Related papers: Textual Analogy Parsing: What's Shared and What's …
I generalize state-of-the-art approaches that decompose differences in the distribution of a variable of interest between two groups into a portion explained by covariates and a residual portion. The method that I propose relaxes the…
Dialectal data are characterized by linguistic variation that appears small to humans but has a significant impact on the performance of models. This dialect gap has been related to various factors (e.g., data size, economic and social…
Retrieval-augmented generation (RAG) ranks passages by semantic similarity to the input, implicitly assuming that semantic similarity is a reliable indication of applicability in downstream tasks. This assumption breaks down when task…
In many covering settings, it is natural to consider the presence both of elements that we seek to include and of elements that we seek to avoid. This paper introduces a novel combinatorial problem formalizing this tradeoff: from a…
We highlight an important frontier in algorithmic fairness: disparity in the quality of natural language processing algorithms when applied to language from authors of different social groups. For example, current systems sometimes analyze…
Knowledge graphs play a pivotal role in various applications, such as question-answering and fact-checking. Abstract Meaning Representation (AMR) represents text as knowledge graphs. Evaluating the quality of these graphs involves matching…
In this paper, we propose Text-Aware Pre-training (TAP) for Text-VQA and Text-Caption tasks. These two tasks aim at reading and understanding scene text in images for question answering and image caption generation, respectively. In…
Representation learning on text-attributed graphs (TAGs) integrates structural connectivity with rich textual semantics, enabling applications in diverse domains. Current methods largely rely on contrastive learning to maximize cross-modal…
We study the problem of quantitative facts extraction for text with percentages. For example, given the sentence "30 percent of Americans like watching football, while 20% prefer to watch NBA.", our goal is to obtain a deep understanding of…
Parallel texts (bitexts) have properties that distinguish them from other kinds of parallel data. First, most words translate to only one other word. Second, bitext correspondence is noisy. This article presents methods for biasing…
Recent improvements in KG-to-text generation are due to additional auxiliary pre-training tasks designed to give the fine-tune task a boost in performance. These tasks require extensive computational resources while only suggesting marginal…
Graph partitioning is the problem of dividing the nodes of a graph into balanced partitions while minimizing the edge cut across the partitions. Due to its combinatorial nature, many approximate solutions have been developed, including…
Hybrid data combining both tabular and textual content (e.g., financial reports) are quite pervasive in the real world. However, Question Answering (QA) over such hybrid data is largely neglected in existing research. In this work, we…
This article describes mathematical methods for estimating the top-tail of the wealth distribution and therefrom the share of total wealth that the richest $p$ percent hold, which is an intuitive measure of inequality. As the data base for…
Pooling operations have shown to be effective on computer vision and natural language processing tasks. One challenge of performing pooling operations on graph data is the lack of locality that is not well-defined on graphs. Previous…
Where previous reviews on content-based image retrieval emphasize on what can be seen in an image to bridge the semantic gap, this survey considers what people tag about an image. A comprehensive treatise of three closely linked problems,…
A considerable number of texts encountered daily are somehow connected with each other. For example, Wikipedia articles refer to other articles via hyperlinks, scientific papers relate to others via citations or (co)authors, while tweets…
We evaluate how well LLMs understand African American Language (AAL) in comparison to their performance on White Mainstream English (WME), the encouraged "standard" form of English taught in American classrooms. We measure LLM performance…
Global Average Pooling (GAP) [4] has been used previously to generate class activation for image classification tasks. The motivation behind SIMILARnet comes from the fact that the convolutional filters possess position information of the…
Although conceptualization has been widely studied in semantics and knowledge representation, it is still challenging to find the most accurate concept phrases to characterize the main idea of a text snippet on the fast-growing social…