Episode Summary: Natural Language Processing (NLP) can be applied to tasks such as customer service handling or in chatbots to answer fact based questions. Another emerging application for NLP is in content marketing and content production.
In this episode of AI in industry, we talk to Tomás Ratia García-Oliveros, the co-founder and CEO founder of Frase.io, a Boston based startup which focuses on NLP for content marketing and content creation. Tomas explores how NLP platforms are now able to summarize resources on the web, perform contextual search, and help writers and content marketers streamline their processes.
Subscribe to our AI in Industry Podcast with your favorite podcast service:
Guest: Tomás Ratia García-Oliveros, Co-Founder & CEO at Frase.io
Expertise: Natural language processing, AI applications for content marketing
Brief Recognition: Before founding Frase.io, Tomas was co-founder and CEO at Dat Ventures, an accelerator for international startups. He has a master’s degree from Harvard and was visiting researcher at the Sustainable Technologies and Health Program within the Center for Health and the Global Environment at the Harvard T.H. Chan School of Public Health.
Big Idea
Tomás talks about how AI is streamlining the content creation and content research processes today. Search engine platforms like Google have already integrated basic extractive summarizing and can answering very specific fact-based questions with defined boundaries.
With improvements in AI technology, newer NLP platforms can augment human researchers by creating multi-page summarized articles for even open-domain questions like ‘what is the future of AI technology going to look like?’ or ‘How is AI affecting the healthcare industry?’ According to Tomás , two of the major app
lications for NLP platforms in content creation, currently, are summarizing and research assistance.
(Readers with a deeper interest in NLP applications in business may enjoy our full article on this topic, titled: “Natural Language Processing – Current Applications and Future Possibilities“.)
How NLP Summarization Works:
- Summarizing content through the use of NLP can be either “extractive” (where the system distills text into just the most relevant parts, cutting out the rest) or “abstractive” (which is machine learning based, and involves AI coming up with it’s own “wording” for summarizing a given text).
- As opposed to what Google does in summarizing fact based questions, more advanced contextual summarizing would involve condensing information from the top 50 search results, finding meaningful relationships between these results and then extracting the most appropriate sentences from within those relationships.
- Over time, the AI also learns the best order in which these sentences can be arranged to form a meaningful article.
- For example, searching for ‘What is AI?’ would automatically show the writer summarized links for deep learning, NLP etc. The aim of extractive summarizing here is to augment a human writers capabilities by giving them an outline generation tool to build upon.
NLP Uses for Content Research Assistance:
A key step in content marketing involves implementing SEO best practices once the content has been produced. Tomás claims that Frase.io’s NLP platform can assist researchers by giving them a summary which has already been optimized from the top search results.
- In research assistance applications, NLP platforms can combine word processors with search engines into one progressively learning tool. Essentially, the platform offers a word processor that can learn from things that you write and can research contextual topics in the background and give you links for the topic etc.
- Once the writer is on the word processor, the platform will give them an outline of topics relevant to the research being conducted.
- The core AI tenet of this technology is topic modelling, which involves identification of how a topic evolves as you write. A typical extractive snippet from each search result would include 3 points of summary, one statistic and a last point capturing some of the key words related to the topic.
The Future of NLP in Content Marketing:
- We can expect AIs to become proficient at both extractive and abstractive summarization in the near future. In terms of capabilities for AIs, text understanding and reading comprehension are also very active research domains.
- Another development we will see more of is voice-based NLP platforms which will be capable of answering not just fact based questions, but more ‘humanized’ open ended questions.
- Although there are already platforms which are contextually aware enough to answer open ended questions, they remain a premium product for now. Contextual summarization with voice and language understanding are somewhat inevitable.
- In the sightly far future the technology could be integrated with brain interfaces to record ideas or with augmented reality wearable devices.
Interview Highlights with Tomás from Frase.io
The main questions Tomás answered during our interview are listed below. Listeners can use the embedded podcast player (at the top of this post) to jump ahead to sections they might be interested in:
- (2.57) Where does NLP help in the content creation and content marketing today?
- (11.38) How does an NLP system summarize text?
- (18.18) What facets of NLP will become ubiquitous for content production in the future? What are business leaders going to expect from NLP platforms in the future?
Subscribe to our AI in Industry Podcast with your favorite podcast service:
Header image credit: The Balance
