Raman Chandrasekar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Raman Chandrasekar has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
Abhishek Gupta
Georgia Institute of Technology, Atlanta, USA
3 shared publicationsChris Quirk
Microsoft Research, Redmond, USA
3 shared publicationsHao Ma
The Chinese University of Hong Kong, Hong Kong, Hong Kong
3 shared publications- Kenneth Ward Church
Northeastern University - Boston Campus
3 shared publications B. Srinivas
2 shared publications- S Ramani2 shared publications
Latest Publications
- Open Access
- 1 July 2024
- Published by Cambridge University Press (CUP) in Natural Language Engineering
- Vol. 30 (4) , 870-881
Emerging trends: a gentle introduction to RAG
Retrieval-augmented generation (RAG) adds a simple but powerful feature to chatbots, the ability to upload files just-in-time. Chatbots are trained on large quantities of public data. The ability to upload files just-in-time makes it possible to reduce hallucinations by filling in gaps in the knowledge base that go beyond the public training data such as private data and recent events. For example, in a customer service scenario, with RAG, we can upload your private bill and then the bot can discuss questions about your bill as opposed to generic FAQ questions about bills in general. This tutorial will show how to upload files and generate responses to prompts; see https://github.com/kwchurch/RAG for multiple solutions based on tools from OpenAI, LangChain, HuggingFace transformers and VecML.
- 1 July 2024
- Published by Cambridge University Press (CUP) in Natural Language Engineering
- Vol. 30 (4) , 870-881
Open AccessEmerging trends: a gentle introduction to RAG
Retrieval-augmented generation (RAG) adds a simple but powerful feature to chatbots, the ability to upload files just-in-time. Chatbots are trained on large quantities of public data. The ability to upload files just-in-time makes it possible to reduce hallucinations by filling in gaps in the knowledge base that go beyond the public training data such as private data and recent events. For example, in a customer service scenario, with RAG, we can upload your private bill and then the bot can discuss questions about your bill as opposed to generic FAQ questions about bills in general. This tutorial will show how to upload files and generate responses to prompts; see https://github.com/kwchurch/RAG for multiple solutions based on tools from OpenAI, LangChain, HuggingFace transformers and VecML.
- Open Access
- 19 May 2023
- Published by Cambridge University Press (CUP) in Natural Language Engineering
- Vol. 29 (3) , 824-841
Emerging trends: Risks 3.0 and proliferation of spyware to 50,000 cell phones
Our last emerging trend article introduced Risks 1.0 (fairness and bias) and Risks 2.0 (addictive, dangerous, deadly, and insanely profitable). This article introduces Risks 3.0 (spyware and cyber weapons). Risks 3.0 are less profitable, but more destructive. We will summarize two recent books, Pegasus: How a Spy in Your Pocket Threatens the End of Privacy, Dignity, and Democracy and This is How They Tell Me the World Ends: The Cyberweapons Arms Race. The first book starts with a leak of 50,000 phone numbers, targeted by spyware named Pegasus. Pegasus uses a zero-click exploit to obtain root access to your phone, taking control of the microphone, camera, GPS, text messages, etc. The list of 50,000 numbers includes journalists, politicians, and academics, as well as their friends and family. Some of these people have been murdered. The second book describes the history of cyber weapons such as Stuxnet, which is described as crossing the Rubicon. In the short term, it sets back Iran’s nuclear program for less than the cost of conventional weapons, but it did not take long for Iran to build the fourth-biggest cyber army in the world. As spyware continues to proliferate, we envision a future dystopia where everyone spies on everyone. Nothing will be safe from hacking: not your identity, or your secrets, or your passwords, or your bank accounts. When the endpoints (phones) have been compromised, technologies such as end-to-end encryption and multi-factor authentication offer a false sense of security; encryption and authentication are as pointless as closing the proverbial barn door after the fact. To address Risks 3.0, journalists are using the tools of their trade to raise awareness in the court of public opinion. We should do what we can to support them. This paper is a small step in that direction.
- 19 May 2023
- Published by Cambridge University Press (CUP) in Natural Language Engineering
- Vol. 29 (3) , 824-841
Open AccessEmerging trends: Risks 3.0 and proliferation of spyware to 50,000 cell phones
Our last emerging trend article introduced Risks 1.0 (fairness and bias) and Risks 2.0 (addictive, dangerous, deadly, and insanely profitable). This article introduces Risks 3.0 (spyware and cyber weapons). Risks 3.0 are less profitable, but more destructive. We will summarize two recent books, Pegasus: How a Spy in Your Pocket Threatens the End of Privacy, Dignity, and Democracy and This is How They Tell Me the World Ends: The Cyberweapons Arms Race. The first book starts with a leak of 50,000 phone numbers, targeted by spyware named Pegasus. Pegasus uses a zero-click exploit to obtain root access to your phone, taking control of the microphone, camera, GPS, text messages, etc. The list of 50,000 numbers includes journalists, politicians, and academics, as well as their friends and family. Some of these people have been murdered. The second book describes the history of cyber weapons such as Stuxnet, which is described as crossing the Rubicon. In the short term, it sets back Iran’s nuclear program for less than the cost of conventional weapons, but it did not take long for Iran to build the fourth-biggest cyber army in the world. As spyware continues to proliferate, we envision a future dystopia where everyone spies on everyone. Nothing will be safe from hacking: not your identity, or your secrets, or your passwords, or your bank accounts. When the endpoints (phones) have been compromised, technologies such as end-to-end encryption and multi-factor authentication offer a false sense of security; encryption and authentication are as pointless as closing the proverbial barn door after the fact. To address Risks 3.0, journalists are using the tools of their trade to raise awareness in the court of public opinion. We should do what we can to support them. This paper is a small step in that direction.
