相关论文: Representing Numbers in NLP: a Survey and a Vision

Although behavioral studies have documented numerical reasoning errors in large language models (LLMs), the underlying representational mechanisms remain unclear. We hypothesize that numerical attributes occupy shared latent subspaces and…

Relational reasoning lies at the core of many NLP tasks, drawing on complementary signals from text and graphs. While prior research has investigated how to leverage this dual complementarity, a detailed and systematic understanding of…

Given the complexity of combinations of tasks, languages, and domains in natural language processing (NLP) research, it is computationally prohibitive to exhaustively test newly proposed models on each possible experimental setting. In this…

To demystify the "black box" property of deep neural networks for natural language processing (NLP), several methods have been proposed to interpret their predictions by measuring the change in prediction probability after erasing each…

When people interpret text, they rely on inferences that go beyond the observed language itself. Inspired by this observation, we introduce a method for the analysis of text that takes implicitly communicated content explicitly into…

The close link between cognitive decline and language has fostered long-standing collaboration between the NLP and medical communities in dementia research. To examine this, we reviewed over 240 papers applying NLP to dementia-related…

Recently, the Natural Language Inference (NLI) task has been studied for semi-structured tables that do not have a strict format. Although neural approaches have achieved high performance in various types of NLI, including NLI between…

Artificial Intelligence (AI) has huge impact on our daily lives with applications such as voice assistants, facial recognition, chatbots, autonomously driving cars, etc. Natural Language Processing (NLP) is a cross-discipline of AI and…

The task of text classification is usually divided into two stages: {\it text feature extraction} and {\it classification}. In this standard formalization categories are merely represented as indexes in the label vocabulary, and the model…

Deep learning has become the dominant approach in coping with various tasks in Natural LanguageProcessing (NLP). Although text inputs are typically represented as a sequence of tokens, there isa rich variety of NLP problems that can be best…

We introduce a new methodology for intrinsic evaluation of word representations. Specifically, we identify four fundamental criteria based on the characteristics of natural language that pose difficulties to NLP systems; and develop tests…

Embedding text sequences is a widespread requirement in modern language understanding. Existing approaches focus largely on constant-size representations. This is problematic, as the amount of information contained in text often varies with…

This work lists and describes the main recent strategies for building fixed-length, dense and distributed representations for words, based on the distributional hypothesis. These representations are now commonly called word embeddings and,…

Large language models (LLMs) continue to face challenges in reliably solving reasoning tasks, particularly those that require precise rule following, as often found in mathematical reasoning. This paper introduces a novel neurosymbolic…

Counting is one of the fundamental abilities of large language models (LLMs) and large vision-language models (LVLMs). This paper examines how these foundation models represent and compute numerical information in counting tasks. We use…

We present one of the preliminary NLP works under the challenging setup of Learning from Label Proportions (LLP), where the data is provided in an aggregate form called bags and only the proportion of samples in each class as the ground…

Despite its simplicity, bag-of-n-grams sen- tence representation has been found to excel in some NLP tasks. However, it has not re- ceived much attention in recent years and fur- ther analysis on its properties is necessary. We propose a…

Working with documents is a key part of almost any knowledge work, from contextualizing research in a literature review to reviewing legal precedent. Recently, as their capabilities have expanded, primarily text-based NLP systems have often…

Machines have achieved a broad and growing set of linguistic competencies, thanks to recent progress in Natural Language Processing (NLP). Psychologists have shown increasing interest in such models, comparing their output to psychological…

Deep learning models have performed well on many NLP tasks. However, their internal mechanisms are typically difficult for humans to understand. The development of methods to explain models has become a key issue in the reliability of deep…