Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLearning to Learn to be Right for the Right Reasons
تعلم تعلم أن يكون صحيحا للأسباب الصحيحة
469
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يعد تحسين تعميم النموذج حول البيانات المحتفظ بها أحد الأهداف الأساسية في التفكير المعني بالمعنى. لقد أظهر العمل الحديث أن النماذج المدربة على مجموعة البيانات مع الإشارات السطحية تميل إلى أداء جيد في الاختبار السهل مع الإشارات السطحية ولكنها تؤدي بشكل سيء على مجموعة الاختبار الثابت دون إشارات سطحية. لجأت النهج السابقة إلى الأساليب اليدوية لتشجيع النماذج غير المبالفة للعظة السطحية. في حين أن بعض الأساليب قد تحسن الأداء على الحالات الصعبة، فإنها تؤدي أيضا إلى أدائها المتدهورة بشأن التعرضات السهلة. هنا، نقترح أن تتعلم صراحة نموذجا جيدا على كل من مجموعة الاختبار السهلة مع الإشارات السطحية ومجموعة الاختبار الثابت دون إشارات سطحية. باستخدام هدف التعلم التلوي، نتعلم مثل هذا النموذج الذي يحسن الأداء على كل من مجموعة الاختبار السهلة ومجموعة الاختبار الثابت. من خلال تقييم نماذجنا عند اختيار البدائل المعقولة (COPA) وشرح المنطقي، نوضح أن أسلوبنا المقترح يؤدي إلى تحسين الأداء على كل من مجموعة الاختبارات السهلة ومجموعة الاختبار الصعب الذي نلاحظ عليه ما يصل إلى 16.5 نقطة مئوية من التحسن على أساس الأساس وبعد
Improving model generalization on held-out data is one of the core objectives in common- sense reasoning. Recent work has shown that models trained on the dataset with superficial cues tend to perform well on the easy test set with superficial cues but perform poorly on the hard test set without superficial cues. Previous approaches have resorted to manual methods of encouraging models not to overfit to superficial cues. While some of the methods have improved performance on hard instances, they also lead to degraded performance on easy in- stances. Here, we propose to explicitly learn a model that does well on both the easy test set with superficial cues and the hard test set without superficial cues. Using a meta-learning objective, we learn such a model that improves performance on both the easy test set and the hard test set. By evaluating our models on Choice of Plausible Alternatives (COPA) and Commonsense Explanation, we show that our proposed method leads to improved performance on both the easy test set and the hard test set upon which we observe up to 16.5 percentage points improvement over the baseline.
References used
https://aclanthology.org/
rate research
Read More
Paraphrase generation is a longstanding NLP task that has diverse applications on downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised endeavors have be
en proposed to alleviate this issue, they may fail to generate meaningful paraphrases due to the lack of supervision signals. In this work, we go beyond the existing paradigms and propose a novel approach to generate high-quality paraphrases with data of weak supervision. Specifically, we tackle the weakly-supervised paraphrase generation problem by: (1) obtaining abundant weakly-labeled parallel sentences via retrieval-based pseudo paraphrase expansion; and (2) developing a meta-learning framework to progressively select valuable samples for fine-tuning a pre-trained language model BART on the sentential paraphrasing task. We demonstrate that our approach achieves significant improvements over existing unsupervised approaches, and is even comparable in performance with supervised state-of-the-arts.
Existing supervised models for text clustering find it difficult to directly optimize for clustering results. This is because clustering is a discrete process and it is difficult to estimate meaningful gradient of any discrete function that can drive
gradient based optimization algorithms. So, existing supervised clustering algorithms indirectly optimize for some continuous function that approximates the clustering process. We propose a scalable training strategy that directly optimizes for a discrete clustering metric. We train a BERT-based embedding model using our method and evaluate it on two publicly available datasets. We show that our method outperforms another BERT-based embedding model employing Triplet loss and other unsupervised baselines. This suggests that optimizing directly for the clustering outcome indeed yields better representations suitable for clustering.
For each goal-oriented dialog task of interest, large amounts of data need to be collected for end-to-end learning of a neural dialog system. Collecting that data is a costly and time-consuming process. Instead, we show that we can use only a small a
mount of data, supplemented with data from a related dialog task. Naively learning from related data fails to improve performance as the related data can be inconsistent with the target task. We describe a meta-learning based method that selectively learns from the related dialog task data. Our approach leads to significant accuracy improvements in an example dialog task.
We present a scaffolded discovery learning approach to introducing concepts in a Natural Language Processing course aimed at computer science students at liberal arts institutions. We describe some of the objectives of this approach, as well as prese
nting specific ways that four of our discovery-based assignments combine specific natural language processing concepts with broader analytic skills. We argue this approach helps prepare students for many possible future paths involving both application and innovation of NLP technology by emphasizing experimental data navigation, experiment design, and awareness of the complexities and challenges of analysis.
Vector representations have become a central element in semantic language modelling, leading to mathematical overlaps with many fields including quantum theory. Compositionality is a core goal for such representations: given representations for wet'
and fish', how should the concept wet fish' be represented? This position paper surveys this question from two points of view. The first considers the question of whether an explicit mathematical representation can be successful using only tools from within linear algebra, or whether other mathematical tools are needed. The second considers whether semantic vector composition should be explicitly described mathematically, or whether it can be a model-internal side-effect of training a neural network. A third and newer question is whether a compositional model can be implemented on a quantum computer. Given the fundamentally linear nature of quantum mechanics, we propose that these questions are related, and that this survey may help to highlight candidate operations for future quantum implementation.
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
