DOCmT5: Document-Level Pretraining of Multilingual Language Models

• URL: http://arxiv.org/abs/2112.08709v1
• Date: Thu, 16 Dec 2021 08:58:52 GMT
• Title: DOCmT5: Document-Level Pretraining of Multilingual Language Models
• Authors: Chia-Hsuan Lee, Aditya Siddhant, Viresh Ratnakar, Melvin Johnson
• Abstract summary: We introduce DOCmT5, a multilingual sequence-to-sequence language model pre-trained with large scale parallel documents. We propose a simple and effective pre-training objective - Document Reordering Machine Translation. DrMT brings consistent improvements over strong baselines on a variety of document-level generation tasks.
• Score: 9.072507490639218
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this paper, we introduce DOCmT5, a multilingual sequence-to-sequence language model pre-trained with large scale parallel documents. While previous approaches have focused on leveraging sentence-level parallel data, we try to build a general-purpose pre-trained model that can understand and generate long documents. We propose a simple and effective pre-training objective - Document Reordering Machine Translation (DrMT), in which the input documents that are shuffled and masked need to be translated. DrMT brings consistent improvements over strong baselines on a variety of document-level generation tasks, including over 12 BLEU points for seen-language-pair document-level MT, over 7 BLEU points for unseen-language-pair document-level MT and over 3 ROUGE-1 points for seen-language-pair cross-lingual summarization. We achieve state-of-the-art (SOTA) on WMT20 De-En and IWSLT15 Zh-En document translation tasks. We also conduct extensive analysis on various factors for document pre-training, including (1) the effects of pre-training data quality and (2) The effects of combining mono-lingual and cross-lingual pre-training. We plan to make our model checkpoints publicly available.

Related papers

• In-context Pretraining: Language Modeling Beyond Document Boundaries [137.53145699439898]
  In-Context Pretraining is a new approach where language models are pretrained on a sequence of related documents. We introduce approximate algorithms for finding related documents with efficient nearest neighbor search. We see notable improvements in tasks that require more complex contextual reasoning.
  arXiv  Detail & Related papers  (2023-10-16T17:57:12Z)
• Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering [49.85790367128085]
  We pre-training a generic multi-document model from a novel cross-document question answering pre-training objective. This novel multi-document QA formulation directs the model to better recover cross-text informational relations. Unlike prior multi-document models that focus on either classification or summarization tasks, our pre-training objective formulation enables the model to perform tasks that involve both short text generation and long text generation.
  arXiv  Detail & Related papers  (2023-05-24T17:48:40Z)
• A General-Purpose Multilingual Document Encoder [9.868221447090855]
  We pretrain a massively multilingual document encoder as a hierarchical transformer model (HMDE) We leverage Wikipedia as a readily available source of comparable documents for creating training data. We evaluate the effectiveness of HMDE in two arguably most common and prominent cross-lingual document-level tasks.
  arXiv  Detail & Related papers  (2023-05-11T17:55:45Z)
• Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval [87.11836738011007]
  We propose a multilingual multilingual language model called masked sentence model (MSM) MSM consists of a sentence encoder to generate the sentence representations, and a document encoder applied to a sequence of sentence vectors from a document. To train the model, we propose a masked sentence prediction task, which masks and predicts the sentence vector via a hierarchical contrastive loss with sampled negatives.
  arXiv  Detail & Related papers  (2023-02-03T09:54:27Z)
• Advancing Multilingual Pre-training: TRIP Triangular Document-level Pre-training for Multilingual Language Models [107.83158521848372]
  We present textbfTriangular Document-level textbfPre-training (textbfTRIP), which is the first in the field to accelerate the conventional monolingual and bilingual objectives into a trilingual objective with a novel method called Grafting. TRIP achieves several strong state-of-the-art (SOTA) scores on three multilingual document-level machine translation benchmarks and one cross-lingual abstractive summarization benchmark, including consistent improvements by up to 3.11 d-BLEU points and 8.9 ROUGE-L points.
  arXiv  Detail & Related papers  (2022-12-15T12:14:25Z)
• Bridging Cross-Lingual Gaps During Leveraging the Multilingual Sequence-to-Sequence Pretraining for Text Generation [80.16548523140025]
  We extend the vanilla pretrain-finetune pipeline with extra code-switching restore task to bridge the gap between the pretrain and finetune stages. Our approach could narrow the cross-lingual sentence representation distance and improve low-frequency word translation with trivial computational cost.
  arXiv  Detail & Related papers  (2022-04-16T16:08:38Z)
• Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents [19.59133362105703]
  Document-level neural machine translation (DocNMT) delivers coherent translations by incorporating cross-sentence context. We study whether and how contextual modeling in DocNMT is transferable from sentences to documents in a zero-shot fashion.
  arXiv  Detail & Related papers  (2021-09-21T17:49:34Z)
• MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer [13.24356999779404]
  We introduce MULTI-EURLEX, a new multilingual dataset for topic classification of legal documents. The dataset comprises 65k European Union (EU) laws, officially translated in 23 languages, annotated with multiple labels from the EUROVOC taxonomy. We use the dataset as a testbed for zero-shot cross-lingual transfer, where we exploit annotated training documents in one language (source) to classify documents in another language (target)
  arXiv  Detail & Related papers  (2021-09-02T12:52:55Z)
• LAWDR: Language-Agnostic Weighted Document Representations from Pre-trained Models [8.745407715423992]
  Cross-lingual document representations enable language understanding in multilingual contexts. Large pre-trained language models such as BERT, XLM and XLM-RoBERTa have achieved great success when fine-tuned on sentence-level downstream tasks.
  arXiv  Detail & Related papers  (2021-06-07T07:14:00Z)
• Scalable Cross-lingual Document Similarity through Language-specific Concept Hierarchies [0.0]
  This paper presents an unsupervised document similarity algorithm that does not require parallel or comparable corpora. The algorithm annotates topics automatically created from documents in a single language with cross-lingual labels. Experiments performed on the English, Spanish and French editions of JCR-Acquis corpora reveal promising results on classifying and sorting documents by similar content.
  arXiv  Detail & Related papers  (2020-12-15T10:42:40Z)
• Pre-training via Paraphrasing [96.79972492585112]
  We introduce MARGE, a pre-trained sequence-to-sequence model learned with an unsupervised multi-lingual paraphrasing objective. We show it is possible to jointly learn to do retrieval and reconstruction, given only a random initialization. For example, with no additional task-specific training we achieve BLEU scores of up to 35.8 for document translation.
  arXiv  Detail & Related papers  (2020-06-26T14:43:43Z)

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.