تعتمد تقنيات AdgeDDing Word بشدة على ترددات الكلمات في Corpus، وتتأثر سلبا بفشل في تقديم تمثيلات موثوقة للكلمات ذات التردد المنخفض أو الكلمات غير المرئية أثناء التدريب. لمعالجة هذه المشكلة، نقترح خوارزمية لتعلم Admeddings عن الكلمات النادرة على أساس محرك بحث الإنترنت وعلاقات الموقع المكاني. خوارزميتنا عائدات في خطوتين. نقوم أولا باسترجاع صفحات الويب المقابلة للكلمة النادرة من خلال محرك البحث وتحليل النتائج المرسلة لاستخراج مجموعة من أكثر الكلمات ذات الصلة. نحن متوسط ناقلات الكلمات ذات الصلة باعتبارها المتجه الأولي للكلمة النادرة. بعد ذلك، فإن موقع الكلمة النادرة في مساحة المتجه يتم ضبطه بشكل متكرر وفقا لترتيب ما له في الكلمات ذات الصلة. بالمقارنة مع النهج الأخرى، يمكن للخوارزمية لدينا معرفة تمثيلات أكثر دقة لمجموعة واسعة من المفردات. نقوم بتقييم شركاتنا النادرة المستفادة من الكلمات النادرة على مهمة كلمة متعلقة، وتظهر النتائج التجريبية أن خوارزميتنا تحقق الأداء الحديث من بين الفن.
Word embedding techniques depend heavily on the frequencies of words in the corpus, and are negatively impacted by failures in providing reliable representations for low-frequency words or unseen words during training. To address this problem, we propose an algorithm to learn embeddings for rare words based on an Internet search engine and the spatial location relationships. Our algorithm proceeds in two steps. We firstly retrieve webpages corresponding to the rare word through the search engine and parse the returned results to extract a set of most related words. We average the vectors of the related words as the initial vector of the rare word. Then, the location of the rare word in the vector space is iteratively fine-tuned according to the order of its relevances to the related words. Compared to other approaches, our algorithm can learn more accurate representations for a wider range of vocabulary. We evaluate our learned rare-word embeddings on the word relatedness task, and the experimental results show that our algorithm achieves state-of-the-art performance.
References used
https://aclanthology.org/
The basics of sEO, create unique page titles, improve the website structure, improve the content, dealing with crawlers, improve SEO for mobile devices, using analytics and promotional operating
Although there are many studies on neural language generation (NLG), few trials are put into the real world, especially in the advertising domain. Generating ads with NLG models can help copywriters in their creation. However, few studies have adequa
Recently, sponsored search has become one of the most lucrative channels for marketing. As the fundamental basis of sponsored search, relevance modeling has attracted increasing attention due to the tremendous practical value. Most existing methods s
Recognizing named entities in short search engine queries is a difficult task due to their weaker contextual information compared to long sentences. Standard named entity recognition (NER) systems that are trained on grammatically correct and long se
Supervised learning assumes that a ground truth label exists. However, the reliability of this ground truth depends on human annotators, who often disagree. Prior work has shown that this disagreement can be helpful in training models. We propose a n