Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLearn The Big Picture: Representation Learning for Clustering
تعلم الصورة الكبيرة: التمثيل تعلم التجميع
252
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تجد النماذج الموجودة الإشراف على النصوص النصية صعوبة في تحسين نتائج تجميعها مباشرة.وذلك لأن التجميع عملية منفصلة، ومن الصعب تقدير التدرج المجدي لأي وظيفة منفصلة يمكن أن تدفع خوارزميات التحسين المستندة إلى التدرج.لذا، فإن خوارزميات التجميع الموجودة محتجزة بشكل غير مباشر تحقق بشكل غير مباشر لبعض الوظائف المستمرة التي تقارب عملية التجميع.نقترح استراتيجية تدريبية قابلة للتطوير التي تعمل بشكل مباشر على متري تجميع منفصل.نحن ندرب نموذج التضمين القائم على بيرت باستخدام أسلوبنا وتقييمه على مجموعة بيانات متوفرة للجمهور.نظهر أن أسلوبنا تتفوق على نموذج آخر مضمون يستند إلى بيرت توظف خسارة ثلاثية وغيرها من خطوط الأساس غير المدعومة.هذا يشير إلى أن التحسين مباشرة لنتائج التجميع تعطي بالفعل تمثيل أفضل مناسبة للتجميع.
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.
References used
https://aclanthology.org/
rate research
Read More
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 b
ut 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.
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.
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.
Lemmatization is often used with morphologically rich languages to address issues caused by morphological complexity, performed by grammar-based lemmatizers. We propose an alternative for this, in form of a tool that performs lemmatization in the spa
ce of word embeddings. Word embeddings as distributed representations natively encode some information about the relationship between base and inflected forms, and we show that it is possible to learn a transformation that approximately maps the embeddings of inflected forms to the embeddings of the corresponding lemmas. This facilitates an alternative processing pipeline that replaces traditional lemmatization with the lemmatizing transformation in downstream processing for any application. We demonstrate the method in the Finnish language, outperforming traditional lemmatizers in example task of document similarity comparison, but the approach is language independent and can be trained for new languages with mild requirements.
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.
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
