Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userWikipedia Entities as Rendezvous across Languages: Grounding Multilingual Language Models by Predicting Wikipedia Hyperlinks
كيانات ويكيبيديا كما rendezvous عبر اللغات: تأريض نماذج لغات متعددة اللغات من خلال التنبؤ برقائق ويكيبيديا
355
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
أصبحت نماذج لغة ملثم بسرعة قياسي فعلي عند معالجة النص. في الآونة الأخيرة، اقترح العديد من الأساليب زيادة إثراء تمثيلات Word مع مصادر المعرفة الخارجية مثل الرسوم البيانية المعرفة. ومع ذلك، يتم وضع هذه النماذج وتقييمها في إعداد أحادي فقط. في هذا العمل، نقترح مهمة تنبؤات كيان مستقلة في اللغة كإجراء تدريب متوسط لتمثيلات الكلمات البرية على دلالات الكيان وجسم الفجوة عبر لغات مختلفة عن طريق المفردات المشتركة للكيانات. نظهر أن نهجنا يضجع بفعالية إلى معرفة جديدة من المعرفة المعجمية في النماذج العصبية، مما يحسن أدائها في مهام دلالية مختلفة في إعداد Croadlingual Zero-Shot. كميزة إضافية، لا يتطلب التدريب الوسيط لدينا أي مدخلات تكميلية، مما يسمح بتطبيق نماذجنا على مجموعات بيانات جديدة على الفور. في تجاربنا، نستخدم مقالات ويكيبيديا تصل إلى 100 لغة وتراقب بالفعل مكاسب متسقة مقارنة مع خطوط الأساس القوية عند التنبؤ بالكيانات باستخدام فقط Wikipedia الإنجليزية. يؤدي إضافة لغات إضافية أخرى إلى تحسينات في معظم المهام حتى نقطة معينة، ولكن عموما وجدنا أنها غير تافهة على تحسين التحسينات في عملية تحويل النموذج عن طريق التدريب على كميات متزايدة من أي وقت مضى لغات ويكيبيديا.
Masked language models have quickly become the de facto standard when processing text. Recently, several approaches have been proposed to further enrich word representations with external knowledge sources such as knowledge graphs. However, these models are devised and evaluated in a monolingual setting only. In this work, we propose a language-independent entity prediction task as an intermediate training procedure to ground word representations on entity semantics and bridge the gap across different languages by means of a shared vocabulary of entities. We show that our approach effectively injects new lexical-semantic knowledge into neural models, improving their performance on different semantic tasks in the zero-shot crosslingual setting. As an additional advantage, our intermediate training does not require any supplementary input, allowing our models to be applied to new datasets right away. In our experiments, we use Wikipedia articles in up to 100 languages and already observe consistent gains compared to strong baselines when predicting entities using only the English Wikipedia. Further adding extra languages lead to improvements in most tasks up to a certain point, but overall we found it non-trivial to scale improvements in model transferability by training on ever increasing amounts of Wikipedia languages.
References used
https://aclanthology.org/
rate research
Read More
How would you explain Bill Gates to a German? He is associated with founding a company in the United States, so perhaps the German founder Carl Benz could stand in for Gates in those contexts. This type of translation is called adaptation in the tran
slation community. Until now, this task has not been done computationally. Automatic adaptation could be used in natural language processing for machine translation and indirectly for generating new question answering datasets and education. We propose two automatic methods and compare them to human results for this novel NLP task. First, a structured knowledge base adapts named entities using their shared properties. Second, vector-arithmetic and orthogonal embedding mappings methods identify better candidates, but at the expense of interpretable features. We evaluate our methods through a new dataset of human adaptations.
We release FoolMeTwice (FM2 for short), a large dataset of challenging entailment pairs collected through a fun multi-player game. Gamification encourages adversarial examples, drastically lowering the number of examples that can be solved using shor
tcuts'' compared to other popular entailment datasets. Players are presented with two tasks. The first task asks the player to write a plausible claim based on the evidence from a Wikipedia page. The second one shows two plausible claims written by other players, one of which is false, and the goal is to identify it before the time runs out. Players pay'' to see clues retrieved from the evidence pool: the more evidence the player needs, the harder the claim. Game-play between motivated players leads to diverse strategies for crafting claims, such as temporal inference and diverting to unrelated evidence, and results in higher quality data for the entailment and evidence retrieval tasks. We open source the dataset and the game code.
This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextual multilingual multimodal embeddings. Under a zero-s
hot setting, we empirically demonstrate that performance degrades significantly when we query the multilingual text-video model with non-English sentences. To address this problem, we introduce a multilingual multimodal pre-training strategy, and collect a new multilingual instructional video dataset (Multi-HowTo100M) for pre-training. Experiments on VTT show that our method significantly improves video search in non-English languages without additional annotations. Furthermore, when multilingual annotations are available, our method outperforms recent baselines by a large margin in multilingual text-to-video search on VTT and VATEX; as well as in multilingual text-to-image search on Multi30K. Our model and Multi-HowTo100M is available at http://github.com/berniebear/Multi-HT100M.
Supervised deep learning-based approaches have been applied to task-oriented dialog and have proven to be effective for limited domain and language applications when a sufficient number of training examples are available. In practice, these approache
s suffer from the drawbacks of domain-driven design and under-resourced languages. Domain and language models are supposed to grow and change as the problem space evolves. On one hand, research on transfer learning has demonstrated the cross-lingual ability of multilingual Transformers-based models to learn semantically rich representations. On the other, in addition to the above approaches, meta-learning have enabled the development of task and language learning algorithms capable of far generalization. Through this context, this article proposes to investigate the cross-lingual transferability of using synergistically few-shot learning with prototypical neural networks and multilingual Transformers-based models. Experiments in natural language understanding tasks on MultiATIS++ corpus shows that our approach substantially improves the observed transfer learning performances between the low and the high resource languages. More generally our approach confirms that the meaningful latent space learned in a given language can be can be generalized to unseen and under-resourced ones using meta-learning.
Pretrained multilingual language models have been shown to work well on many languages for a variety of downstream NLP tasks. However, these models are known to require a lot of training data. This consequently leaves out a huge percentage of the wor
ld's languages as they are under-resourced. Furthermore, a major motivation behind these models is that lower-resource languages benefit from joint training with higher-resource languages. In this work, we challenge this assumption and present the first attempt at training a multilingual language model on only low-resource languages. We show that it is possible to train competitive multilingual language models on less than 1 GB of text. Our model, named AfriBERTa, covers 11 African languages, including the first language model for 4 of these languages. Evaluations on named entity recognition and text classification spanning 10 languages show that our model outperforms mBERT and XLM-Rin several languages and is very competitive overall. Results suggest that our small data'' approach based on similar languages may sometimes work better than joint training on large datasets with high-resource languages. Code, data and models are released at https://github.com/keleog/afriberta.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
