One of the challenges in large-scale information retrieval (IR) is to develop fine-grained and domain-specific methods to answer natural language questions. Despite the availability of numerous sources and datasets for answer retrieval, Question Answering (QA) remains a challenging problem due to the difficulty of the question understanding and answer extraction tasks. One of the promising tracks investigated in QA is to map new questions to formerly answered questions that are `similar'. In this paper, we propose a novel QA approach based on Recognizing Question Entailment (RQE) and we describe the QA system and resources that we built and evaluated on real medical questions. First, we compare machine learning and deep learning methods for RQE using different kinds of datasets, including textual inference, question similarity and entailment in both the open and clinical domains. Second, we combine IR models with the best RQE method to select entailed questions and rank the retrieved answers. To study the end-to-end QA approach, we built the MedQuAD collection of 47,457 question-answer pairs from trusted medical sources, that we introduce and share in the scope of this paper. Following the evaluation process used in TREC 2017 LiveQA, we find that our approach exceeds the best results of the medical task with a 29.8% increase over the best official score. The evaluation results also support the relevance of question entailment for QA and highlight the effectiveness of combining IR and RQE for future QA efforts. Our findings also show that relying on a restricted set of reliable answer sources can bring a substantial improvement in medical QA.

With video streaming services and social media platforms reporting large amounts of traffic, videos are slowly but surely moving front and center as the most popular form of online content. Plus, they are made more accessible by the widespread use of mobile devices and the growing average speed of Internet connectivity. Look no further than sites like Twitch and YouTube to understand how powerful videos can be at keeping people glued to their screens. As a matter of fact, according to YouTube, U.S. residents aged 18-34 watch more videos on mobile devices than they do on any TV broadcast or cable network. Bearing this in mind, performing video optimization has never been as important as it is today. To get more eyeballs looking at your videos, you must do your best to ensure that people can find your videos online and that they choose to watch your video over the vast pool of competition -- something that was covered in the YouTube SEO 101 post. Getting yourself noticed on YouTube can be quite a daunting challenge, but in this post, we've rounded up some of the best tools that can help you optimize your YouTube videos for SEO. Without further ado, let's get started! One of the most crucial parts of producing videos is getting everything ready even before the camera starts rolling.

Twitter has released a new, free resource to help guide marketers' social media strategies in 2019. The 2019 Twitter marketing calendar identifies highly anticipated events that will unfold throughout the year. In addition, Twitter estimates the number of Tweet impressions each of the events are expected to reach, based on internal data. Everything from Valentine's Day to Talk Like a Pirate Day is contained in the calendar. Here's an example of what it looks like: Marketers can use this information to capitalize on unique, once-a-year, opportunities to boost their reach.

Online retailers face a whole host of relatively unique search engine optimization (SEO) considerations most other websites don't deal with. Most discussions about those differences focus on issues such as tags, uniform resource locators (URLs), link structure, duplicate content and so on. In this post, I want to zoom out a bit and start talking about strategic approaches. I've decided to focus specifically on three factors that deserve special attention in developing an SEO strategy for online retailers: keyword research, mobile crawling and customer reviews. This is by no means an exhaustive list, but I believe it's a useful starting point.

If you want to take your SEO to the next level – or even keep up – in 2018 and beyond, then you need to understand how artificial intelligence (AI) is shaping SEO, and how you can use this knowledge to boost your rankings. Up until recently, search engine algorithms were entirely hand-coded by engineers but this has its limitations, not least because of the sheer size of the task and the potential for human error. Artificial intelligence such as speech recognition and image classification software has helped to pave the way for integrating'machine learning' into search engine algorithms. Now new technologies are enabling engineers to push the boundaries even further. Artificial intelligence presents an opportunity to create an algorithm that learns from the behaviour of searchers and, ultimately, refines itself with minimal human input, if any. With the help of AI, search engines can consider factors such as your location, your search history, your favourite websites, and what other users click on for a similar query to give you the most appropriate search results for your individual needs. The AI can then analyse your behaviour in response to a particular search and how you interact with the results, and then improve what it offers the next time someone makes the same search.

Search Engine Optimisation refers to the science of making sure that your website comes on top of the search results to attract your target audience. SEO has its own syntax- it does not involve stuffing keywords or having many product pages to spank up your ranking. If you do this, the chances are high that you will not achieve the desired results. Your pages should have a mobile-friendly interface and feature relevant keywords. Every now and then, SEO techniques keep changing.

If you run a website and would like to research keywords, there are some best practices that are recommended to help you find the best keyword phrases to use. In this article, we'll focus on the several research methods and provide hints on how to carry out effective keyword research. Keep in mind that getting ranked for a keyword phrase depends on how relevant the content is around the much sought-after phrase. Choosing the right keywords can easily get overwhelming in your quest to create the best SEO strategies. That is why we came up with this step by step guide that you can use to find the best keywords for your website.

At Las Vegas gadget show CES, Google is showcasing new features of its voice-enabled digital assistant including a language translator. We use this phrase every day. Once upon a time, the word "Google" just indicated a very long number. That extends to physical products as well. But the world's most powerful search engine can do more than find things.

Google's logo is seen on a building in Irvine, California. We use this phrase every day. Once upon a time, the word "Google" just indicated a very long number. That extends to physical products as well, like these 20 incredibly useful Google products and services you probably didn't know about until now. But the world's most powerful search engine can do more than find things.

Supervised machine learning methods usually require a large set of labeled examples for model training. However, in many real applications, there are plentiful unlabeled data but limited labeled data; and the acquisition of labels is costly. Active learning (AL) reduces the labeling cost by iteratively selecting the most valuable data to query their labels from the annotator. This article introduces a Python toobox ALiPy for active learning. ALiPy provides a module based implementation of active learning framework, which allows users to conveniently evaluate, compare and analyze the performance of active learning methods. In the toolbox, multiple options are available for each component of the learning framework, including data process, active selection, label query, results visualization, etc. In addition to the implementations of more than 20 state-of-the-art active learning algorithms, ALiPy also supports users to easily configure and implement their own approaches under different active learning settings, such as AL for multi-label data, AL with noisy annotators, AL with different costs and so on. The toolbox is well-documented and open-source on Github, and can be easily installed through PyPI.