Related papers: On the Interpretation of Spreadsheets within their…

Humans refer to objects in their environments all the time, especially in dialogue with other people. We explore generating and comprehending natural language referring expressions for objects in images. In particular, we focus on…

We explore link prediction as a proxy for automatically surfacing documents from existing literature that might be topically or contextually relevant to a new document. Our model uses transformer-based graph embeddings to encode the meaning…

Subset models provide a new semantics for justifcation logic. The main idea of subset models is that evidence terms are interpreted as sets of possible worlds. A term then justifies a formula if that formula is true in each world of the…

Inter-sentence relation extraction deals with a number of complex semantic relationships in documents, which require local, non-local, syntactic and semantic dependencies. Existing methods do not fully exploit such dependencies. We present…

The Web today has millions of datasets, and the number of datasets continues to grow at a rapid pace. These datasets are not standalone entities; rather, they are intricately connected through complex relationships. Semantic relationships…

Efficiently navigating complex environments requires agents to internalize the underlying logic of their world, yet standard world modelling methods often struggle with sample inefficiency, lack of transparency, and poor scalability. We…

To correctly use in-context information, language models (LMs) must bind entities to their attributes. For example, given a context describing a "green square" and a "blue circle", LMs must bind the shapes to their respective colors. We…

In this work, we systematically investigate how well current models of coherence can capture aspects of text implicated in discourse organisation. We devise two datasets of various linguistic alterations that undermine coherence and test…

Since early machine learning models, metrics such as accuracy and precision have been the de facto way to evaluate and compare trained models. However, a single metric number doesn't fully capture the similarities and differences between…

With the growing abundance of unlabeled data in real-world tasks, researchers have to rely on the predictions given by black-boxed computational models. However, it is an often neglected fact that these models may be scoring high on…

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

Long document classification presents challenges in capturing both local and global dependencies due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequately model…

In Part 1, we showed how to develop a conceptual model of a problem involving variables of multiple dimensions, like Products, Regions, Sectors and Months. The conceptual model is presented as a Formula Diagram, giving a global view of the…

We introduce SQLSpace, a human-interpretable, generalizable, compact representation for text-to-SQL examples derived with minimal human intervention. We demonstrate the utility of these representations in evaluation with three use cases:…

We develop models to classify desirable evidence and desirable reasoning revisions in student argumentative writing. We explore two ways to improve classifier performance - using the essay context of the revision, and using the feedback…

There has been a significant amount of research into spreadsheets over the last two decades. Errors in spreadsheets are well documented. Once used mainly for simple functions such as logging, tracking and totalling information, spreadsheets…

Several methods have been proposed for classifying long textual documents using Transformers. However, there is a lack of consensus on a benchmark to enable a fair comparison among different approaches. In this paper, we provide a…

Interpretability methods are developed to understand the working mechanisms of black-box models, which is crucial to their responsible deployment. Fulfilling this goal requires both that the explanations generated by these methods are…

In this paper, we ask if it is possible to increase the interpretability in multivariate analysis by aligning and projecting covariates onto comparative subspaces. We demonstrate our method as well as the interpretative power of PLS…

Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities. However, effective aggregation of relevant…