Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userRuleBERT: Teaching Soft Rules to Pre-Trained Language Models
Surebert: تدريس القواعد الناعمة لنماذج اللغة المدربة مسبقا
553
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في حين أن النماذج اللغوية المدربة مسبقا (PLMS) هي محلول الذهاب لمعالجة العديد من مشاكل معالجة اللغة الطبيعية، فإنها لا تزال محدودة للغاية في قدرتها على التقاط ومعرفة المعيشية المشتركة. في الواقع، حتى إذا كانت المعلومات متوفرة في شكل قواعد منطقية تقريبية (ناعمة)، فليس من الواضح كيفية نقلها إلى PLM من أجل تحسين أدائها لمهام التفكير الاستنتاجي. هنا، نهدف إلى سد هذه الفجوة من خلال تدريس PLMS كيفية التفكير مع قواعد القرن الناعمة. نقدم مهمة التصنيف حيث، بالنظر إلى الحقائق والقواعد الناعمة، يجب أن تعيد PLM التنبؤ باحتمال فرضية معينة. نقوم بإصدار بيانات البيانات الأولى لهذه المهمة، ونقترح وظيفة الخسارة المنقحة التي تمكن PLM لتعلم كيفية التنبؤ بحتميات دقيقة للمهمة. تظهر نتائج التقييم الخاصة بنا أن النماذج الناتجة عن القسرية تحقق أداء عال للغاية، حتى على القواعد المنطقية التي كانت غير مرئية في التدريب. علاوة على ذلك، فإننا نوضح أن المفاهيم المنطقية التي أعربنا عنها القواعد يتم نقلها إلى النموذج الدقيق، مما يؤدي إلى نتائج أحدث النتائج على مجموعات البيانات الخارجية.
While pre-trained language models (PLMs) are the go-to solution to tackle many natural language processing problems, they are still very limited in their ability to capture and to use common-sense knowledge. In fact, even if information is available in the form of approximate (soft) logical rules, it is not clear how to transfer it to a PLM in order to improve its performance for deductive reasoning tasks. Here, we aim to bridge this gap by teaching PLMs how to reason with soft Horn rules. We introduce a classification task where, given facts and soft rules, the PLM should return a prediction with a probability for a given hypothesis. We release the first dataset for this task, and we propose a revised loss function that enables the PLM to learn how to predict precise probabilities for the task. Our evaluation results show that the resulting fine-tuned models achieve very high performance, even on logical rules that were unseen at training. Moreover, we demonstrate that logical notions expressed by the rules are transferred to the fine-tuned model, yielding state-of-the-art results on external datasets.
References used
https://aclanthology.org/
rate research
Read More
We introduce BERTweetFR, the first large-scale pre-trained language model for French tweets. Our model is initialised using a general-domain French language model CamemBERT which follows the base architecture of BERT. Experiments show that BERTweetFR
outperforms all previous general-domain French language models on two downstream Twitter NLP tasks of offensiveness identification and named entity recognition. The dataset used in the offensiveness detection task is first created and annotated by our team, filling in the gap of such analytic datasets in French. We make our model publicly available in the transformers library with the aim of promoting future research in analytic tasks for French tweets.
Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over consecutive words i
n pre-training could further improve the performance of PrLMs. However, given that span-level clues are introduced and fixed in pre-training, previous methods are time-consuming and lack of flexibility. To alleviate the inconvenience, this paper presents a novel span fine-tuning method for PrLMs, which facilitates the span setting to be adaptively determined by specific downstream tasks during the fine-tuning phase. In detail, any sentences processed by the PrLM will be segmented into multiple spans according to a pre-sampled dictionary. Then the segmentation information will be sent through a hierarchical CNN module together with the representation outputs of the PrLM and ultimately generate a span-enhanced representation. Experiments on GLUE benchmark show that the proposed span fine-tuning method significantly enhances the PrLM, and at the same time, offer more flexibility in an efficient way.
Pretrained language models (PTLMs) yield state-of-the-art performance on many natural language processing tasks, including syntax, semantics and commonsense. In this paper, we focus on identifying to what extent do PTLMs capture semantic attributes a
nd their values, e.g., the correlation between rich and high net worth. We use PTLMs to predict masked tokens using patterns and lists of items from Wikidata in order to verify how likely PTLMs encode semantic attributes along with their values. Such inferences based on semantics are intuitive for humans as part of our language understanding. Since PTLMs are trained on large amount of Wikipedia data we would assume that they can generate similar predictions, yet our findings reveal that PTLMs are still much worse than humans on this task. We show evidence and analysis explaining how to exploit our methodology to integrate better context and semantics into PTLMs using knowledge bases.
Modern transformer-based language models are revolutionizing NLP. However, existing studies into language modelling with BERT have been mostly limited to English-language material and do not pay enough attention to the implicit knowledge of language,
such as semantic roles, presupposition and negations, that can be acquired by the model during training. Thus, the aim of this study is to examine behavior of the model BERT in the task of masked language modelling and to provide linguistic interpretation to the unexpected effects and errors produced by the model. For this purpose, we used a new Russian-language dataset based on educational texts for learners of Russian and annotated with the help of the National Corpus of the Russian language. In terms of quality metrics (the proportion of words, semantically related to the target word), the multilingual BERT is recognized as the best model. Generally, each model has distinct strengths in relation to a certain linguistic phenomenon. These observations have meaningful implications for research into applied linguistics and pedagogy, contribute to dialogue system development, automatic exercise making, text generation and potentially could improve the quality of existing linguistic technologies
In this study, we propose a self-supervised learning method that distils representations of word meaning in context from a pre-trained masked language model. Word representations are the basis for context-aware lexical semantics and unsupervised sema
ntic textual similarity (STS) estimation. A previous study transforms contextualised representations employing static word embeddings to weaken excessive effects of contextual information. In contrast, the proposed method derives representations of word meaning in context while preserving useful context information intact. Specifically, our method learns to combine outputs of different hidden layers using self-attention through self-supervised learning with an automatically generated training corpus. To evaluate the performance of the proposed approach, we performed comparative experiments using a range of benchmark tasks. The results confirm that our representations exhibited a competitive performance compared to that of the state-of-the-art method transforming contextualised representations for the context-aware lexical semantic tasks and outperformed it for STS estimation.
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
