{"id":20689,"date":"2020-02-10T11:20:50","date_gmt":"2020-02-10T16:20:50","guid":{"rendered":"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/"},"modified":"2022-02-17T17:58:07","modified_gmt":"2022-02-17T22:58:07","slug":"bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020","status":"publish","type":"post","link":"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/","title":{"rendered":"Bloomberg Researchers Explore Adversarial Learning for Keyphrase Generation at AAAI 2020"},"content":{"rendered":"
\n \n\t\n\t\n\t
\n\t\t\n\t\t\t
\n\t
\n \n

Generative adversarial networks (GANs) are a relatively new class of machine learning systems. First introduced in 2014, these deep neural nets have mostly been used to create lifelike images and videos. It is only since about 2017 that GANs have been used for text generation.<\/p>\n

In a paper entitled \u201cKeyphrase Generation for Scientific Articles Using GANs<\/a>,\u201d which was presented at the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20)<\/a> in New York City (February 7-12, 2020), a team of research scientists from Bloomberg\u2019s AI Group have shown for the first time that GANs can be used to generate keyphrases from scientific abstracts.<\/p>\n\n<\/div>\n

\n \"\"\"\"\n \n<\/figure>\n
\n \n

The Bloomberg team completed this research in collaboration with students and researchers at the Multimodal Digital Media Analysis (MIDAS) Lab<\/a> at Indraprastha Institute of Information Technology, Delhi (IIIT-Delhi), where Debanjan Mahata, one of the Bloomberg researchers, is an adjunct faculty member.<\/p>\n

\u201cWe are the first ones exploring the use of GANs in keyphrase generation,\u201d says Haimin (Raymond) Zhang, one of the Bloomberg research scientists who co-authored the paper.<\/p>\n

The GAN structure is unique in that it pits two neural networks against each other. One network, called the generator, comes up with possible answers to a problem. The second network, called a discriminator, tries to distinguish those answers from ones created by a human. Over time, the generator learns from the discriminator, and comes up with candidates that are ever closer to those proposed by a person. Intuitively, GANs make sense: They use a machine to teach a machine.<\/p>\n

\u201cPeople still have some doubts about the use of GANs to generate text,\u201d notes Rakesh Gosangi, another Bloomberg researcher who co-authored the paper. \u201cBut, in problems specifically related to the summarization of texts, GANs have had some promising results.\u201d<\/p>\n

\u201cThere was a clear opportunity to try this out on text, and specifically in keyphrase generation,\u201d says Mahata. Keyphrase generation, or the process of coming up with natural language phrases that accurately represent a larger body of text, is a foundational task in natural language processing.<\/p>\n

The Bloomberg team developed the architecture for the GANs, and advised students Avinash Swaminathan and Raj Kuwar Gupta who were interning at MIDAS Lab, which is led by Dr. Rajiv Ratn Shah, Assistant Professor in the Department of Computer Science and Engineering at IIIT-Delhi.<\/p>\n\n<\/div>\n

\n \"Avinash\"Avinash\n
Avinash Swaminathan showcases “Keyphrase Generation for Scientific Articles Using GANs” at the AAAI 2020 poster session.<\/figcaption>\n<\/figure>\n
\n\t
\n<\/div>\n
\n \n

The GANs were put to work on four different data sets, containing thousands of abstracts of scientific papers, their titles, and their human-curated keyphrases. The model obtains state-of-the-art results in terms of accuracy, but it does better in terms of keyphrase diversity in three out of four datasets.<\/p>\n

One of the main challenges in using GANs for this task lies in so-called backpropagation, a technique used for training neural networks. While used widely in training GANs, backpropagation cannot be easily adapted to text because the outputs from the generator are discrete, in that they are not differentiable. To address this problem, they use reinforcement learning to train the discriminator.<\/p>\n

Another challenge, says Zhang, is to use the right discriminator. For this research, the Bloomberg team designed the discriminator from scratch. Zhang sees a lot of opportunity to innovate on this discriminator, possibly by changing the way it provides rewards to the generator. Another option would be to use multiple discriminators to teach the generator, or to combine them in different ways. The research team is already at work trying to make the deep neural nets more effective.<\/p>\n

\u201cThis is an important problem that needed some attention and had to be tried,\u201d says Mahata.<\/p>\n

Added Zhang, \u201cBy doing this initial analysis and generating these preliminary results, we can see the potential and are working on additional research to further establish whether GANs are the right approach for this problem.\u201d<\/p>\n\n<\/div>\n

\n\t
\n<\/div>\n
\n \n

Read some of the other Bloomberg co-authored research papers presented at AAAI 2020 and additional peer-reviewed academic conferences at journals <\/em>here<\/em><\/a>.<\/em><\/p>\n\n<\/div>\n\n<\/div>\n\n\n\t\t\n\t<\/div>\n<\/div>\n\n","protected":false},"excerpt":{"rendered":"

