ترغب بنشر مسار تعليمي؟ اضغط هنا

GLOW : Global Weighted Self-Attention Network for Web Search

232   0   0.0 ( 0 )
 نشر من قبل Xuan Shan
 تاريخ النشر 2020
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Deep matching models aim to facilitate search engines retrieving more relevant documents by mapping queries and documents into semantic vectors in the first-stage retrieval. When leveraging BERT as the deep matching model, the attention score across two words are solely built upon local contextualized word embeddings. It lacks prior global knowledge to distinguish the importance of different words, which has been proved to play a critical role in information retrieval tasks. In addition to this, BERT only performs attention across sub-words tokens which weakens whole word attention representation. We propose a novel Global Weighted Self-Attention (GLOW) network for web document search. GLOW fuses global corpus statistics into the deep matching model. By adding prior weights into attention generation from global information, like BM25, GLOW successfully learns weighted attention scores jointly with query matrix $Q$ and key matrix $K$. We also present an efficient whole word weight sharing solution to bring prior whole word knowledge into sub-words level attention. It aids Transformer to learn whole word level attention. To make our models applicable to complicated web search scenarios, we introduce combined fields representation to accommodate documents with multiple fields even with variable number of instances. We demonstrate GLOW is more efficient to capture the topical and semantic representation both in queries and documents. Intrinsic evaluation and experiments conducted on public data sets reveal GLOW to be a general framework for document retrieve task. It significantly outperforms BERT and other competitive baselines by a large margin while retaining the same model complexity with BERT.



قيم البحث

اقرأ أيضاً

314 - Maksims Volkovs 2015
We present our solution to the Yandex Personalized Web Search Challenge. The aim of this challenge was to use the historical search logs to personalize top-N document rankings for a set of test users. We used over 100 features extracted from user- an d query-depended contexts to train neural net and tree-based learning-to-rank and regression models. Our final submission, which was a blend of several different models, achieved an NDCG@10 of 0.80476 and placed 4th amongst the 194 teams winning 3rd prize.
Information extraction from semi-structured webpages provides valuable long-tailed facts for augmenting knowledge graph. Relational Web tables are a critical component containing additional entities and attributes of rich and diverse knowledge. Howev er, extracting knowledge from relational tables is challenging because of sparse contextual information. Existing work linearize table cells and heavily rely on modifying deep language models such as BERT which only captures related cells information in the same table. In this work, we propose a novel relational table representation learning approach considering both the intra- and inter-table contextual information. On one hand, the proposed Table Convolutional Network model employs the attention mechanism to adaptively focus on the most informative intra-table cells of the same row or column; and, on the other hand, it aggregates inter-table contextual information from various types of implicit connections between cells across different tables. Specifically, we propose three novel aggregation modules for (i) cells of the same value, (ii) cells of the same schema position, and (iii) cells linked to the same page topic. We further devise a supervised multi-task training objective for jointly predicting column type and pairwise column relation, as well as a table cell recovery objective for pre-training. Experiments on real Web table datasets demonstrate our method can outperform competitive baselines by +4.8% of F1 for column type prediction and by +4.1% of F1 for pairwise column relation prediction.
This paper presents GEneric iNtent Encoder (GEN Encoder) which learns a distributed representation space for user intent in search. Leveraging large scale user clicks from Bing search logs as weak supervision of user intent, GEN Encoder learns to map queries with shared clicks into similar embeddings end-to-end and then finetunes on multiple paraphrase tasks. Experimental results on an intrinsic evaluation task - query intent similarity modeling - demonstrate GEN Encoders robust and significant advantages over previous representation methods. Ablation studies reveal the crucial role of learning from implicit user feedback in representing user intent and the contributions of multi-task learning in representation generality. We also demonstrate that GEN Encoder alleviates the sparsity of tail search traffic and cuts down half of the unseen queries by using an efficient approximate nearest neighbor search to effectively identify previous queries with the same search intent. Finally, we demonstrate distances between GEN encodings reflect certain information seeking behaviors in search sessions.
We analyze access statistics of a hundred and fifty blog entries and news articles, for periods of up to three years. Access rate falls as an inverse power of time passed since publication. The power law holds for periods of up to thousand days. The exponents are different for different blogs and are distributed between 0.6 and 3.2. We argue that the decay of attention to a web article is caused by the link to it first dropping down the list of links on the websites front page, and then disappearing from the front page and its subsequent movement further into background. The other proposed explanations that use a decaying with time novelty factor, or some intricate theory of human dynamics cannot explain all of the experimental observations.
Topic models are popular models for analyzing a collection of text documents. The models assert that documents are distributions over latent topics and latent topics are distributions over words. A nested document collection is where documents are ne sted inside a higher order structure such as stories in a book, articles in a journal, or web pages in a web site. In a single collection of documents, topics are global, or shared across all documents. For web pages nested in web sites, topic frequencies likely vary between web sites. Within a web site, topic frequencies almost certainly vary between web pages. A hierarchical prior for topic frequencies models this hierarchical structure and specifies a global topic distribution. Web site topic distributions vary around the global topic distribution and web page topic distributions vary around the web site topic distribution. In a nested collection of web pages, some topics are likely unique to a single web site. Local topics in a nested collection of web pages are topics unique to one web site. For US local health department web sites, brief inspection of the text shows local geographic and news topics specific to each department that are not present in others. Topic models that ignore the nesting may identify local topics, but do not label topics as local nor do they explicitly identify the web site owner of the local topic. For web pages nested inside web sites, local topic models explicitly label local topics and identifies the owning web site. This identification can be used to adjust inferences about global topics. In the US public health web site data, topic coverage is defined at the web site level after removing local topic words from pages. Hierarchical local topic models can be used to identify local topics, adjust inferences about if web sites cover particular health topics, and study how well health topics are covered.
التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا