no code implementations • 2 May 2024 • Dawn Lawrie, Efsun Kayi, Eugene Yang, James Mayfield, Douglas W. Oard
PLAID, an efficient implementation of the ColBERT late interaction bi-encoder using pretrained language models for ranking, consistently achieves state-of-the-art performance in monolingual, cross-language, and multilingual retrieval.
no code implementations • 2 May 2024 • Eugene Yang, Dawn Lawrie, James Mayfield
Recent work in cross-language information retrieval (CLIR), where queries and documents are in different languages, has shown the benefit of the Translate-Distill framework that trains a cross-language neural dual-encoder model using translation and distillation.
1 code implementation • 2 May 2024 • Eugene Yang, Thomas Jänich, James Mayfield, Dawn Lawrie
We also evaluate real MLIR systems on two publicly available benchmarks and show that the PEER scores align with prior analytical findings on MLIR fairness.
no code implementations • 2 May 2024 • James Mayfield, Eugene Yang, Dawn Lawrie, Sean MacAvaney, Paul McNamee, Douglas W. Oard, Luca Soldaini, Ian Soboroff, Orion Weller, Efsun Kayi, Kate Sanders, Marc Mason, Noah Hibbler
Reports with these qualities are necessary to satisfy the complex, nuanced, or multi-faceted information needs of users.
1 code implementation • 29 Apr 2024 • Eugene Yang, Suraj Nair, Dawn Lawrie, James Mayfield, Douglas W. Oard, Kevin Duh
Probabilistic Structured Queries (PSQ) is a cross-language information retrieval (CLIR) method that uses translation probabilities statistically derived from aligned corpora.
no code implementations • 11 Apr 2024 • Dawn Lawrie, Sean MacAvaney, James Mayfield, Paul McNamee, Douglas W. Oard, Luca Soldaini, Eugene Yang
The principal tasks are ranked retrieval of news in one of the three languages, using English topics.
no code implementations • 11 Apr 2024 • Eugene Yang, Dawn Lawrie, James Mayfield
TT trains a ColBERT model with English queries and passages automatically translated into the document language from the MS-MARCO v1 collection.
no code implementations • 11 Apr 2024 • Eugene Yang, Dawn J. Lawrie, Paul McNamee, James Mayfield
This paper describes the submission runs from the HLTCOE team at the CIRAL CLIR tasks for African languages at FIRE 2023.
1 code implementation • 9 Jan 2024 • Eugene Yang, Dawn Lawrie, James Mayfield, Douglas W. Oard, Scott Miller
Applying a similar knowledge distillation approach to training an efficient dual-encoder model for Cross-Language Information Retrieval (CLIR), where queries and documents are in different languages, is challenging due to the lack of a sufficiently large training collection when the query and document languages differ.
no code implementations • 29 Apr 2023 • James Mayfield, Eugene Yang, Dawn Lawrie, Samuel Barham, Orion Weller, Marc Mason, Suraj Nair, Scott Miller
By repeating this process, collections of arbitrary size can be created in the style of MS MARCO but using naturally-occurring documents in any desired genre and domain of discourse.
no code implementations • 24 Apr 2023 • Dawn Lawrie, Sean MacAvaney, James Mayfield, Paul McNamee, Douglas W. Oard, Luca Soldaini, Eugene Yang
This is the first year of the TREC Neural CLIR (NeuCLIR) track, which aims to study the impact of neural approaches to cross-language information retrieval.
no code implementations • 20 Dec 2022 • Eugene Yang, Suraj Nair, Dawn Lawrie, James Mayfield, Douglas W. Oard
By adding adapters pretrained on language tasks for a specific language with task-specific adapters, prior work has shown that the adapter-enhanced models perform better than fine-tuning the entire model when transferring across languages in various NLP tasks.
1 code implementation • 3 Sep 2022 • Dawn Lawrie, Eugene Yang, Douglas W. Oard, James Mayfield
Providing access to information across languages has been a goal of Information Retrieval (IR) for decades.
