Search Results for author: James Allan

Found 19 papers, 2 papers with code

Uncertainty in Additive Feature Attribution methods

no code implementations29 Nov 2023 Abhishek Madaan, Tanya Chowdhury, Neha Rana, James Allan, Tanmoy Chakraborty

As a result, we propose a measure to quantify the relative complexity of a blackbox classifier.

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

Evaluating the Robustness of Conversational Recommender Systems by Adversarial Examples

no code implementations9 Mar 2023 Ali Montazeralghaem, James Allan

In this paper, we propose an adversarial evaluation scheme including four scenarios in two categories and automatically generate adversarial examples to evaluate the robustness of these systems in the face of different input data.

Recommendation Systems

Cross-lingual Knowledge Transfer via Distillation for Multilingual Information Retrieval

no code implementations26 Feb 2023 Zhiqi Huang, Puxuan Yu, James Allan

In this paper, we introduce the approach behind our submission for the MIRACL challenge, a WSDM 2023 Cup competition that centers on ad-hoc retrieval across 18 diverse languages.

Information Retrieval Machine Translation +2

Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation

no code implementations29 Jan 2023 Zhiqi Huang, Puxuan Yu, James Allan

Moreover, unlike the English-to-English retrieval task, where large-scale training collections for document ranking such as MS MARCO are available, the lack of cross-lingual retrieval data for low-resource language makes it more challenging for training cross-lingual retrieval models.

Cross-Lingual Information Retrieval Document Ranking +2

Rank-LIME: Local Model-Agnostic Feature Attribution for Learning to Rank

no code implementations24 Dec 2022 Tanya Chowdhury, Razieh Rahimi, James Allan

In this work, we extend LIME to propose Rank-LIME, a model-agnostic, local, post-hoc linear feature attribution method for the task of learning to rank that generates explanations for ranked lists.

Decision Making Information Retrieval +3

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.

Cross-Market Product Recommendation

1 code implementation13 Sep 2021 Hamed Bonab, Mohammad Aliannejadi, Ali Vardasbi, Evangelos Kanoulas, James Allan

We introduce and formalize the problem of cross-market product recommendation, i. e., market adaptation.

Domain Adaptation Meta-Learning +1

AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction

no code implementations10 Sep 2021 Dong-Ho Lee, Ravi Kiran Selvam, Sheikh Muhammad Sarwar, Bill Yuchen Lin, Fred Morstatter, Jay Pujara, Elizabeth Boschee, James Allan, Xiang Ren

Deep neural models for named entity recognition (NER) have shown impressive results in overcoming label scarcity and generalizing to unseen entities by leveraging distant supervision and auxiliary information such as explanations.

Low Resource Named Entity Recognition named-entity-recognition +2

Query-driven Segment Selection for Ranking Long Documents

no code implementations10 Sep 2021 Youngwoo Kim, Razieh Rahimi, Hamed Bonab, James Allan

Transformer-based rankers have shown state-of-the-art performance.

CEQE: Contextualized Embeddings for Query Expansion

no code implementations9 Mar 2021 Shahrzad Naseri, Jeffrey Dalton, Andrew Yates, James Allan

We find that CEQE outperforms static embedding-based expansion methods on multiple collections (by up to 18% on Robust and 31% on Deep Learning on average precision) and also improves over proven probabilistic pseudo-relevance feedback (PRF) models.

Re-Ranking Retrieval

A Study of Neural Matching Models for Cross-lingual IR

no code implementations26 May 2020 Puxuan Yu, James Allan

In this study, we investigate interaction-based neural matching models for ad-hoc cross-lingual information retrieval (CLIR) using cross-lingual word embeddings (CLWEs).

Cross-Lingual Information Retrieval Cross-Lingual Word Embeddings +2

FEVER Breaker's Run of Team NbAuzDrLqg

no code implementations WS 2019 Youngwoo Kim, James Allan

We describe our submission for the Breaker phase of the second Fact Extraction and VERification (FEVER) Shared Task.

Semantic Driven Fielded Entity Retrieval

no code implementations2 Jul 2019 Shahrzad Naseri, Sheikh Muhammad Sarwar, James Allan

A common approach for knowledge-base entity search is to consider an entity as a document with multiple fields.

Entity Retrieval Re-Ranking +1

A Multi-Task Architecture on Relevance-based Neural Query Translation

no code implementations ACL 2019 Sheikh Muhammad Sarwar, Hamed Bonab, James Allan

We describe a multi-task learning approach to train a Neural Machine Translation (NMT) model with a Relevance-based Auxiliary Task (RAT) for search query translation.

Cross-Lingual Information Retrieval Machine Translation +5

Named Entity Recognition with Extremely Limited Data

1 code implementation12 Jun 2018 John Foley, Sheikh Muhammad Sarwar, James Allan

Traditional information retrieval treats named entity recognition as a pre-indexing corpus annotation task, allowing entity tags to be indexed and used during search.

Information Retrieval named-entity-recognition +3

Improving Document Clustering by Removing Unnatural Language

no code implementations WS 2017 Myungha Jang, Jinho D. Choi, James Allan

We view this problem as an information extraction task and build a multiclass classification model identifying unnatural language components into four categories.

Clustering Document Layout Analysis +1

Improving Document Clustering by Eliminating Unnatural Language

no code implementations16 Mar 2017 Myungha Jang, Jinho D. Choi, James Allan

We view this problem as an information extraction task and build a multiclass classification model identifying unnatural language components into four categories.

Clustering

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