |
| Approach: | They extend expectation-maximization to predict phonological changes between ancient word forms and their cognates in modern languages. |
| Outcome: | The proposed model reduces edit distance from the target word forms compared to previous methods. |
Decipherment of Substitution Ciphers with Neural Language Models (D18-1)
Copied to clipboard
| Challenge: | Existing methods for deciphering homophonic substitution ciphers use pre-trained neural LMs. |
| Approach: | They propose a beam search algorithm that scores the entire candidate plaintext at each step of the decipherment using a neural language model. |
| Outcome: | The proposed beam search algorithm improves on challenging ciphers with smaller beam sizes and better error rates than state-of-the-art methods. |
Deconvolution-Based Global Decoding for Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Existing models for Neural Machine Translation (NMT) use Recurrent Neural Network (RNN) to generate translation word by word following a sequential order. |
| Approach: | They propose a Neural Machine Translation (NMT) model that decodes the sequence with the guidance of its structural prediction of the target-side context. |
| Outcome: | The proposed model is more competitive compared with the state-of-the-art methods and reduces repetition with the instruction from the target-side context for decoding. |
Advancing Regular Language Reasoning in Linear Recurrent Neural Networks (2024.naacl-short)
Copied to clipboard
| Challenge: | Existing linear recurrent neural networks have been used for natural language and long-range modeling for decades. |
| Approach: | They propose a linear recurrent neural network with a block-diagonal transition matrix and a transition matrix for LRNNs. |
| Outcome: | The proposed model is the only one capable of performing length extrapolation on regular language tasks such as Sum, Even Pair, and Modular Arithmetic. |
Minimum Description Length Recurrent Neural Networks (2022.tacl-1)
Copied to clipboard
| Challenge: | We show that neural networks that optimize a minimum description length score master memory challenges and perform addition with 100% accuracy. |
| Approach: | They train neural networks to optimize a Minimum Description Length score . they show that they master tasks involving memory challenges and perform addition . |
| Outcome: | The proposed models master languages and perform addition with 100% accuracy . they show that they can generalize from small training corpora and large training corpus . |
Pushing the Limits of Low-Resource Morphological Inflection (D19-1)
Copied to clipboard
| Challenge: | Recent advances in morphological inflection generation have limited resources . antonisa and colleagues present a battery of improvements to improve performance under low-resource conditions . |
| Approach: | They propose a two-step attention architecture for the inflection decoder that uses two-segments attention and a multi-single-syllabic attention architecture. |
| Outcome: | The proposed model outperforms the state-of-the-art in low-resource languages by 15 percentage points . the proposed model also shows that it can be used to model monolingual data hallucinations . |
Can Sequence-to-Sequence Models Crack Substitution Ciphers? (2021.acl-long)
Copied to clipboard
| Challenge: | Current methods for deciphering historical ciphers use beam search and a neural language model . but, this approach assumes that the target plaintext language is known . |
| Approach: | They propose an end-to-end multilingual decipherment model that can solve 1:1 substitution ciphers without explicit language identification. |
| Outcome: | The proposed model can decipher text without explicit language identification while still being robust to noise. |
Deciphering Undersegmented Ancient Scripts Using Phonetic Prior (2021.tacl-1)
Copied to clipboard
| Challenge: | a number of undeciphered languages are still undecipherated, igniting fierce scientific debate . a recent study shows that NLP methods can successfully decipher lost languages . |
| Approach: | They propose a decipherment model that incorporates phonetic geometry into word segmentation and cognate alignment . they use the International Phonetic Alphabet to learn character embeddings based on historical sound change . |
| Outcome: | The proposed model shows that it can decipher both deciphered and undeciphered languages. |
Neural Machine Translation Models with Back-Translation for the Extremely Low-Resource Indigenous Language Bribri (2020.coling-main)
Copied to clipboard
| Challenge: | a small dataset of 5923 Bribri-Spanish pairs is used to train low-resource NMT models . |
| Approach: | They propose a Chibchan NMT model and dataset with an average performance of BLEU 16.91.7 for Bribri. |
| Outcome: | The proposed model improves on the Bribri dataset by 1.0 BLEU, but only when the new Spanish sentences belong to the same domain as the other Spanish examples. |
Automatic Interlinear Glossing for Under-Resourced Languages Leveraging Translations (2020.coling-main)
Copied to clipboard
| Challenge: | Documentation is not a cure-all for language loss, but it is an important part of language preservation. |
| Approach: | They propose to use multi-source neural models to create automatic glossing models . they also explore cross-lingual transfer and a simple output length control mechanism . |
| Outcome: | The proposed model outperforms state-of-the-art models on low-resource scenarios. |