Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userInfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training
INFOXLM: إطار معلومات نظرية لنموذج اللغة عبر اللغات قبل التدريب
213
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذا العمل، نقدم إطارا نظريا للمعلومات يقوم بتصوير نموذج اللغة عبر اللغات قبل تعظيم المعلومات المتبادلة بين النصوص متعددة اللغات متعددة التحبيب.العرض الموحد يساعدنا على فهم الأساليب الموجودة بشكل أفضل لتعلم تمثيلات عبر اللغات.الأهم من ذلك، مستوحاة من الإطار، نقترح مهمة جديدة قبل التدريب على التعلم المتعاقل.على وجه التحديد، نعتبر زوج جملة ثنائية اللغة كأراضتين لنفس المعنى وتشجيع تمثيلاتها المشفرة أكثر مماثلة من الأمثلة السلبية.من خلال الاستفادة من كل من Corpora Monolingual والمتوازي، فإننا ندرب بشكل مشترك مهام ذريعة التحسين القدرة على التحويل المتبادلة للنماذج المدربة مسبقا.النتائج التجريبية على العديد من المعايير تظهر أن نهجنا يحقق أداء أفضل بكثير.تتوفر الكود والنماذج المدربة مسبقا في https://aka.ms/infoxlm.
In this work, we present an information-theoretic framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts. The unified view helps us to better understand the existing methods for learning cross-lingual representations. More importantly, inspired by the framework, we propose a new pre-training task based on contrastive learning. Specifically, we regard a bilingual sentence pair as two views of the same meaning and encourage their encoded representations to be more similar than the negative examples. By leveraging both monolingual and parallel corpora, we jointly train the pretext tasks to improve the cross-lingual transferability of pre-trained models. Experimental results on several benchmarks show that our approach achieves considerably better performance. The code and pre-trained models are available at https://aka.ms/infoxlm.
References used
https://aclanthology.org/
rate research
Read More
Compared to monolingual models, cross-lingual models usually require a more expressive vocabulary to represent all languages adequately. We find that many languages are under-represented in recent cross-lingual language models due to the limited voca
bulary capacity. To this end, we propose an algorithm VoCap to determine the desired vocabulary capacity of each language. However, increasing the vocabulary size significantly slows down the pre-training speed. In order to address the issues, we propose k-NN-based target sampling to accelerate the expensive softmax. Our experiments show that the multilingual vocabulary learned with VoCap benefits cross-lingual language model pre-training. Moreover, k-NN-based target sampling mitigates the side-effects of increasing the vocabulary size while achieving comparable performance and faster pre-training speed. The code and the pretrained multilingual vocabularies are available at https://github.com/bozheng-hit/VoCapXLM.
Pimentel et al. (2020) recently analysed probing from an information-theoretic perspective. They argue that probing should be seen as approximating a mutual information. This led to the rather unintuitive conclusion that representations encode exactl
y the same information about a target task as the original sentences. The mutual information, however, assumes the true probability distribution of a pair of random variables is known, leading to unintuitive results in settings where it is not. This paper proposes a new framework to measure what we term Bayesian mutual information, which analyses information from the perspective of Bayesian agents---allowing for more intuitive findings in scenarios with finite data. For instance, under Bayesian MI we have that data can add information, processing can help, and information can hurt, which makes it more intuitive for machine learning applications. Finally, we apply our framework to probing where we believe Bayesian mutual information naturally operationalises ease of extraction by explicitly limiting the available background knowledge to solve a task.
Multilingual pre-trained models have achieved remarkable performance on cross-lingual transfer learning. Some multilingual models such as mBERT, have been pre-trained on unlabeled corpora, therefore the embeddings of different languages in the models
may not be aligned very well. In this paper, we aim to improve the zero-shot cross-lingual transfer performance by proposing a pre-training task named Word-Exchange Aligning Model (WEAM), which uses the statistical alignment information as the prior knowledge to guide cross-lingual word prediction. We evaluate our model on multilingual machine reading comprehension task MLQA and natural language interface task XNLI. The results show that WEAM can significantly improve the zero-shot performance.
Prior work on Data-To-Text Generation, the task of converting knowledge graph (KG) triples into natural text, focused on domain-specific benchmark datasets. In this paper, however, we verbalize the entire English Wikidata KG, and discuss the unique c
hallenges associated with a broad, open-domain, large-scale verbalization. We further show that verbalizing a comprehensive, encyclopedic KG like Wikidata can be used to integrate structured KGs and natural language corpora. In contrast to the many architectures that have been developed to integrate these two sources, our approach converts the KG into natural text, allowing it to be seamlessly integrated into existing language models. It carries the further advantages of improved factual accuracy and reduced toxicity in the resulting language model. We evaluate this approach by augmenting the retrieval corpus in a retrieval language model and showing significant improvements on the knowledge intensive tasks of open domain QA and the LAMA knowledge probe.
Many recent works use consistency regularisation' to improve the generalisation of fine-tuned pre-trained models, both multilingual and English-only. These works encourage model outputs to be similar between a perturbed and normal version of the inpu
t, usually via penalising the Kullback--Leibler (KL) divergence between the probability distribution of the perturbed and normal model. We believe that consistency losses may be implicitly regularizing the loss landscape. In particular, we build on work hypothesising that implicitly or explicitly regularizing trace of the Fisher Information Matrix (FIM), amplifies the implicit bias of SGD to avoid memorization. Our initial results show both empirically and theoretically that consistency losses are related to the FIM, and show that the flat minima implied by a small trace of the FIM improves performance when fine-tuning a multilingual model on additional languages. We aim to confirm these initial results on more datasets, and use our insights to develop better multilingual fine-tuning techniques.
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
