Cross-lingual alignments of ELMo contextual embeddings

• URL: http://arxiv.org/abs/2106.15986v1
• Date: Wed, 30 Jun 2021 11:26:43 GMT
• Title: Cross-lingual alignments of ELMo contextual embeddings
• Authors: Matej Ul\v{c}ar and Marko Robnik-\v{S}ikonja
• Abstract summary: Cross-lingual embeddings map word embeddings from a low-resource language to a high-resource language. To produce cross-lingual mappings of recent contextual embeddings, anchor points between the embedding spaces have to be words in the same context. We propose novel cross-lingual mapping methods for ELMo embeddings.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Building machine learning prediction models for a specific NLP task requires sufficient training data, which can be difficult to obtain for low-resource languages. Cross-lingual embeddings map word embeddings from a low-resource language to a high-resource language so that a prediction model trained on data from the high-resource language can also be used in the low-resource language. To produce cross-lingual mappings of recent contextual embeddings, anchor points between the embedding spaces have to be words in the same context. We address this issue with a new method for creating datasets for cross-lingual contextual alignments. Based on that, we propose novel cross-lingual mapping methods for ELMo embeddings. Our linear mapping methods use existing vecmap and MUSE alignments on contextual ELMo embeddings. Our new nonlinear ELMoGAN mapping method is based on GANs and does not assume isomorphic embedding spaces. We evaluate the proposed mapping methods on nine languages, using two downstream tasks, NER and dependency parsing. The ELMoGAN method performs well on the NER task, with low cross-lingual loss compared to direct training on some languages. In the dependency parsing, linear alignment variants are more successful.

Related papers

• Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization [108.6908427615402]
  Cross-lingual summarization ( CLS) aims to generate a summary for the source text in a different target language. Currently, instruction-tuned large language models (LLMs) excel at various English tasks. Recent studies have shown that LLMs' performance on CLS tasks remains unsatisfactory even with few-shot settings.
  arXiv  Detail & Related papers  (2024-10-26T00:39:44Z)
• MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions [54.08017526771947]
  Multilingual Reverse Instructions (MURI) generates high-quality instruction tuning datasets for low-resource languages. MURI produces instruction-output pairs from existing human-written texts in low-resource languages. Our dataset, MURI-IT, includes more than 2 million instruction-output pairs across 200 languages.
  arXiv  Detail & Related papers  (2024-09-19T17:59:20Z)
• MoSECroT: Model Stitching with Static Word Embeddings for Crosslingual Zero-shot Transfer [50.40191599304911]
  We introduce MoSECroT Model Stitching with Static Word Embeddings for Crosslingual Zero-shot Transfer. In this paper, we present the first framework that leverages relative representations to construct a common space for the embeddings of a source language PLM and the static word embeddings of a target language. We show that although our proposed framework is competitive with weak baselines when addressing MoSECroT, it fails to achieve competitive results compared with some strong baselines.
  arXiv  Detail & Related papers  (2024-01-09T21:09:07Z)
• ProMap: Effective Bilingual Lexicon Induction via Language Model Prompting [22.743097175747575]
  We introduce ProMap, a novel approach for bilingual induction (BLI) ProMap relies on an effective padded prompting of language models with a seed dictionary that achieves good performance when used independently. When evaluated on both rich-resource and low-resource languages, ProMap consistently achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2023-10-28T18:33:24Z)
• Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition [31.575930914290762]
  Exploiting cross-lingual resources is an effective way to compensate for data scarcity of low resource languages. We extend the concept of learnable cross-lingual mappings for end-to-end speech recognition. The results show that any source language ASR model can be used for a low-resource target language recognition.
  arXiv  Detail & Related papers  (2023-06-14T15:24:31Z)
• Isomorphic Cross-lingual Embeddings for Low-Resource Languages [1.5076964620370268]
  Cross-Lingual Word Embeddings (CLWEs) are a key component to transfer linguistic information learnt from higher-resource settings into lower-resource ones. We introduce a framework to learn CLWEs, without assuming isometry, for low-resource pairs via joint exploitation of a related higher-resource language. We show consistent gains over current methods in both quality and degree of isomorphism, as measured by bilingual lexicon induction (BLI) and eigenvalue similarity respectively.
  arXiv  Detail & Related papers  (2022-03-28T10:39:07Z)
• UNKs Everywhere: Adapting Multilingual Language Models to New Scripts [103.79021395138423]
  Massively multilingual language models such as multilingual BERT (mBERT) and XLM-R offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. Due to their limited capacity and large differences in pretraining data, there is a profound performance gap between resource-rich and resource-poor target languages. We propose novel data-efficient methods that enable quick and effective adaptation of pretrained multilingual models to such low-resource languages and unseen scripts.
  arXiv  Detail & Related papers  (2020-12-31T11:37:28Z)
• Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model [58.27176041092891]
  Recent research indicates that pretraining cross-lingual language models on large-scale unlabeled texts yields significant performance improvements. We propose a novel unsupervised feature decomposition method that can automatically extract domain-specific features from the entangled pretrained cross-lingual representations. Our proposed model leverages mutual information estimation to decompose the representations computed by a cross-lingual model into domain-invariant and domain-specific parts.
  arXiv  Detail & Related papers  (2020-11-23T16:00:42Z)
• Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel Corpora [63.5286019659504]
  We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus. Our method obtains word embeddings via an LSTM encoder-decoder model that simultaneously translates and reconstructs an input sentence.
  arXiv  Detail & Related papers  (2020-10-27T22:24:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.