Multilingual neural machine translation models typically handle one source language at a time.
Additionally, we simply apply red teaming alignment to LLaVA-v1. 5 with Supervised Fine-tuning (SFT) using RTVLM, and this bolsters the models' performance with 10% in RTVLM test set, 13% in MM-Hal, and without noticeable decline in MM-Bench, overpassing other LLaVA-based models with regular alignment data.
Cross-lingual open information extraction aims to extract structured information from raw text across multiple languages.
To tackle these issues, we propose FinPT and FinBench: the former is a novel approach for financial risk prediction that conduct Profile Tuning on large pretrained foundation models, and the latter is a set of high-quality datasets on financial risks such as default, fraud, and churn.
To tackle this challenge and promote research in the vision-language field, we introduce the Multi-Modal, Multilingual Instruction Tuning (M$^3$IT) dataset, designed to optimize VLM alignment with human instructions.
In addition, generative data augmentation (GDA) has been shown to produce more diverse and flexible data.
Context-aware neural machine translation aims to use the document-level context to improve translation quality.
Inspired by the idea of Generative Adversarial Networks (GANs), we propose a GAN-style model for encoder-decoder pre-training by introducing an auxiliary discriminator, unifying the ability of language understanding and generation in a single model.
Specifically, the target sequence is first translated into the source language and then tagged by a source NER model.
Transformer structure, stacked by a sequence of encoder and decoder network layers, achieves significant development in neural machine translation.
Nonetheless, multilingual training is plagued by language interference degeneration in shared parameters because of the negative interference among different translation directions, especially on high-resource languages.
Most translation tasks among languages belong to the zero-resource translation problem where parallel corpora are unavailable.
Few-shot relation learning refers to infer facts for relations with a limited number of observed triples.
Although multilingual neural machine translation (MNMT) enables multiple language translations, the training process is based on independent multilingual objectives.
The task of linking an entity mention in a tweet with its corresponding entity in a heterogeneous information network is of great importance, for the purpose of enriching heterogeneous information networks with the abundant and fresh knowledge embedded in tweets.