Some peliminary research demonstrates how GANs can be used to generate keyphrases from scientific abstracts<\/p>\n","protected":false},"author":184,"featured_media":19008,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1466],"tags":[1717,1472,1718,1716,1704,1719,1587,1571,1477,1570],"class_list":["post-20689","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tech-at-bloomberg","tag-aaai","tag-data-science","tag-gans","tag-keyphrase","tag-keywords","tag-midas-lab","tag-neural-network","tag-rd","tag-research","tag-research-and-development"],"yoast_head":"\nBloomberg Researchers Explore Adversarial Learning for Keyphrase Generation at AAAI 2020 | Bloomberg LP<\/title>\n<meta name=\"description\" content=\"Researchers from Bloomberg's AI group published a paper titled \u201cKeyphrase Generation for Scientific Articles Using GANs\u201d at AAAI 2020.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Bloomberg Researchers Explore Adversarial Learning for Keyphrase Generation at AAAI 2020 | Bloomberg LP\" \/>\n<meta property=\"og:description\" content=\"Researchers from Bloomberg's AI group published a paper titled \u201cKeyphrase Generation for Scientific Articles Using GANs\u201d at AAAI 2020.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/\" \/>\n<meta property=\"og:site_name\" content=\"Bloomberg L.P.\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/bloomberglp\/\" \/>\n<meta property=\"article:published_time\" content=\"2020-02-10T16:20:50+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2022-02-17T22:58:07+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/assets.bbhub.io\/company\/sites\/51\/2020\/02\/AAAI-20-Paper-Header.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1116\" \/>\n\t<meta property=\"og:image:height\" content=\"601\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"chaas30\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/assets.bbhub.io\/company\/sites\/51\/2020\/02\/AAAI-20-Paper-Header.jpg\" \/>\n<meta name=\"twitter:creator\" content=\"@bloomberg\" \/>\n<meta name=\"twitter:site\" content=\"@bloomberg\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"chaas30\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/\",\"url\":\"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/\",\"name\":\"Bloomberg Researchers Explore Adversarial Learning for Keyphrase Generation at AAAI 2020 | Bloomberg LP\",\"isPartOf\":{\"@id\":\"https:\/\/www.bloomberg.com\/company\/#website\"},\"datePublished\":\"2020-02-10T16:20:50+00:00\",\"dateModified\":\"2022-02-17T22:58:07+00:00\",\"author\":{\"@id\":\"https:\/\/www.bloomberg.com\/company\/#\/schema\/person\/4d4a18aae79d6fcc1ea98181a906905e\"},\"description\":\"Researchers from Bloomberg's AI group published a paper titled \u201cKeyphrase Generation for Scientific Articles Using GANs\u201d at AAAI 2020.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":\"1\",\"name\":\"Home\",\"item\":\"https:\/\/www.bloomberg.com\/company\/\"},{\"@type\":\"ListItem\",\"position\":\"2\",\"name\":\"Bloomberg Researchers Explore Adversarial Learning for Keyphrase Generation at AAAI 2020\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.bloomberg.com\/company\/#website\",\"url\":\"https:\/\/www.bloomberg.com\/company\/\",\"name\":\"Bloomberg L.P.\",\"description\":\"Bloomberg L.P. is the leader in global business and financial information, enabling customers to make smarter, faster, more informed business decisions.\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.bloomberg.com\/company\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.bloomberg.com\/company\/#\/schema\/person\/4d4a18aae79d6fcc1ea98181a906905e\",\"name\":\"Bloomberg L.P.\",\"url\":\"https:\/\/www.bloomberg.com\/company\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Bloomberg Researchers Explore Adversarial Learning for Keyphrase Generation at AAAI 2020 | Bloomberg LP","description":"Researchers from Bloomberg's AI group published a paper titled \u201cKeyphrase Generation for Scientific Articles Using GANs\u201d at AAAI 2020.