Search Results for author: Hamed Zamani

Found 58 papers, 29 papers with code

ProCIS: A Benchmark for Proactive Retrieval in Conversations

1 code implementation10 May 2024 Chris Samarinas, Hamed Zamani

The field of conversational information seeking, which is rapidly gaining interest in both academia and industry, is changing how we interact with search engines through natural language interactions.

Retrieval Text Retrieval

Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization

no code implementations5 May 2024 Hamed Zamani, Michael Bendersky

This paper introduces Stochastic RAG--a novel approach for end-to-end optimization of retrieval-augmented generation (RAG) models that relaxes the simplifying assumptions of marginalization and document independence, made in most prior work.

Fact Verification Open-Domain Question Answering +4

Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Models

1 code implementation30 Apr 2024 Alireza Salemi, Hamed Zamani

This lays the groundwork for us to build a large-scale experimentation ecosystem consisting of 18 RAG systems that engage in training and 18 unknown RAG systems that use the uRAG as the new users of the search engine.

Entity Linking Fact Verification +3

Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models

1 code implementation23 Apr 2024 Chris Samarinas, Pracha Promthaw, Atharva Nijasure, Hansi Zeng, Julian Killingback, Hamed Zamani

In our experiments, using graph-guided response simulations leads to significant improvements in intent classification, slot filling and response relevance compared to naive single-prompt simulated conversations.

Conversational Question Answering Dialogue State Tracking +8

Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decoding

1 code implementation22 Apr 2024 Hansi Zeng, Chen Luo, Hamed Zamani

This paper introduces PAG-a novel optimization and decoding approach that guides autoregressive generation of document identifiers in generative retrieval models through simultaneous decoding.

Information Retrieval Retrieval

Evaluating Retrieval Quality in Retrieval-Augmented Generation

1 code implementation21 Apr 2024 Alireza Salemi, Hamed Zamani

Furthermore, evaluation of the retrieval model's performance based on query-document relevance labels shows a small correlation with the RAG system's downstream performance.

Language Modelling Large Language Model +1

Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation

1 code implementation9 Apr 2024 Alireza Salemi, Surya Kallumadi, Hamed Zamani

This paper studies retrieval-augmented approaches for personalizing large language models (LLMs), which potentially have a substantial impact on various applications and domains.

Knowledge Distillation Language Modelling +1

Online and Offline Evaluation in Search Clarification

no code implementations14 Mar 2024 Leila Tavakoli, Johanne R. Trippas, Hamed Zamani, Falk Scholer, Mark Sanderson

The effectiveness of clarification question models in engaging users within search systems is currently constrained, casting doubt on their overall usefulness.

Information Retrieval Retrieval

ICXML: An In-Context Learning Framework for Zero-Shot Extreme Multi-Label Classification

1 code implementation16 Nov 2023 Yaxin Zhu, Hamed Zamani

This paper focuses on the task of Extreme Multi-Label Classification (XMC) whose goal is to predict multiple labels for each instance from an extremely large label space.

Extreme Multi-Label Classification In-Context Learning

Scalable and Effective Generative Information Retrieval

2 code implementations15 Nov 2023 Hansi Zeng, Chen Luo, Bowen Jin, Sheikh Muhammad Sarwar, Tianxin Wei, Hamed Zamani

This paper represents an important milestone in generative retrieval research by showing, for the first time, that generative retrieval models can be trained to perform effectively on large-scale standard retrieval benchmarks.

Information Retrieval Retrieval

Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering

1 code implementation28 Jun 2023 Alireza Salemi, Mahta Rafiee, Hamed Zamani

The proposed approach leads to 26. 9% Precision@5 improvements compared to the current state-of-the-art asymmetric architecture.

Passage Retrieval Question Answering +2

Large Language Model Augmented Narrative Driven Recommendations

1 code implementation4 Jun 2023 Sheshera Mysore, Andrew McCallum, Hamed Zamani

Narrative-driven recommendation (NDR) presents an information access problem where users solicit recommendations with verbose descriptions of their preferences and context, for example, travelers soliciting recommendations for points of interest while describing their likes/dislikes and travel circumstances.

Data Augmentation Language Modelling +3

Soft Prompt Decoding for Multilingual Dense Retrieval

no code implementations15 May 2023 Zhiqi Huang, Hansi Zeng, Hamed Zamani, James Allan

In this work, we explore a Multilingual Information Retrieval (MLIR) task, where the collection includes documents in multiple languages.

