research
∙
06/13/2023
Domain Information Control at Inference Time for Acoustic Scene Classification
Domain shift is considered a challenge in machine learning as it causes ...
share
research
∙
05/26/2023
Leveraging Domain Knowledge for Inclusive and Bias-aware Humanitarian Response Entry Classification
Accurate and rapid situation analysis during humanitarian crises is crit...
research
∙
05/25/2023
Enhancing the Ranking Context of Dense Retrieval Methods through Reciprocal Nearest Neighbors
Sparse annotation poses persistent challenges to training dense retrieva...
research
∙
02/13/2023
Parameter-efficient Modularised Bias Mitigation via AdapterFusion
Large pre-trained language models contain societal biases and carry alon...
research
∙
01/17/2023
Leveraging Vision-Language Models for Granular Market Change Prediction
Predicting future direction of stock markets using the historical data h...
research
∙
10/10/2022
HumSet: Dataset of Multilingual Information Extraction and Classification for Humanitarian Crisis Response
Timely and effective response to humanitarian crises requires quick and ...
research
∙
06/09/2022
Unlearning Protected User Attributes in Recommendations with Adversarial Training
Collaborative filtering algorithms capture underlying consumption patter...
research
∙
05/30/2022
Parameter Efficient Diff Pruning for Bias Mitigation
In recent years language models have achieved state of the art performan...
research
∙
03/03/2022
Do Perceived Gender Biases in Retrieval Results Affect Relevance Judgements?
This work investigates the effect of gender-stereotypical biases in the ...
research
∙
01/19/2022
Grep-BiasIR: A Dataset for Investigating Gender Representation-Bias in Information Retrieval Results
The provided contents by information retrieval (IR) systems can reflect ...
research
∙
12/16/2021
CODER: An efficient framework for improving retrieval through COntextualized Document Embedding Reranking
We present a framework for improving the performance of a wide class of ...
research
∙
12/13/2021
WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models
Recently, large pretrained language models (LMs) have gained popularity....
research
∙
08/16/2021
Analyzing Item Popularity Bias of Music Recommender Systems: Are Different Genders Equally Affected?
Several studies have identified discrepancies between the popularity of ...
research
∙
06/25/2021
A Modern Perspective on Query Likelihood with Deep Generative Retrieval Models
Existing neural ranking models follow the text matching paradigm, where ...
research
∙
05/10/2021
Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Models
In any ranking system, the retrieval model outputs a single score for a ...
research
∙
04/28/2021
Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankers
Societal biases resonate in the retrieved contents of information retrie...
research
∙
03/14/2021
TripClick: The Log Files of a Large Health Web Search Engine
Click logs are valuable resources for a variety of information retrieval...
research
∙
05/01/2020
Do Neural Ranking Models Intensify Gender Bias?
Concerns regarding the footprint of societal biases in information retri...
research
∙
01/15/2020
DSR: A Collection for the Evaluation of Graded Disease-Symptom Relations
The effective extraction of ranked disease-symptom relationships is a cr...
research
∙
05/29/2019
Regularization Advantages of Multilingual Neural Language Models for Low Resource Domains
Neural language modeling (LM) has led to significant improvements in sev...
research
∙
12/13/2018
An Unbiased Approach to Quantification of Gender Inclination using Interpretable Word Representations
Recent advances in word embedding provide significant benefit to various...
research
∙
11/16/2017
Addressing Cross-Lingual Word Sense Disambiguation on Low-Density Languages: Application to Persian
We explore the use of unsupervised methods in Cross-Lingual Word Sense D...
research
∙
07/20/2017
Toward Incorporation of Relevant Documents in word2vec
Recent advances in neural word embedding provide significant benefit to ...
research
∙
06/20/2016