TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: API to detect abusive content in 27 languages

5 pointsby vadimbermanover 6 years ago
Hello HN,<p>I am Vadim of Tisane Labs (<a href="http:&#x2F;&#x2F;tisane.ai" rel="nofollow">http:&#x2F;&#x2F;tisane.ai</a>). We build text analytics APIs.<p>My natural language processing journey started over a decade ago, when I built an NLP engine with an emphasis on scalability across languages. The engine served as a foundation of a startup I cofounded in 2010 (<a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;LinguaSys" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;LinguaSys</a>), which had Mark Cuban as an investor and was acquired in 2015.<p>Utilizing our expertise, we&#x27;re trying to tackle one of the most painful issues with the Internet today: abusive content. Hate speech, sexual harassment, cyberbullying are difficult to detect. Today&#x27;s solutions mostly look for obscenities; correlation with training datasets only works with limited demos as the patterns of abuse are too many. Hate speech is more than just ethnic slurs.<p>The API is a generic analytical engine, so it may be used for other purposes as well, but abusive content is our main focus.<p>We&#x27;d love to hear your feedback, ideas, wishes, and complaints.

1 comment

web64over 6 years ago
Looks interesting, but I couldn&#x27;t get the code samples to work. Would be good to have all languages available in the demo on the website.
评论 #17977999 未加载