相关论文: Low Frequency Names Exhibit Bias and Overfitting i…

Prediction head is a crucial component of Transformer language models. Despite its direct impact on prediction, this component has often been overlooked in analyzing Transformers. In this study, we investigate the inner workings of the…

Gender bias in language models has gained increasing attention in the field of natural language processing. Encoder-based transformer models, which have achieved state-of-the-art performance in various language tasks, have been shown to…

Low-resource named entity recognition is still an open problem in NLP. Most state-of-the-art systems require tens of thousands of annotated sentences in order to obtain high performance. However, for most of the world's languages, it is…

In this paper, we introduce the NameRec* task, which aims to do highly accurate and fine-grained person name recognition. Traditional Named Entity Recognition models have good performance in recognising well-formed person names from text…

Neural language models learn, to varying degrees of accuracy, the grammatical properties of natural languages. In this work, we investigate whether there are systematic sources of variation in the language models' accuracy. Focusing on…

Large Language Models (LLMs) have made substantial progress in the past several months, shattering state-of-the-art benchmarks in many domains. This paper investigates LLMs' behavior with respect to gender stereotypes, a known issue for…

Masked Language Modeling (MLM) is widely used to pretrain language models. The standard random masking strategy in MLM causes the pre-trained language models (PLMs) to be biased toward high-frequency tokens. Representation learning of rare…

Names are deeply tied to human identity. They can serve as markers of individuality, cultural heritage, and personal history. However, using names as a core indicator of identity can lead to over-simplification of complex identities. When…

Real-world data usually exhibits a long-tailed distribution,with a few frequent labels and a lot of few-shot labels. The study of institution name normalization is a perfect application case showing this phenomenon. There are many…

Gender-inclusive NLP research has documented the harmful limitations of gender binary-centric large language models (LLM), such as the inability to correctly use gender-diverse English neopronouns (e.g., xe, zir, fae). While data scarcity…

Large language models (LLMs) are increasingly being used in user-facing applications, from providing medical consultations to job interview advice. Recent research suggests that these models are becoming increasingly proficient at inferring…

Modern language models are typically trained over subword sequences, but ultimately define probabilities over character-strings. Ideally, the choice of the tokeniser -- which maps character-strings to subwords -- should not affect the…

Text simplification seeks to improve readability while retaining the original content and meaning. Our study investigates whether pre-trained classifiers also maintain such coherence by comparing their predictions on both original and…

CNNs exhibit many behaviors different from humans, one of which is the capability of employing high-frequency components. This paper discusses the frequency bias phenomenon in image classification tasks: the high-frequency components are…

In the current landscape of language model research, larger models, larger datasets and more compute seems to be the only way to advance towards intelligence. While there have been extensive studies of scaling laws and models' scaling…

Language-model (LM) surprisal is widely used as a proxy for contextual predictability and has been reported to correlate with metaphor novelty judgments. However, surprisal is tightly intertwined with lexical frequency. We explore this…

We report investigations on the statistical characteristics of the baby names given between 1910 and 2010 in the United States of America. For each year, the 100 most frequent names in the USA are sorted out. For these names, the…

Language models (LMs) have become pivotal in the realm of technological advancements. While their capabilities are vast and transformative, they often include societal biases encoded in the human-produced datasets used for their training.…

Predicting gender by the first name is not a simple task. In many applications, especially in the natural language processing (NLP) field, this task may be necessary, mainly when considering foreign names. In this paper, we examined and…

Models trained to estimate word probabilities in context have become ubiquitous in natural language processing. How do these models use lexical cues in context to inform their word probabilities? To answer this question, we present a case…