Cross-Lingual Information Retrieval Knowledge Distillation +1

Multivariate Representation Learning for Information Retrieval

no code implementations27 Apr 2023 Hamed Zamani, Michael Bendersky

Instead of learning a vector for each query and document, our framework learns a multivariate distribution and uses negative multivariate KL divergence to compute the similarity between distributions.

Information Retrieval Representation Learning +1

A Personalized Dense Retrieval Framework for Unified Information Access

1 code implementation26 Apr 2023 Hansi Zeng, Surya Kallumadi, Zaid Alibadi, Rodrigo Nogueira, Hamed Zamani

Developing a universal model that can efficiently and effectively respond to a wide range of information access requests -- from retrieval to recommendation to question answering -- has been a long-lasting goal in the information retrieval community.

Information Retrieval Question Answering +1

A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering

1 code implementation26 Apr 2023 Alireza Salemi, Juan Altmayer Pizzorno, Hamed Zamani

Utilizing the passages retrieved by DEDR, we further introduce MM-FiD, an encoder-decoder multi-modal fusion-in-decoder model, for generating a textual answer for KI-VQA tasks.

Decoder Knowledge Distillation +3

LaMP: When Large Language Models Meet Personalization

1 code implementation22 Apr 2023 Alireza Salemi, Sheshera Mysore, Michael Bendersky, Hamed Zamani

This paper highlights the importance of personalization in large language models and introduces the LaMP benchmark -- a novel benchmark for training and evaluating language models for producing personalized outputs.

Language Modelling Natural Language Understanding +4

Generalized Weak Supervision for Neural Information Retrieval

no code implementations18 Apr 2023 Yen-Chieh Lien, Hamed Zamani, W. Bruce Croft

To address this issue, one can train NRMs via weak supervision, where a large dataset is automatically generated using an existing ranking model (called the weak labeler) for training NRMs.

Passage Retrieval Retrieval

Editable User Profiles for Controllable Text Recommendation

1 code implementation9 Apr 2023 Sheshera Mysore, Mahmood Jasim, Andrew McCallum, Hamed Zamani

Finally, we implement LACE in an interactive controllable recommender system and conduct a user study to demonstrate that users are able to improve the quality of recommendations they receive through interactions with an editable user profile.

Recommendation Systems Retrieval

You can't pick your neighbors, or can you? When and how to rely on retrieval in the $k$NN-LM

1 code implementation28 Oct 2022 Andrew Drozdov, Shufan Wang, Razieh Rahimi, Andrew McCallum, Hamed Zamani, Mohit Iyyer

Retrieval-enhanced language models (LMs), which condition their predictions on text retrieved from large external datastores, have recently shown significant perplexity improvements compared to standard LMs.

Language Modelling Retrieval +2

FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation

no code implementations28 Sep 2022 Sebastian Hofstätter, Jiecao Chen, Karthik Raman, Hamed Zamani

Retrieval-augmented generation models offer many benefits over standalone language models: besides a textual answer to a given query they provide provenance items retrieved from an updateable knowledge base.

Decoder Open-Domain Question Answering +3

Are We There Yet? A Decision Framework for Replacing Term Based Retrieval with Dense Retrieval Systems

no code implementations26 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.


MIMICS-Duo: Offline & Online Evaluation of Search Clarification

no code implementations9 Jun 2022 Leila Tavakoli, Johanne R. Trippas, Hamed Zamani, Falk Scholer, Mark Sanderson

Asking clarification questions is an active area of research; however, resources for training and evaluating search clarification methods are not sufficient.

Retrieval-Enhanced Machine Learning

no code implementations2 May 2022 Hamed Zamani, Fernando Diaz, Mostafa Dehghani, Donald Metzler, Michael Bendersky

Although information access systems have long supported people in accomplishing a wide range of tasks, we propose broadening the scope of users of information access systems to include task-driven machines, such as machine learning models.

BIG-bench Machine Learning Information Retrieval +1

Curriculum Learning for Dense Retrieval Distillation

1 code implementation28 Apr 2022 Hansi Zeng, Hamed Zamani, Vishwa Vinay

Recent work has shown that more effective dense retrieval models can be obtained by distilling ranking knowledge from an existing base re-ranking model.

