12 code implementations • 28 Nov 2016 • Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang
The size of the dataset and the fact that the questions are derived from real user search queries distinguishes MS MARCO from other well-known publicly available datasets for machine reading comprehension and question-answering.
1 code implementation • 11 May 2020 • Sebastian Hofstätter, Hamed Zamani, Bhaskar Mitra, Nick Craswell, Allan Hanbury
In this work, we propose a local self-attention which considers a moving window over the document terms and for each term attends only to other terms in the same window.
1 code implementation • 18 Mar 2019 • Bhaskar Mitra, Nick Craswell
We propose several small modifications to Duet---a deep neural ranking model---and evaluate the updated model on the MS MARCO passage ranking task.
Ranked #4 on Passage Re-Ranking on MS MARCO
1 code implementation • Proceedings of the 26th International Conference on World Wide Web, WWW '17 2017 • Bhaskar Mitra, Fernando Diaz, Nick Craswell
Models such as latent semantic analysis and those based on neural embeddings learn distributed representations of text, and match the query against the document in the latent semantic space.
2 code implementations • 17 Mar 2020 • Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, Ellen M. Voorhees
The Deep Learning Track is a new track for TREC 2019, with the goal of studying ad hoc ranking in a large data regime.
1 code implementation • 20 Jul 2020 • Bhaskar Mitra, Sebastian Hofstatter, Hamed Zamani, Nick Craswell
In this work, we extend the TK architecture to the full retrieval setting by incorporating the query term independence assumption.
1 code implementation • 15 Feb 2021 • Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos
This is the second year of the TREC Deep Learning Track, with the goal of studying ad hoc ranking in the large training data regime.
1 code implementation • 10 Dec 2019 • Bhaskar Mitra, Nick Craswell
This report discusses three submissions based on the Duet architecture to the Deep Learning track at TREC 2019.
1 code implementation • 20 May 2021 • Sebastian Hofstätter, Bhaskar Mitra, Hamed Zamani, Nick Craswell, Allan Hanbury
An emerging recipe for achieving state-of-the-art effectiveness in neural document re-ranking involves utilizing large pre-trained language models - e. g., BERT - to evaluate all individual passages in the document and then aggregating the outputs by pooling or additional Transformer layers.
1 code implementation • 22 Feb 2023 • Fernando Diaz, Bhaskar Mitra
In light of this debate, we reflect on the measurement of recall in rankings from a formal perspective.
1 code implementation • 10 May 2021 • Daniel Cohen, Bhaskar Mitra, Oleg Lesota, Navid Rekabsaz, Carsten Eickhoff
In any ranking system, the retrieval model outputs a single score for a document based on its belief on how relevant it is to a given search query.
1 code implementation • 29 Apr 2022 • Haolun Wu, Bhaskar Mitra, Chen Ma, Fernando Diaz, Xue Liu
Prior research on exposure fairness in the context of recommender systems has focused mostly on disparities in the exposure of individual or groups of items to individual users of the system.
1 code implementation • 29 Dec 2022 • Haolun Wu, Yansen Zhang, Chen Ma, Fuyuan Lyu, Bowei He, Bhaskar Mitra, Xue Liu
Diversifying return results is an important research topic in retrieval systems in order to satisfy both the various interests of customers and the equal market exposure of providers.
no code implementations • 20 Jul 2017 • Navid Rekabsaz, Bhaskar Mitra, Mihai Lupu, Allan Hanbury
As an alternative, explicit word representations propose vectors whose dimensions are easily interpretable, and recent methods show competitive performance to the dense vectors.
no code implementations • 17 Oct 2017 • Christophe Van Gysel, Bhaskar Mitra, Matteo Venanzi, Roy Rosemarin, Grzegorz Kukla, Piotr Grudzien, Nicola Cancedda
Email responses often contain items-such as a file or a hyperlink to an external document-that are attached to or included inline in the body of the message.
no code implementations • 13 Jul 2017 • Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra
Machine learning plays a role in many aspects of modern IR systems, and deep learning is applied in all of them.
no code implementations • ACL 2016 • Fernando Diaz, Bhaskar Mitra, Nick Craswell
Continuous space word embeddings have received a great deal of attention in the natural language processing and machine learning communities for their ability to model term similarity and other relationships.
no code implementations • 9 May 2018 • Daniel Cohen, Bhaskar Mitra, Katja Hofmann, W. Bruce Croft
We use an adversarial discriminator and train our neural ranking model on a small set of domains.