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/","og_locale":"en_US","og_type":"article","og_title":"Bloomberg Researchers Explore Adversarial Learning for Keyphrase Generation at AAAI 2020 | Bloomberg LP","og_description":"Researchers from Bloomberg's AI group published a paper titled \u201cKeyphrase Generation for Scientific Articles Using GANs\u201d at AAAI 2020.","og_url":"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/","og_site_name":"Bloomberg L.P.","article_publisher":"https:\/\/www.facebook.com\/bloomberglp\/","article_published_time":"2020-02-10T16:20:50+00:00","article_modified_time":"2022-02-17T22:58:07+00:00","og_image":[{"width":1116,"height":601,"url":"https:\/\/assets.bbhub.io\/company\/sites\/51\/2020\/02\/AAAI-20-Paper-Header.jpg","type":"image\/jpeg"}],"author":"chaas30","twitter_card":"summary_large_image","twitter_image":"https:\/\/assets.bbhub.io\/company\/sites\/51\/2020\/02\/AAAI-20-Paper-Header.jpg","twitter_creator":"@bloomberg","twitter_site":"@bloomberg","twitter_misc":{"Written by":"chaas30","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/","url":"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/","name":"Bloomberg Researchers Explore Adversarial Learning for Keyphrase Generation at AAAI 2020 | Bloomberg LP","isPartOf":{"@id":"https:\/\/www.bloomberg.com\/company\/#website"},"datePublished":"2020-02-10T16:20:50+00:00","dateModified":"2022-02-17T22:58:07+00:00","author":{"@id":"https:\/\/www.bloomberg.com\/company\/#\/schema\/person\/4d4a18aae79d6fcc1ea98181a906905e"},"description":"Researchers from Bloomberg's AI group published a paper titled \u201cKeyphrase Generation for Scientific Articles Using GANs\u201d at AAAI 2020.","breadcrumb":{"@id":"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.bloomberg.com\/company\/stories\/bloomberg-researchers-explore-adversarial-learning-for-keyphrase-generation-at-aaai-2020\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":"1","name":"Home","item":"https:\/\/www.bloomberg.com\/company\/"},{"@type":"ListItem","position":"2","name":"Bloomberg Researchers Explore Adversarial Learning for Keyphrase Generation at AAAI 2020"}]},{"@type":"WebSite","@id":"https:\/\/www.bloomberg.com\/company\/#website","url":"https:\/\/www.bloomberg.com\/company\/","name":"Bloomberg L.P.","description":"Bloomberg L.P. is the leader in global business and financial information, enabling customers to make smarter, faster, more informed business decisions.","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.bloomberg.com\/company\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.bloomberg.com\/company\/#\/schema\/person\/4d4a18aae79d6fcc1ea98181a906905e","name":"Bloomberg L.P.","url":"https:\/\/www.bloomberg.com\/company"}]}},"featured_image_rendered":"<img srcset='https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&type=webp&url=https:\/\/assets.bbhub.io\/company\/sites\/51\/2020\/02\/AAAI-20-Paper-Header.jpg 1116w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&type=webp&url=https:\/\/assets.bbhub.io\/company\/sites\/51\/2020\/02\/AAAI-20-Paper-Header.jpg 300w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&type=webp&url=https:\/\/assets.bbhub.io\/company\/sites\/51\/2020\/02\/AAAI-20-Paper-Header.jpg 768w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&type=webp&url=https:\/\/assets.bbhub.io\/company\/sites\/51\/2020\/02\/AAAI-20-Paper-Header.jpg 1024w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&type=webp&url=https:\/\/assets.bbhub.io\/company\/sites\/51\/2020\/02\/AAAI-20-Paper-Header.jpg 170w, https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&type=webp&url=https:\/\/assets.bbhub.io\/company\/sites\/51\/2020\/02\/AAAI-20-Paper-Header.jpg 140w' src='https:\/\/assets.bbhub.io\/image\/v1\/resize?width=auto&type=webp&url=https:\/\/assets.bbhub.io\/company\/sites\/51\/2020\/02\/AAAI-20-Paper-Header.jpg' alt='' \/>","category_info":{"name":"Tech At Bloomberg","blog_landing_name":"Tech At Bloomberg"},"_links":{"self":[{"href":"https:\/\/www.bloomberg.com\/company\/wp-json\/wp\/v2\/posts\/20689","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.bloomberg.com\/company\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bloomberg.com\/company\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bloomberg.com\/company\/wp-json\/wp\/v2\/users\/184"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bloomberg.com\/company\/wp-json\/wp\/v2\/comments?post=20689"}],"version-history":[{"count":2,"href":"https:\/\/www.bloomberg.com\/company\/wp-json\/wp\/v2\/posts\/20689\/revisions"}],"predecessor-version":[{"id":21099,"href":"https:\/\/www.bloomberg.com\/company\/wp-json\/wp\/v2\/posts\/20689\/revisions\/21099"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.bloomberg.com\/company\/wp-json\/wp\/v2\/media\/19008"}],"wp:attachment":[{"href":"https:\/\/www.bloomberg.com\/company\/wp-json\/wp\/v2\/media?parent=20689"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bloomberg.com\/company\/wp-json\/wp\/v2\/categories?post=20689"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bloomberg.com\/company\/wp-json\/wp\/v2\/tags?post=20689"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}