Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userExploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models
استكشاف استراتيجيات لمنطق العموم المتعميم مع النماذج المدربة مسبقا
601
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تم حل معايير المنطق المنطقي إلى حد كبير عن طريق نماذج لغة ضبط دقيقة. الجانب السلبي هو أن الضبط الدقيق قد يتسبب في طرح نماذج إلى البيانات الخاصة بمهام المهام وبالتالي انسوا معرفتهم المكتسبة خلال التدريب المسبق. تعمل الأعمال الحديثة فقط على اقتراح تحديثات نموذجية خفيفة الوزن حيث قد تمتلك النماذج بالفعل معرفة مفيدة من الخبرة السابقة، لكن التحدي لا يزال في فهم الأجزاء وإلى أي مدى يجب أن يتم تنقيح النماذج بمهمة معينة. في هذه الورقة، نقوم بالتحقيق في نماذج تتعلم من مجموعات بيانات منطق المنطقية. نقيس تأثير ثلاث طرق تكييف مختلفة عن تعميم ودقة النماذج. تظهر تجاربنا مع نماذجين أن الضبط الدقيق يؤدي بشكل أفضل، من خلال تعلم كل من المحتوى والهيكل المهمة، ولكنه يعاني من التجمع المحدود والمحدود لإجابات جديدة. نلاحظ أن طرق التكيف البديلة مثل ضبط البادئة لها دقة قابلة للمقارنة، ولكن تعميم أفضل من الإجابات غير المرئية وهي أكثر قوة لانشقاقات الخصومة.
Commonsense reasoning benchmarks have been largely solved by fine-tuning language models. The downside is that fine-tuning may cause models to overfit to task-specific data and thereby forget their knowledge gained during pre-training. Recent works only propose lightweight model updates as models may already possess useful knowledge from past experience, but a challenge remains in understanding what parts and to what extent models should be refined for a given task. In this paper, we investigate what models learn from commonsense reasoning datasets. We measure the impact of three different adaptation methods on the generalization and accuracy of models. Our experiments with two models show that fine-tuning performs best, by learning both the content and the structure of the task, but suffers from overfitting and limited generalization to novel answers. We observe that alternative adaptation methods like prefix-tuning have comparable accuracy, but generalize better to unseen answers and are more robust to adversarial splits.
References used
https://aclanthology.org/
rate research
Read More
Recent developments in natural language generation (NLG) have bolstered arguments in favor of re-introducing explicit coding of discourse relations in the input to neural models. In the Methodius corpus, a meaning representation (MR) is hierarchicall
y structured and includes discourse relations. Meanwhile pre-trained language models have been shown to implicitly encode rich linguistic knowledge which provides an excellent resource for NLG. By virtue of synthesizing these lines of research, we conduct extensive experiments on the benefits of using pre-trained models and discourse relation information in MRs, focusing on the improvement of discourse coherence and correctness. We redesign the Methodius corpus; we also construct another Methodius corpus in which MRs are not hierarchically structured but flat. We report experiments on different versions of the corpora, which probe when, where, and how pre-trained models benefit from MRs with discourse relation information in them. We conclude that discourse relations significantly improve NLG when data is limited.
We present two novel unsupervised methods for eliminating toxicity in text. Our first method combines two recent ideas: (1) guidance of the generation process with small style-conditional language models and (2) use of paraphrasing models to perform
style transfer. We use a well-performing paraphraser guided by style-trained language models to keep the text content and remove toxicity. Our second method uses BERT to replace toxic words with their non-offensive synonyms. We make the method more flexible by enabling BERT to replace mask tokens with a variable number of words. Finally, we present the first large-scale comparative study of style transfer models on the task of toxicity removal. We compare our models with a number of methods for style transfer. The models are evaluated in a reference-free way using a combination of unsupervised style transfer metrics. Both methods we suggest yield new SOTA results.
Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and weakens its cro
ss-lingual ability, which leads to sub-optimal performance. To alleviate this problem, we leverage continual learning to preserve the original cross-lingual ability of the pre-trained model when we fine-tune it to downstream tasks. The experimental result shows that our fine-tuning methods can better preserve the cross-lingual ability of the pre-trained model in a sentence retrieval task. Our methods also achieve better performance than other fine-tuning baselines on the zero-shot cross-lingual part-of-speech tagging and named entity recognition tasks.
Pre-trained language models have achieved huge success on a wide range of NLP tasks. However, contextual representations from pre-trained models contain entangled semantic and syntactic information, and therefore cannot be directly used to derive use
ful semantic sentence embeddings for some tasks. Paraphrase pairs offer an effective way of learning the distinction between semantics and syntax, as they naturally share semantics and often vary in syntax. In this work, we present ParaBART, a semantic sentence embedding model that learns to disentangle semantics and syntax in sentence embeddings obtained by pre-trained language models. ParaBART is trained to perform syntax-guided paraphrasing, based on a source sentence that shares semantics with the target paraphrase, and a parse tree that specifies the target syntax. In this way, ParaBART learns disentangled semantic and syntactic representations from their respective inputs with separate encoders. Experiments in English show that ParaBART outperforms state-of-the-art sentence embedding models on unsupervised semantic similarity tasks. Additionally, we show that our approach can effectively remove syntactic information from semantic sentence embeddings, leading to better robustness against syntactic variation on downstream semantic tasks.
Early exit mechanism aims to accelerate the inference speed of large-scale pre-trained language models. The essential idea is to exit early without passing through all the inference layers at the inference stage. To make accurate predictions for down
stream tasks, the hierarchical linguistic information embedded in all layers should be jointly considered. However, much of the research up to now has been limited to use local representations of the exit layer. Such treatment inevitably loses information of the unused past layers as well as the high-level features embedded in future layers, leading to sub-optimal performance. To address this issue, we propose a novel Past-Future method to make comprehensive predictions from a global perspective. We first take into consideration all the linguistic information embedded in the past layers and then take a further step to engage the future information which is originally inaccessible for predictions. Extensive experiments demonstrate that our method outperforms previous early exit methods by a large margin, yielding better and robust performance.
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