Information Retrieval
no code implementations • 2 Feb 2016 • Bhaskar Mitra, Eric Nalisnick, Nick Craswell, Rich Caruana
A fundamental goal of search engines is to identify, given a query, documents that have relevant text.
no code implementations • 15 Apr 2019 • Corby Rosset, Bhaskar Mitra, Chenyan Xiong, Nick Craswell, Xia Song, Saurabh Tiwary
The training of these models involve a search for appropriate parameter values based on large quantities of labeled examples.
no code implementations • 8 Jul 2019 • Bhaskar Mitra, Corby Rosset, David Hawking, Nick Craswell, Fernando Diaz, Emine Yilmaz
Deep neural IR models, in contrast, compare the whole query to the document and are, therefore, typically employed only for late stage re-ranking.
no code implementations • 12 Apr 2018 • Corby Rosset, Damien Jose, Gargi Ghosh, Bhaskar Mitra, Saurabh Tiwary
In web search, typically a candidate generation step selects a small set of documents---from collections containing as many as billions of web pages---that are subsequently ranked and pruned before being presented to the user.
no code implementations • 20 Dec 2019 • Laura Dietz, Bhaskar Mitra, Jeremy Pickens, Hana Anber, Sandeep Avula, Asia Biega, Adrian Boteanu, Shubham Chatterjee, Jeff Dalton, Shiri Dori-Hacohen, John Foley, Henry Feild, Ben Gamari, Rosie Jones, Pallika Kanani, Sumanta Kashyapi, Widad Machmouchi, Matthew Mitsui, Steve Nole, Alexandre Tachard Passos, Jordan Ramsdell, Adam Roegiest, David Smith, Alessandro Sordoni
The vision of HIPstIR is that early stage information retrieval (IR) researchers get together to develop a future for non-mainstream ideas and research agendas in IR.
no code implementations • 28 Apr 2020 • Emine Yilmaz, Nick Craswell, Bhaskar Mitra, Daniel Campos
As deep learning based models are increasingly being used for information retrieval (IR), a major challenge is to ensure the availability of test collections for measuring their quality.
no code implementations • 27 Apr 2020 • Fernando Diaz, Bhaskar Mitra, Michael D. Ekstrand, Asia J. Biega, Ben Carterette
We introduce the concept of \emph{expected exposure} as the average attention ranked items receive from users over repeated samples of the same query.
no code implementations • 30 May 2020 • Hamed Zamani, Bhaskar Mitra, Everest Chen, Gord Lueck, Fernando Diaz, Paul N. Bennett, Nick Craswell, Susan T. Dumais
We also propose a model for learning representation for clarifying questions based on the user interaction data as implicit feedback.
no code implementations • 9 Jun 2020 • Nick Craswell, Daniel Campos, Bhaskar Mitra, Emine Yilmaz, Bodo Billerbeck
Users of Web search engines reveal their information needs through queries and clicks, making click logs a useful asset for information retrieval.
no code implementations • 18 Aug 2020 • Jason Ingyu Choi, Surya Kallumadi, Bhaskar Mitra, Eugene Agichtein, Faizan Javed
Retrieving all semantically relevant products from the product catalog is an important problem in E-commerce.
no code implementations • 3 May 2017 • Bhaskar Mitra, Nick Craswell
Neural ranking models for information retrieval (IR) use shallow or deep neural networks to rank search results in response to a query.