- Open Access
- 19 December 2022
- Published by Cambridge University Press (CUP) in Natural Language Engineering
- Vol. 29 (2) , 483-508
Emerging trends: Unfair, biased, addictive, dangerous, deadly, and insanely profitable
There has been considerable work recently in the natural language community and elsewhere on Responsible AI. Much of this work focuses on fairness and biases (henceforth Risks 1.0), following the 2016 best seller:Weapons of Math Destruction. Two books published in 2022, The Chaos MachineandLike, Comment, Subscribe, raise additional risks to public health/safety/security such as genocide, insurrection, polarized politics, vaccinations (henceforth, Risks 2.0). These books suggest that the use of machine learning to maximize engagement in social media has created a Frankenstein Monster that is exploiting human weaknesses with persuasive technology, the illusory truth effect, Pavlovian conditioning, and Skinner’s intermittent variable reinforcement. Just as we cannot expect tobacco companies to sell fewer cigarettes and prioritize public health ahead of profits, so too, it may be asking too much of companies (and countries) to stop trafficking in misinformation given that it is so effective and so insanely profitable (at least in the short term). Eventually, we believe the current chaos will end, like the lawlessness in Wild West, because chaos is bad for business. As computer scientists, this paper will summarize criticisms from other fields and focus on implications for computer science; we will not attempt to contribute to those other fields. There is quite a bit of work in computer science on these risks, especially on Risks 1.0 (bias and fairness), but more work is needed, especially on Risks 2.0 (addictive, dangerous, and deadly).
- 19 December 2022
- Published by Cambridge University Press (CUP) in Natural Language Engineering
- Vol. 29 (2) , 483-508
Open AccessEmerging trends: Unfair, biased, addictive, dangerous, deadly, and insanely profitable
There has been considerable work recently in the natural language community and elsewhere on Responsible AI. Much of this work focuses on fairness and biases (henceforth Risks 1.0), following the 2016 best seller:Weapons of Math Destruction. Two books published in 2022, The Chaos MachineandLike, Comment, Subscribe, raise additional risks to public health/safety/security such as genocide, insurrection, polarized politics, vaccinations (henceforth, Risks 2.0). These books suggest that the use of machine learning to maximize engagement in social media has created a Frankenstein Monster that is exploiting human weaknesses with persuasive technology, the illusory truth effect, Pavlovian conditioning, and Skinner’s intermittent variable reinforcement. Just as we cannot expect tobacco companies to sell fewer cigarettes and prioritize public health ahead of profits, so too, it may be asking too much of companies (and countries) to stop trafficking in misinformation given that it is so effective and so insanely profitable (at least in the short term). Eventually, we believe the current chaos will end, like the lawlessness in Wild West, because chaos is bad for business. As computer scientists, this paper will summarize criticisms from other fields and focus on implications for computer science; we will not attempt to contribute to those other fields. There is quite a bit of work in computer science on these risks, especially on Risks 1.0 (bias and fairness), but more work is needed, especially on Risks 2.0 (addictive, dangerous, and deadly).
- 1 March 2014
- Published by Springer Nature in Resonance
- Vol. 19 (3) , 222-241
Elementary? Question answering, IBM’s Watson, and the Jeopardy! challenge
- 1 March 2014
- Published by Springer Nature in Resonance
- Vol. 19 (3) , 222-241
Elementary? Question answering, IBM’s Watson, and the Jeopardy! challenge
- Open Access
- 11 January 2011
- Published by Wiley in Proceedings of the American Society for Information Science and Technology
- Vol. 48 (1) , 1-10
News Sync: Enabling scenario‐based news exploration
News consumption patterns are changing, but the tools to view news are dominated by portal and search approaches. In this paper, we suggest using elements of search, visualization, natural language processing, and machine learning to provide a more captivating, sticky news consumption experience. We propose a novel use‐case driven approach to present news and present News Sync, a system that addresses three specific news exploration scenarios where a user wants to catch up on news from a particular time period, keep in touch with news from specific locations, or follow the lives of celebrities. The news experience is enhanced by clustering news articles and allowing users to interact with and share stories of interest, and filter results on specific dimensions such as time, location, and key entities. User deployment studies suggest a distinct preference for an interface that supports exploration and visualization of news articles.
