Search Results for author:
Found 30 papers, 19 papers with code
Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters
Bias mitigation of Language Models has been the topic of many studies with a recent focus on learning separate modules like adapters for on-demand debiasing.
What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition
The knowledge encapsulated in a model is the core factor determining its final performance on downstream tasks.
ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale
We introduce ScaLearn, a simple and highly parameter-efficient two-stage MTL method that capitalizes on the knowledge of the source tasks by learning a minimal set of scaling parameters that enable effective knowledge transfer to a target task.
Domain Information Control at Inference Time for Acoustic Scene Classification
In the Acoustic Scene Classification task (ASC), domain shift is mainly caused by different recording devices.
Leveraging Domain Knowledge for Inclusive and Bias-aware Humanitarian Response Entry Classification
Accurate and rapid situation analysis during humanitarian crises is critical to delivering humanitarian aid efficiently and is fundamental to humanitarian imperatives and the Leave No One Behind (LNOB) principle.
Enhancing the Ranking Context of Dense Retrieval Methods through Reciprocal Nearest Neighbors
Sparse annotation poses persistent challenges to training dense retrieval models; for example, it distorts the training signal when unlabeled relevant documents are used spuriously as negatives in contrastive learning.
Leveraging Vision-Language Models for Granular Market Change Prediction
Predicting future direction of stock markets using the historical data has been a fundamental component in financial forecasting.
HumSet: Dataset of Multilingual Information Extraction and Classification for Humanitarian Crisis Response
Timely and effective response to humanitarian crises requires quick and accurate analysis of large amounts of text data - a process that can highly benefit from expert-assisted NLP systems trained on validated and annotated data in the humanitarian response domain.
Unlearning Protected User Attributes in Recommendations with Adversarial Training
We conduct experiments on the MovieLens-1M and LFM-2b-DemoBias datasets, and evaluate the effectiveness of the bias mitigation method based on the inability of external attackers in revealing the users' gender information from the model.
Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks
Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks.
Do Perceived Gender Biases in Retrieval Results Affect Relevance Judgements?
This work investigates the effect of gender-stereotypical biases in the content of retrieved results on the relevance judgement of users/annotators.
Grep-BiasIR: A Dataset for Investigating Gender Representation-Bias in Information Retrieval Results
To facilitate the studies of gender bias in the retrieval results of IR systems, we introduce Gender Representation-Bias for Information Retrieval (Grep-BiasIR), a novel thoroughly-audited dataset consisting of 118 bias-sensitive neutral search queries.
CODER: An efficient framework for improving retrieval through COntextual Document Embedding Reranking
Contrastive learning has been the dominant approach to training dense retrieval models.
WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models
Our method makes training large language models for new languages more accessible and less damaging to the environment.
Analyzing Item Popularity Bias of Music Recommender Systems: Are Different Genders Equally Affected?
In this work, in contrast, we propose to investigate popularity differences (between the user profile and recommendation list) in terms of median, a variety of statistical moments, as well as similarity measures that consider the entire popularity distributions (Kullback-Leibler divergence and Kendall's tau rank-order correlation).
A Modern Perspective on Query Likelihood with Deep Generative Retrieval Models
In contrast to the matching paradigm, the probabilistic nature of generative rankers readily offers a fine-grained measure of uncertainty.
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 document based on its belief on how relevant it is to a given search query.
Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankers
In this work, we first provide a novel framework to measure the fairness in the retrieved text contents of ranking models.
MultiHumES: Multilingual Humanitarian Dataset for Extractive Summarization
To improve this process, effective summarization models are a valuable tool for humanitarian response experts as they provide digestible overviews of essential information in secondary data.
TripClick: The Log Files of a Large Health Web Search Engine
As such, the collection is one of the few datasets offering the necessary data richness and scale to train neural IR models with a large amount of parameters, and notably the first in the health domain.
Do Neural Ranking Models Intensify Gender Bias?
Concerns regarding the footprint of societal biases in information retrieval (IR) systems have been raised in several previous studies.
DSR: A Collection for the Evaluation of Graded Disease-Symptom Relations
While existing disease-symptom relationship extraction methods are used as the foundation in the various medical tasks, no collection is available to systematically evaluate the performance of such methods.
Regularization Advantages of Multilingual Neural Language Models for Low Resource Domains
In this study, we propose a multilingual neural language model architecture, trained jointly on the domain-specific data of several low-resource languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
On the Effect of Low-Frequency Terms on Neural-IR Models
Low-frequency terms are a recurring challenge for information retrieval models, especially neural IR frameworks struggle with adequately capturing infrequently observed words.
Measuring Societal Biases from Text Corpora with Smoothed First-Order Co-occurrence
The common approach to measuring such biases using a corpus is by calculating the similarities between the embedding vector of a word (like nurse) and the vectors of the representative words of the concepts of interest (such as genders).
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 Disambiguation (CL-WSD) with the application of English to Persian.
Toward Incorporation of Relevant Documents in word2vec
As an alternative, explicit word representations propose vectors whose dimensions are easily interpretable, and recent methods show competitive performance to the dense vectors.
Uncertainty in Neural Network Word Embedding: Exploration of Threshold for Similarity
Word embedding, specially with its recent developments, promises a quantification of the similarity between terms.
Standard Test Collection for English-Persian Cross-Lingual Word Sense Disambiguation
In this paper, we address the shortage of evaluation benchmarks on Persian (Farsi) language by creating and making available a new benchmark for English to Persian Cross Lingual Word Sense Disambiguation (CL-WSD).