no code implementations • 14 Nov 2020 • Bhaskar Mitra, Sebastian Hofstatter, Hamed Zamani, Nick Craswell
We benchmark Conformer-Kernel models under the strict blind evaluation setting of the TREC 2020 Deep Learning track.
no code implementations • 13 Apr 2020 • Bhaskar Mitra, Suman Debanth, Badrul Chowdhury
A relationship between the damped natural frequency of oscillation of the transmission line current and fault location is established in this paper.
no code implementations • 21 Dec 2020 • Bhaskar Mitra
In many real-life IR tasks, the retrieval involves extremely large collections--such as the document index of a commercial Web search engine--containing billions of documents.
no code implementations • 18 Jan 2021 • Jaime Arguello, Adam Ferguson, Emery Fine, Bhaskar Mitra, Hamed Zamani, Fernando Diaz
Using movie search as a case study, we explore the characteristics of questions posed by searchers in TOT states in a community question answering website.
no code implementations • 25 Feb 2021 • Jimmy Lin, Daniel Campos, Nick Craswell, Bhaskar Mitra, Emine Yilmaz
Leaderboards are a ubiquitous part of modern research in applied machine learning.
no code implementations • 19 Apr 2021 • Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, Ellen M. Voorhees, Ian Soboroff
The TREC Deep Learning (DL) Track studies ad hoc search in the large data regime, meaning that a large set of human-labeled training data is available.
no code implementations • 19 Apr 2021 • Bhaskar Mitra, Sebastian Hofstatter, Hamed Zamani, Nick Craswell
The Transformer-Kernel (TK) model has demonstrated strong reranking performance on the TREC Deep Learning benchmark -- and can be considered to be an efficient (but slightly less effective) alternative to other Transformer-based architectures that employ (i) large-scale pretraining (high training cost), (ii) joint encoding of query and document (high inference cost), and (iii) larger number of Transformer layers (both high training and high inference costs).
no code implementations • 6 May 2021 • Haolun Wu, Chen Ma, Bhaskar Mitra, Fernando Diaz, Xue Liu
To address these limitations, we propose a multi-objective optimization framework for fairness-aware recommendation, Multi-FR, that adaptively balances accuracy and fairness for various stakeholders with Pareto optimality guarantee.
no code implementations • 9 May 2021 • Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, Jimmy Lin
Evaluation efforts such as TREC, CLEF, NTCIR and FIRE, alongside public leaderboard such as MS MARCO, are intended to encourage research and track our progress, addressing big questions in our field.
no code implementations • 14 Oct 2021 • Ruohan Li, Jianxiang Li, Bhaskar Mitra, Fernando Diaz, Asia J. Biega
Search systems control the exposure of ranked content to searchers.
no code implementations • 15 Oct 2021 • Nicola Neophytou, Bhaskar Mitra, Catherine Stinson
We find statistically significant differences in recommender performance by both age and gender.
no code implementations • 20 Jan 2022 • Timothy Flavin, Bhaskar Mitra, Vidhyashree Nagaraju, Rounak Meyur
Precise location of faults for large distance power transmission networks is essential for faster repair and restoration process.
no code implementations • 21 Jan 2022 • Gabriella Kazai, Bhaskar Mitra, Anlei Dong, Nick Craswell, Linjun Yang
This raises questions about when such summaries are sufficient for relevance estimation by the ranking model or the human assessor, and whether humans and machines benefit from the document's full text in similar ways.
no code implementations • 26 Feb 2022 • Timothy Flavin, Thomas Steiner, Bhaskar Mitra, Vidhyashree Nagaraju
This paper discusses a method for accurately estimating the fault location in multi-terminal High Voltage direct current (HVdc) transmission network using single ended current and voltage measurements.
