相关论文: Corpus-Guided Contrast Sets for Morphosyntactic Fe…

Language change is a cultural evolutionary process in which variants of linguistic variables change in frequency through processes analogous to mutation, selection and genetic drift. In this work, we apply a recently-introduced method to…

Machine-Generated Text (MGT) detection, a task that discriminates MGT from Human-Written Text (HWT), plays a crucial role in preventing misuse of text generative models, which excel in mimicking human writing style recently. Latest proposed…

Growing digital archives and improving algorithms for automatic analysis of text and speech create new research opportunities for fundamental research in phonetics. Such empirical approaches allow statistical evaluation of a much larger set…

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…

This work examines the impact of cross-linguistic transfer on grammatical errors in English as Second Language (ESL) texts. Using a computational framework that formalizes the theory of Contrastive Analysis (CA), we demonstrate that…

Morphologically rich languages accentuate two properties of distributional vector space models: 1) the difficulty of inducing accurate representations for low-frequency word forms; and 2) insensitivity to distinct lexical relations that…

It is now a common practice to compare models of human language processing by predicting participant reactions (such as reading times) to corpora consisting of rich naturalistic linguistic materials. However, many of the corpora used in…

Contrastive analysis (CA) refers to the exploration of variations uniquely enriched in a target dataset as compared to a corresponding background dataset generated from sources of variation that are irrelevant to a given task. For example,…

The disparity in language resources poses a challenge in multilingual NLP, with high-resource languages benefiting from extensive data, while low-resource languages lack sufficient data for effective training. Our Contrastive Language…

We present a methodological framework to discover linguistic and discursive patterns associated to different social groups through contrastive synthetic text generation and statistical analysis. In contrast with previous approaches, we aim…

We study cultural and socioeconomic diversity in contrastive vision-language models (VLMs). Using a broad range of benchmark datasets and evaluation metrics, we bring to attention several important findings. First, the common filtering of…

Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus…

Robot evaluations in language-guided, real world settings are time-consuming and often sample only a small space of potential instructions across complex scenes. In this work, we introduce contrast sets for robotics as an approach to make…

A Prompt-based Text-To-Speech model allows a user to control different aspects of speech, such as speaking rate and perceived gender, through natural language instruction. Although user-friendly, such approaches are on one hand constrained:…

This paper develops a construction-based dialectometry capable of identifying previously unknown constructions and measuring the degree to which a given construction is subject to regional variation. The central idea is to learn a grammar…

Vision-language models are growing in popularity and public visibility to generate, edit, and caption images at scale; but their outputs can perpetuate and amplify societal biases learned during pre-training on uncurated image-text pairs…

Contrastive learning has become pivotal in unsupervised representation learning, with frameworks like Momentum Contrast (MoCo) effectively utilizing large negative sample sets to extract discriminative features. However, traditional…

The recent demand for customized image generation raises a need for techniques that effectively extract the common concept from small sets of images. Existing methods typically rely on additional guidance, such as text prompts or spatial…

In English, prosody adds a broad range of information to segment sequences, from information structure (e.g. contrast) to stylistic variation (e.g. expression of emotion). However, when learning to control prosody in text-to-speech voices,…

Large language models (LLMs) are trained on huge amounts of textual data, and concerns have been raised that the limits of such data may soon be reached. A potential solution is to train on synthetic data sampled from LLMs. In this work, we…