- 11 January 2011
- Published by Wiley in Proceedings of the American Society for Information Science and Technology
- Vol. 48 (1) , 1-10
Open AccessNews Sync: Enabling scenario‐based news exploration
News consumption patterns are changing, but the tools to view news are dominated by portal and search approaches. In this paper, we suggest using elements of search, visualization, natural language processing, and machine learning to provide a more captivating, sticky news consumption experience. We propose a novel use‐case driven approach to present news and present News Sync, a system that addresses three specific news exploration scenarios where a user wants to catch up on news from a particular time period, keep in touch with news from specific locations, or follow the lives of celebrities. The news experience is enhanced by clustering news articles and allowing users to interact with and share stories of interest, and filter results on specific dimensions such as time, location, and key entities. User deployment studies suggest a distinct preference for an interface that supports exploration and visualization of news articles.
- Open Access
- 1 November 2010
- Published by Wiley in Proceedings of the American Society for Information Science and Technology
- Vol. 47 (1) , 1-2
Domain‐specific entity and relationship extraction from query logs
Extracting domain‐specific entity‐relationships is useful in a wide variety of applications. For example, knowledge of camera companies and their product hierarchies can help photography‐related search engines greatly in improving search interfaces. In this paper we describe an unsupervised approach for extracting prominent domain specific entity‐relationships from query logs. Our approach is complementary to other entity extraction methods. It first constructs a weighted directed graph with query keywords as nodes and then prunes out edges not likely to represent useful relations. Experiments with multiple domains show promising results with over 80% precision.
- 1 November 2010
- Published by Wiley in Proceedings of the American Society for Information Science and Technology
- Vol. 47 (1) , 1-2
Open AccessDomain‐specific entity and relationship extraction from query logs
Extracting domain‐specific entity‐relationships is useful in a wide variety of applications. For example, knowledge of camera companies and their product hierarchies can help photography‐related search engines greatly in improving search interfaces. In this paper we describe an unsupervised approach for extracting prominent domain specific entity‐relationships from query logs. Our approach is complementary to other entity extraction methods. It first constructs a weighted directed graph with query keywords as nodes and then prunes out edges not likely to represent useful relations. Experiments with multiple domains show promising results with over 80% precision.
- Open Access
- 18 August 2010
- Published by Association for Computing Machinery (ACM)
- p. 75-84
Using query context models to construct topical search engines
- 18 August 2010
- Published by Association for Computing Machinery (ACM)
- p. 75-84
Open AccessUsing query context models to construct topical search engines
- Open Access
- 19 July 2010
- Published by Association for Computing Machinery (ACM)
- p. 811-812
Exploring the use of labels to shortcut search trails
Search trails comprising queries and Web page views are created as searchers engage in information-seeking activity online. During known-item search (where the objective may be to locate a target Web page), searchers may waste valuable time repeatedly reformulating queries as they attempt to locate an elusive page. Trail shortcuts help users bypass unnecessary queries and get them to their desired destination faster. In this poster we present a comparative oracle study of techniques to shortcut sub-optimal search trails using labels derived from social bookmarking, anchor text, query logs, and a human-computation game. We show that labels can help users reach target pages efficiently, that the label sources perform differently, and that shortcuts are potentially most useful when the target is challenging to find.
- 19 July 2010
- Published by Association for Computing Machinery (ACM)
- p. 811-812
Open AccessExploring the use of labels to shortcut search trails
Search trails comprising queries and Web page views are created as searchers engage in information-seeking activity online. During known-item search (where the objective may be to locate a target Web page), searchers may waste valuable time repeatedly reformulating queries as they attempt to locate an elusive page. Trail shortcuts help users bypass unnecessary queries and get them to their desired destination faster. In this poster we present a comparative oracle study of techniques to shortcut sub-optimal search trails using labels derived from social bookmarking, anchor text, query logs, and a human-computation game. We show that labels can help users reach target pages efficiently, that the label sources perform differently, and that shortcuts are potentially most useful when the target is challenging to find.
- Open Access
- 27 May 2010
- Published by Association for Computing Machinery (ACM) in ACM SIGKDD Explorations Newsletter
- Vol. 11 (2) , 80-83
A report on the human computation workshop (HComp 2009)
The first Human Computation Workshop (HComp2009) was held on June 28th, 2009, in Paris, France, collocated with SIGKDD 2009. This report summarizes the workshop, with details of the papers, demos and posters presented. The report also includes common themes, issues, and open questions that came up in the workshop.
- 27 May 2010
- Published by Association for Computing Machinery (ACM) in ACM SIGKDD Explorations Newsletter
- Vol. 11 (2) , 80-83
Open AccessA report on the human computation workshop (HComp 2009)
The first Human Computation Workshop (HComp2009) was held on June 28th, 2009, in Paris, France, collocated with SIGKDD 2009. This report summarizes the workshop, with details of the papers, demos and posters presented. The report also includes common themes, issues, and open questions that came up in the workshop.
- Open Access
- 2 November 2009
- Published by Association for Computing Machinery (ACM)
- p. 275-284
Improving search engines using human computation games
- 2 November 2009
- Published by Association for Computing Machinery (ACM)
- p. 275-284
Open AccessImproving search engines using human computation games