Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userControlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models
تقييم التحكم بالمعرفة النحوية في نماذج اللغة الصينية الماندرين
179
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
أظهر العمل السابق أن الإشراف الهيكلية يساعد نماذج اللغة الإنجليزية على تعلم التعميمات حول الظواهر النحوية مثل اتفاقية الفعل الفعل. ومع ذلك، فإنه لا يزال غير واضح إذا كان مثل هذا التحيز الاستقرائي ستحسن أيضا قدرة نماذج اللغة على تعلم التبعيات النحوية بلغات مختلفة من الناحية النموذجية. نحن هنا التحقيق في هذا السؤال في لغة الماندرين الصينية، والتي لديها نظام كتابة من مقدم من لفائف التروج، إلى حد كبير؛ ترتيب كلمة مختلفة و sparser التشكل من الإنجليزية. نحن ندرب LSTMS، ونواسيب الشبكة العصبية المتكررة، ونماذج لغة المحولات، ونماذج تحليل التلال المعلمة للمحول على مجموعات بيانات ماندرين الصينية بأحجام مختلفة. نقيم قدرة النماذج على تعلم جوانب مختلفة من قواعد اللغة الماندرين التي تقييم العلاقات النحوية والدالة. نجد أدلة منهية أن الإشراف الهيكلية يساعد في تمثيل الحالة النحوية عبر المحتوى المتداخلة ويحسن الأداء في إعدادات البيانات المنخفضة، مما يشير إلى أن فوائد التحيزات الاستقرائي التسلسل الهرمي في الحصول على علاقات التبعية قد تتجاوز الإنجليزية.
Prior work has shown that structural supervision helps English language models learn generalizations about syntactic phenomena such as subject-verb agreement. However, it remains unclear if such an inductive bias would also improve language models' ability to learn grammatical dependencies in typologically different languages. Here we investigate this question in Mandarin Chinese, which has a logographic, largely syllable-based writing system; different word order; and sparser morphology than English. We train LSTMs, Recurrent Neural Network Grammars, Transformer language models, and Transformer-parameterized generative parsing models on two Mandarin Chinese datasets of different sizes. We evaluate the models' ability to learn different aspects of Mandarin grammar that assess syntactic and semantic relationships. We find suggestive evidence that structural supervision helps with representing syntactic state across intervening content and improves performance in low-data settings, suggesting that the benefits of hierarchical inductive biases in acquiring dependency relationships may extend beyond English.
References used
https://aclanthology.org/
rate research
Read More
The factual knowledge acquired during pre-training and stored in the parameters of Language Models (LMs) can be useful in downstream tasks (e.g., question answering or textual inference). However, some facts can be incorrectly induced or become obsol
ete over time. We present KnowledgeEditor, a method which can be used to edit this knowledge and, thus, fix bugs' or unexpected predictions without the need for expensive re-training or fine-tuning. Besides being computationally efficient, KnowledgeEditordoes not require any modifications in LM pre-training (e.g., the use of meta-learning). In our approach, we train a hyper-network with constrained optimization to modify a fact without affecting the rest of the knowledge; the trained hyper-network is then used to predict the weight update at test time. We show KnowledgeEditor's efficacy with two popular architectures and knowledge-intensive tasks: i) a BERT model fine-tuned for fact-checking, and ii) a sequence-to-sequence BART model for question answering. With our method, changing a prediction on the specific wording of a query tends to result in a consistent change in predictions also for its paraphrases. We show that this can be further encouraged by exploiting (e.g., automatically-generated) paraphrases during training. Interestingly, our hyper-network can be regarded as a probe' revealing which components need to be changed to manipulate factual knowledge; our analysis shows that the updates tend to be concentrated on a small subset of components. Source code available at https://github.com/nicola-decao/KnowledgeEditor
Grammatical error correction (GEC) requires a set of labeled ungrammatical / grammatical sentence pairs for training, but obtaining such annotation can be prohibitively expensive. Recently, the Break-It-Fix-It (BIFI) framework has demonstrated strong
results on learning to repair a broken program without any labeled examples, but this relies on a perfect critic (e.g., a compiler) that returns whether an example is valid or not, which does not exist for the GEC task. In this work, we show how to leverage a pretrained language model (LM) in defining an LM-Critic, which judges a sentence to be grammatical if the LM assigns it a higher probability than its local perturbations. We apply this LM-Critic and BIFI along with a large set of unlabeled sentences to bootstrap realistic ungrammatical / grammatical pairs for training a corrector. We evaluate our approach on GEC datasets on multiple domains (CoNLL-2014, BEA-2019, GMEG-wiki and GMEG-yahoo) and show that it outperforms existing methods in both the unsupervised setting (+7.7 F0.5) and the supervised setting (+0.5 F0.5).
In this paper, we propose a knowledge infusion mechanism to incorporate domain knowledge into language transformers. Weakly supervised data is regarded as the main source for knowledge acquisition. We pre-train the language models to capture masked k
nowledge of focuses and aspects and then fine-tune them to obtain better performance on the downstream tasks. Due to the lack of publicly available datasets for multi-label classification of Chinese medical questions, we crawled questions from medical question/answer forums and manually annotated them using eight predefined classes: persons and organizations, symptom, cause, examination, disease, information, ingredient, and treatment. Finally, a total of 1,814 questions with 2,340 labels. Each question contains an average of 1.29 labels. We used Baidu Medical Encyclopedia as the knowledge resource. Two transformers BERT and RoBERTa were implemented to compare performance on our constructed datasets. Experimental results showed that our proposed model with knowledge infusion mechanism can achieve better performance, no matter which evaluation metric including Macro F1, Micro F1, Weighted F1 or Subset Accuracy were considered.
Choosing the most suitable classifier in a linguistic context is a well-known problem in the production of Mandarin and many other languages. The present paper proposes a solution based on BERT, compares this solution to previous neural and rule-base
d models, and argues that the BERT model performs particularly well on those difficult cases where the classifier adds information to the text.
Relational knowledge bases (KBs) are commonly used to represent world knowledge in machines. However, while advantageous for their high degree of precision and interpretability, KBs are usually organized according to manually-defined schemas, which l
imit their expressiveness and require significant human efforts to engineer and maintain. In this review, we take a natural language processing perspective to these limitations, examining how they may be addressed in part by training deep contextual language models (LMs) to internalize and express relational knowledge in more flexible forms. We propose to organize knowledge representation strategies in LMs by the level of KB supervision provided, from no KB supervision at all to entity- and relation-level supervision. Our contributions are threefold: (1) We provide a high-level, extensible taxonomy for knowledge representation in LMs; (2) Within our taxonomy, we highlight notable models, evaluation tasks, and findings, in order to provide an up-to-date review of current knowledge representation capabilities in LMs; and (3) We suggest future research directions that build upon the complementary aspects of LMs and KBs as knowledge representations.
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