no code implementations • 11 Jun 2022 • Don Scoffield, John Smart, Timothy Pennington, C. Birk Jones, Matthew Lave, Anudeep Medam, Bhaskar Mitra
Long, lightly loaded feeders serving residential loads may begin to experience voltage excursions as plug-in electric vehicle (PEV) penetration increases.
no code implementations • 26 Jun 2022 • Sebastian Hofstätter, Nick Craswell, Bhaskar Mitra, Hamed Zamani, Allan Hanbury
Recently, several dense retrieval (DR) models have demonstrated competitive performance to term-based retrieval that are ubiquitous in search systems.
no code implementations • 8 Sep 2022 • Ida Larsen-Ledet, Bhaskar Mitra, Siân Lindley
When these knowledge bases begin to actively bring attention to people and the content they work on, especially as that work is still ongoing, we run into important challenges at the intersection of work and the social.
no code implementations • 26 Oct 2022 • Bhaskar Mitra, Ankit Singhal, Soumya Kundu, James P. Ogle
To have a good understanding of current standing challenges, a knowledge of the generation and load mix as well as the current harmonic estimations are essential for designing transformers and evaluating their performance.
no code implementations • 12 Jan 2023 • Chirag Shah, Ryen W. White, Paul Thomas, Bhaskar Mitra, Shawon Sarkar, Nicholas Belkin
For decades, scholars made a case for the role that a user's task plays in how and why that user engages in search and what a search system should do to assist.
no code implementations • 25 Apr 2023 • Amifa Raj, Bhaskar Mitra, Nick Craswell, Michael D. Ekstrand
There are many ways a query, the search results, and a demographic attribute such as gender may relate, leading us to hypothesize different causes for these reformulation patterns, such as under-representation on the original result page or based on the linguistic theory of markedness.
no code implementations • 19 Sep 2023 • Paul Thomas, Seth Spielman, Nick Craswell, Bhaskar Mitra
It takes careful feedback from real users, which by definition is the highest-quality first-party gold data that can be derived, and develops an large language model prompt that agrees with that data.
no code implementations • 2 Oct 2023 • Andrew D. Gordon, Carina Negreanu, José Cambronero, Rasika Chakravarthy, Ian Drosos, Hao Fang, Bhaskar Mitra, Hannah Richardson, Advait Sarkar, Stephanie Simmons, Jack Williams, Ben Zorn
Hence, we are seeing the emergence of tool-assisted experiences to help the user double-check a piece of AI-generated content.
no code implementations • 6 Nov 2023 • Bhaskar Mitra, Sohom Datta, Slaven Kincic, Nader Samaan, Abhishek Somani
In the evolving power system, where new renewable resources continually displace conventional generation, conventional hydropower resources can be an important asset that helps to maintain reliability and flexibility.
no code implementations • 8 Dec 2023 • Ouail Kitouni, Niklas Nolte, James Hensman, Bhaskar Mitra
We introduce Diffusion Models of Structured Knowledge (DiSK) - a new architecture and training approach specialized for structured data.
no code implementations • 17 Jan 2024 • Karina Cortiñas-Lorenzo, Siân Lindley, Ida Larsen-Ledet, Bhaskar Mitra
Knowledge can't be disentangled from people.
no code implementations • 6 Feb 2024 • Haolun Wu, Ye Yuan, Liana Mikaelyan, Alexander Meulemans, Xue Liu, James Hensman, Bhaskar Mitra
Recent advances in machine learning have significantly impacted the field of information extraction, with Large Language Models (LLMs) playing a pivotal role in extracting structured information from unstructured text.
no code implementations • 28 Feb 2024 • Dewei Wang, Bhaskar Mitra, Sameer Nekkalapu, Sohom Datta, Bibi Matthew, Rounak Meyur, Heng Wang, Slaven Kincic
As the power system continues to be flooded with intermittent resources, it becomes more important to accurately assess the role of hydro and its impact on the power grid.
no code implementations • 26 Mar 2024 • Bhaskar Mitra
Information retrieval (IR) technologies and research are undergoing transformative changes.