These may include misspellings and typos, elisions/omissions, unusual phrasing/syntactic structures, the wrong word(s) being used, negations ("not x"), things that have only just happened etc. etc. etc.

Google's new research has discovered a way to join the best of both approaches. They use "extractive summaries" to extract the important facts from web documents and then apply the "abstractive" approach to paraphrase the content. This approach creates a new document based on the information found on the web, creating Google's own version of Wikipedia. Google's new algorithm is described in a research paper titled, Generating Wikipedia by Summarizing Long Sequences

One of the biggest mistakes made by business owners and native digital marketers is being too focused on vanity keywords and search volume as the indicator of SEO success. This article will focus on user intent, often referred to as "searcher intent", as the most valuable point of focus for SEO success, in any SEO campaign. Let's start off by explaining what searcher intent actually is… Searcher intent (also known as "user intent") is the motive a person has for carrying out a query through a search engine. Understanding and optimising for your customers' intent is critical for SEO. How we search for answers has evolved and changed over the years. And with that change, search engine algorithms have been adjusted to return the most relevant results. In the beginning, search engines returned results based on a pretty simplistic formula: They would look at basic factors such as the density of keywords matching the query and some more elusive factors like PageRank. SEO professionals and spammers took advantage of this with keyword stuffing, hiding text techniques and buying links. The era of black hat SEO, unfortunately, blossomed. It was, and will always be, in Google's best interest to become better at answering queries. SEO success used to be built on gaming search engines, but now SEO is about optimising for what the user is trying to accomplish. As it should be, we're no longer writing for robots and algorithms.

Creating an automation strategy should be top of mind in 2019 – indeed, it was identified by 61 percent of marketers as the top priority for optimizing marketing automation efforts in a recent industry survey. Researchers also identified the delivery of personalized content and integration of marketing systems as the most challenging barriers to your success with marketing technology. SEO and Automation is a big part of the solution. Automation is critical in making informed, data-driven decisions in a world in which the amount of data companies are attempting to manage is unprecedented. But we're at the point now where, as marketers have attempted to automate various tasks, many are struggling with unwieldy stacks of different technologies all vying for resources and budget.

Webmaster Hangouts debuted a bilingual Telugu and English version. I have watched it and was impressed with the quality of information about content that ranks, the so-called medic update and a discussion of soft ranking factors. There is a wealth of quality information shared. I may be writing more about what's in that Webmaster Hangout but you should really take the time to view the entire hangout because there is a lot of quality information spoken in English, plus subtitles in the form of Closed Captioning should you need it to follow along. For example, one person asked how important was usability and user experience as ranking factors.

The main goal of this paper is to explore latent topic analysis (LTA), in the context of quantum information retrieval. LTA is a valuable technique for document analysis and representation, which has been extensively used in information retrieval and machine learning. Different LTA techniques have been proposed, some based on geometrical modeling (such as latent semantic analysis, LSA) and others based on a strong statistical foundation. However, these two different approaches are not usually mixed. Quantum information retrieval has the remarkable virtue of combining both geometry and probability in a common principled framework. We built on this quantum framework to propose a new LTA method, which has a clear geometrical motivation but also supports a well-founded probabilistic interpretation. An initial exploratory experimentation was performed on three standard data sets. The results show that the proposed method outperforms LSA on two of the three datasets. These results suggests that the quantum-motivated representation is an alternative for geometrical latent topic modeling worthy of further exploration.

While many of us enjoy longer vacations and sunshine during the summer, major retailers spend the warmer months getting ready for the biggest sales events of the year. In fact, many retailers will report more than 50 percent of their annual profits from a single sales event during the coming fall months. In 2016, Alibaba's Singles Day grossed $17.8 billion in 24 hours, and that figure rose to $25.3 billion in 2017: In the United States, Black Friday and Cyber Monday 2016 sales combined brought in $6.79 billion: These events kick off with Labor Day sales (back to school), which is just around the corner, and end with the holiday shopping season. With online merchandise selling out in seconds and competitive price wars getting exceedingly high, it's no wonder retailers utilize summer months to prepare for eager shoppers. While retailers are focusing on campaigns, commercials, margins and inventory, what can a search engine optimization specialist (SEO) do to help a client's bottom line?

The constant growth of the e-commerce industry has rendered the problem of product retrieval particularly important. As more enterprises move their activities on the Web, the volume and the diversity of the product-related information increase quickly. These factors make it difficult for the users to identify and compare the features of their desired products. Recent studies proved that the standard similarity metrics cannot effectively identify identical products, since similar titles often refer to different products and vice-versa. Other studies employed external data sources (search engines) to enrich the titles; these solutions are rather impractical mainly because the external data fetching is slow. In this paper we introduce UPM, an unsupervised algorithm for matching products by their titles. UPM is independent of any external sources, since it analyzes the titles and extracts combinations of words out of them. These combinations are evaluated according to several criteria, and the most appropriate of them constitutes the cluster where a product is classified into. UPM is also parameter-free, it avoids product pairwise comparisons, and includes a post-processing verification stage which corrects the erroneous matches. The experimental evaluation of UPM demonstrated its superiority against the state-of-the-art approaches in terms of both efficiency and effectiveness.

We describe Voyageur, which is an application of experiential search to the domain of travel. Unlike traditional search engines for online services, experiential search focuses on the experiential aspects of the service under consideration. In particular, Voyageur needs to handle queries for subjective aspects of the service (e.g., quiet hotel, friendly staff) and combine these with objective attributes, such as price and location. Voyageur also highlights interesting facts and tips about the services the user is considering to provide them with further insights into their choices.

E-Commerce (E-Com) search is an emerging important new application of information retrieval. Learning to Rank (LETOR) is a general effective strategy for optimizing search engines, and is thus also a key technology for E-Com search. While the use of LETOR for web search has been well studied, its use for E-Com search has not yet been well explored. In this paper, we discuss the practical challenges in applying learning to rank methods to E-Com search, including the challenges in feature representation, obtaining reliable relevance judgments, and optimally exploiting multiple user feedback signals such as click rates, add-to-cart ratios, order rates, and revenue. We study these new challenges using experiments on industry data sets and report several interesting findings that can provide guidance on how to optimally apply LETOR to E-Com search: First, popularity-based features defined solely on product items are very useful and LETOR methods were able to effectively optimize their combination with relevance-based features. Second, query attribute sparsity raises challenges for LETOR, and selecting features to reduce/avoid sparsity is beneficial. Third, while crowdsourcing is often useful for obtaining relevance judgments for Web search, it does not work as well for E-Com search due to difficulty in eliciting sufficiently fine grained relevance judgments. Finally, among the multiple feedback signals, the order rate is found to be the most robust training objective, followed by click rate, while add-to-cart ratio seems least robust, suggesting that an effective practical strategy may be to initially use click rates for training and gradually shift to using order rates as they become available.