Knowledge Distillation Passage Retrieval +2

Conversational Information Seeking

no code implementations21 Jan 2022 Hamed Zamani, Johanne R. Trippas, Jeff Dalton, Filip Radlinski

Conversational information seeking (CIS) is concerned with a sequence of interactions between one or more users and an information system.

Conversational Question Answering Conversational Search

Explaining Documents' Relevance to Search Queries

no code implementations2 Nov 2021 Razieh Rahimi, Youngwoo Kim, Hamed Zamani, James Allan

GenEx explains a search result by providing a terse description for the query aspect covered by that result.

Analysing Mixed Initiatives and Search Strategies during Conversational Search

1 code implementation13 Sep 2021 Mohammad Aliannejadi, Leif Azzopardi, Hamed Zamani, Evangelos Kanoulas, Paul Thomas, Nick Craswel

In this paper, we present a model for conversational search -- from which we instantiate different observed conversational search strategies, where the agent elicits: (i) Feedback-First, or (ii) Feedback-After.

Conversational Search

Current Challenges and Future Directions in Podcast Information Access

no code implementations17 Jun 2021 Rosie Jones, Hamed Zamani, Markus Schedl, Ching-Wei Chen, Sravana Reddy, Ann Clifton, Jussi Karlgren, Helia Hashemi, Aasish Pappu, Zahra Nazari, Longqi Yang, Oguz Semerci, Hugues Bouchard, Ben Carterette

Podcasts are spoken documents across a wide-range of genres and styles, with growing listenership across the world, and a rapidly lowering barrier to entry for both listeners and creators.

Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking

1 code implementation20 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.

Document Ranking Knowledge Distillation +1

Passage Retrieval for Outside-Knowledge Visual Question Answering

1 code implementation9 May 2021 Chen Qu, Hamed Zamani, Liu Yang, W. Bruce Croft, Erik Learned-Miller

We first conduct sparse retrieval with BM25 and study expanding the question with object names and image captions.

Image Captioning Object +4

Improving Transformer-Kernel Ranking Model Using Conformer and Query Term Independence

no code implementations19 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).

Document Ranking Retrieval

CSFCube -- A Test Collection of Computer Science Research Articles for Faceted Query by Example

1 code implementation24 Mar 2021 Sheshera Mysore, Tim O'Gorman, Andrew McCallum, Hamed Zamani

Query by Example is a well-known information retrieval task in which a document is chosen by the user as the search query and the goal is to retrieve relevant documents from a large collection.

Information Retrieval Retrieval

Tip of the Tongue Known-Item Retrieval: A Case Study in Movie Identification

no code implementations18 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.

Community Question Answering Information Retrieval +1

Context-Aware Target Apps Selection and Recommendation for Enhancing Personal Mobile Assistants

1 code implementation9 Jan 2021 Mohammad Aliannejadi, Hamed Zamani, Fabio Crestani, W. Bruce Croft

Here we focus on context-aware models to leverage the rich contextual information available to mobile devices.


Conformer-Kernel with Query Term Independence at TREC 2020 Deep Learning Track

no code implementations14 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.


Conformer-Kernel with Query Term Independence for Document Retrieval

1 code implementation20 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.


MIMICS: A Large-Scale Data Collection for Search Clarification

1 code implementation17 Jun 2020 Hamed Zamani, Gord Lueck, Everest Chen, Rodolfo Quispe, Flint Luu, Nick Craswell

In this paper, we introduce MIMICS, a collection of search clarification datasets for real web search queries sampled from the Bing query logs.


Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search

no code implementations13 Jun 2020 Helia Hashemi, Hamed Zamani, W. Bruce Croft

Asking clarifying questions in response to ambiguous or faceted queries has been recognized as a useful technique for various information retrieval systems, especially conversational search systems with limited bandwidth interfaces.

Conversational Search Information Retrieval +3

Analyzing and Learning from User Interactions for Search Clarification

no code implementations30 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.

Re-Ranking Retrieval

Local Self-Attention over Long Text for Efficient Document Retrieval

1 code implementation11 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.