1 code implementation • 24 Jan 2022 • Dawn Lawrie, James Mayfield, Douglas Oard, Eugene Yang
HC4 is a new suite of test collections for ad hoc Cross-Language Information Retrieval (CLIR), with Common Crawl News documents in Chinese, Persian, and Russian, topics in English and in the document languages, and graded relevance judgments.
1 code implementation • 24 Jan 2022 • Cash Costello, Eugene Yang, Dawn Lawrie, James Mayfield
While there are high-quality software frameworks for information retrieval experimentation, they do not explicitly support cross-language information retrieval (CLIR).
1 code implementation • 20 Jan 2022 • Suraj Nair, Eugene Yang, Dawn Lawrie, Kevin Duh, Paul McNamee, Kenton Murray, James Mayfield, Douglas W. Oard
These models have improved the effectiveness of retrieval systems well beyond that of lexical term matching models such as BM25.
no code implementations • 16 Apr 2021 • Elliot Schumacher, James Mayfield, Mark Dredze
Entity linking -- the task of identifying references in free text to relevant knowledge base representations -- often focuses on single languages.
1 code implementation • Findings (ACL) 2021 • Elliot Schumacher, James Mayfield, Mark Dredze
We find that the multilingual ability of BERT leads to robust performance in monolingual and multilingual settings.
no code implementations • LREC 2020 • Paul McNamee, James Mayfield, Cash Costello, Caitlyn Bishop, Shelby Anderson
Throughout this time the majority of such work has focused on detection and classification of entities into coarse-grained types like: PERSON, ORGANIZATION, and LOCATION.
no code implementations • LREC 2020 • Dawn Lawrie, James Mayfield, David Etter
This means that named entities are annotated on the transcribed text.
no code implementations • LREC 2020 • Cash Costello, Shelby Anderson, Caitlyn Bishop, James Mayfield, Paul McNamee
Dragonfly is an open source software tool that supports annotation of text in a low resource language by non-speakers of the language.
1 code implementation • 6 Mar 2020 • Chan Hee Song, Dawn Lawrie, Tim Finin, James Mayfield
The goal of this work is to improve the performance of a neural named entity recognition system by adding input features that indicate a word is part of a name included in a gazetteer.
no code implementations • ACL 2018 • Ying Lin, Cash Costello, Boliang Zhang, Di Lu, Heng Ji, James Mayfield, Paul McNamee
We demonstrate two annotation platforms that allow an English speaker to annotate names for any language without knowing the language.
no code implementations • IJCNLP 2017 • Benjamin Van Durme, Tom Lippincott, Kevin Duh, Deana Burchfield, Adam Poliak, Cash Costello, Tim Finin, Scott Miller, James Mayfield, Philipp Koehn, Craig Harman, Dawn Lawrie, Ch May, ler, Max Thomas, Annabelle Carrell, Julianne Chaloux, Tongfei Chen, Alex Comerford, Mark Dredze, Benjamin Glass, Shudong Hao, Patrick Martin, Pushpendre Rastogi, Rashmi Sankepally, Travis Wolfe, Ying-Ying Tran, Ted Zhang
It combines a multitude of analytics together with a flexible environment for customizing the workflow for different users.
no code implementations • WS 2017 • James Mayfield, Paul McNamee, Cash Costello
The 2017 shared task at the Balto-Slavic NLP workshop requires identifying coarse-grained named entities in seven languages, identifying each entity{'}s base form, and clustering name mentions across the multilingual set of documents.
no code implementations • 31 May 2015 • Travis Wolfe, Mark Dredze, James Mayfield, Paul McNamee, Craig Harman, Tim Finin, Benjamin Van Durme
Most work on building knowledge bases has focused on collecting entities and facts from as large a collection of documents as possible.
no code implementations • LREC 2012 • Dawn Lawrie, James Mayfield, Paul McNamee, Douglas Oard
To stimulate research in cross-language entity linking, we present a new test collection for evaluating the accuracy of cross-language entity linking in twenty-one languages.