Christina Lioma
7 papers in the PaperMetrix corpus
Papers by this author
-
Multi-Head Self-Attention with Role-Guided Masks
2020 · arXiv (Cornell University)
The state of the art in learning meaningful semantic representations of words is the Transformer model and its attention mechanisms. Simply put, the attention mechanisms learn to attend to specific parts of the input dispensing …
-
Principled Multi-Aspect Evaluation Measures of Rankings
2021
Information Retrieval evaluation has traditionally focused on defining principled ways of assessing the relevance of a ranked list of documents with respect to a query. Several methods extend this type of evaluation beyond relevance, making …
-
Diagnostics-Guided Explanation Generation
2021 · arXiv (Cornell University)
Explanations shed light on a machine learning model's rationales and can aid in identifying deficiencies in its reasoning process. Explanation generation models are typically trained in a supervised way given human explanations. When such annotations …
-
Joint Evaluation of Fairness and Relevance in Recommender Systems with Pareto Frontier
2025
Fairness and relevance are two important aspects of recommender systems (RSs). Typically, they are evaluated either (i) separately by individual measures of fairness and relevance, or (ii) jointly using a single measure that accounts for …
-
As easy as PIE: understanding when pruning causes language models to disagree
2025 · arXiv (Cornell University)
Language Model (LM) pruning compresses the model by removing weights, nodes, or other parts of its architecture. Typically, pruning focuses on the resulting efficiency gains at the cost of effectiveness. However, when looking at how …
-
A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion
2015
Users may strive to formulate an adequate textual query for their information need. Search engines assist the users by presenting query suggestions. To preserve the original search intent, suggestions should be context-aware and account for …
-
Evaluation measures for relevance and credibility in ranked lists
2017 · Research at the University of Copenhagen (University of Copenhagen)
Recent discussions on alternative facts, fake news, and post truth politics have motivated research on creating technologies that allow people not only to access information, but also to assess the credibility of the information presented …