Document Ranking Retrieval

Common Conversational Community Prototype: Scholarly Conversational Assistant

no code implementations19 Jan 2020 Krisztian Balog, Lucie Flekova, Matthias Hagen, Rosie Jones, Martin Potthast, Filip Radlinski, Mark Sanderson, Svitlana Vakulenko, Hamed Zamani

This paper discusses the potential for creating academic resources (tools, data, and evaluation approaches) to support research in conversational search, by focusing on realistic information needs and conversational interactions.

Conversational Search

Macaw: An Extensible Conversational Information Seeking Platform

1 code implementation18 Dec 2019 Hamed Zamani, Nick Craswell

Such research will require data and tools, to allow the implementation and study of conversational systems.

Information Retrieval Question Answering +1

Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering

no code implementations WS 2019 Ameya Godbole, Dilip Kavarthapu, Rajarshi Das, Zhiyu Gong, Abhishek Singhal, Hamed Zamani, Mo Yu, Tian Gao, Xiaoxiao Guo, Manzil Zaheer, Andrew McCallum

Multi-hop question answering (QA) requires an information retrieval (IR) system that can find \emph{multiple} supporting evidence needed to answer the question, making the retrieval process very challenging.

Information Retrieval Multi-hop Question Answering +2

Recommender Systems Fairness Evaluation via Generalized Cross Entropy

no code implementations19 Aug 2019 Yashar Deldjoo, Vito Walter Anelli, Hamed Zamani, Alejandro Bellogin, Tommaso Di Noia

We present a probabilistic framework based on generalized cross entropy to evaluate fairness of recommender systems under this perspective, where we show that the proposed framework is flexible and explanatory by allowing to incorporate domain knowledge (through an ideal fair distribution) that can help to understand which item or user aspects a recommendation algorithm is over- or under-representing.

Fairness Recommendation Systems

Asking Clarifying Questions in Open-Domain Information-Seeking Conversations

2 code implementations15 Jul 2019 Mohammad Aliannejadi, Hamed Zamani, Fabio Crestani, W. Bruce Croft

In this paper, we formulate the task of asking clarifying questions in open-domain information-seeking conversational systems.

Question Selection Retrieval

ANTIQUE: A Non-Factoid Question Answering Benchmark

1 code implementation22 May 2019 Helia Hashemi, Mohammad Aliannejadi, Hamed Zamani, W. Bruce Croft

Despite the importance of the task, the community still feels the significant lack of large-scale non-factoid question answering collections with real questions and comprehensive relevance judgments.

Community Question Answering Passage Retrieval +1

Investigating the Successes and Failures of BERT for Passage Re-Ranking

no code implementations5 May 2019 Harshith Padigela, Hamed Zamani, W. Bruce Croft

The bidirectional encoder representations from transformers (BERT) model has recently advanced the state-of-the-art in passage re-ranking.

Passage Re-Ranking Re-Ranking +1

An Analysis of Approaches Taken in the ACM RecSys Challenge 2018 for Automatic Music Playlist Continuation

no code implementations2 Oct 2018 Hamed Zamani, Markus Schedl, Paul Lamere, Ching-Wei Chen

We further report and analyze the results obtained by the top performing teams in each track and explore the approaches taken by the winners.

Sequential Recommendation

Relevance-based Word Embedding

no code implementations9 May 2017 Hamed Zamani, W. Bruce Croft

This is the motivation for developing unsupervised relevance-based word embedding models that learn word representations based on query-document relevance information.

General Classification Information Retrieval +3

Neural Ranking Models with Weak Supervision

1 code implementation28 Apr 2017 Mostafa Dehghani, Hamed Zamani, Aliaksei Severyn, Jaap Kamps, W. Bruce Croft

Our experiments indicate that employing proper objective functions and letting the networks to learn the input representation based on weakly supervised data leads to impressive performance, with over 13% and 35% MAP improvements over the BM25 model on the Robust and the ClueWeb collections.

Ad-Hoc Information Retrieval Information Retrieval +1

Regression and Learning to Rank Aggregation for User Engagement Evaluation

no code implementations29 Jan 2015 Hamed Zamani, Azadeh Shakery, Pooya Moradi

In this paper, we consider a tweet containing a rating for a movie as an instance and focus on ranking the instances of each user based on their engagement, i. e., the total number of retweets and favorites it will gain.

Learning-To-Rank Recommendation Systems +1

Cannot find the paper you are looking for? You can Submit a new open access paper.