Related papers: Predicting the Relative Difficulty of Single Sente…

Context of data points, which is usually defined as the other data points in a data set, has been found to play important roles in data representation and classification. In this paper, we study the problem of using context of a data point…

Document-level machine translation conditions on surrounding sentences to produce coherent translations. There has been much recent work in this area with the introduction of custom model architectures and decoding algorithms. This paper…

Different semantic interpretation tasks such as text entailment and question answering require the classification of semantic relations between terms or entities within text. However, in most cases it is not possible to assign a direct…

Comparative reasoning plays a crucial role in text preference prediction; however, large language models (LLMs) often demonstrate inconsistencies in their reasoning. While approaches like Chain-of-Thought improve accuracy in many other…

Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other senses remain unbiased. In comparison to the numerous prior…

Mitigating bias in training on biased datasets is an important open problem. Several techniques have been proposed, however the typical evaluation regime is very limited, considering very narrow data conditions. For instance, the effect of…

Unsupervised vector representations of sentences or documents are a major building block for many language tasks such as sentiment classification. However, current methods are uninterpretable and slow or require large training datasets.…

Linguistic bias in online news and social media is widespread but difficult to measure. Yet, its identification and quantification remain difficult due to subjectivity, context dependence, and the scarcity of high-quality gold-label…

Loneliness does not only have emotional implications on a person but also on his/her well-being. The study of loneliness has been challenging and largely inconclusive in findings because of the several factors that might correlate to the…

We present a set of novel neural supervised and unsupervised approaches for determining the readability of documents. In the unsupervised setting, we leverage neural language models, whereas in the supervised setting, three different neural…

This paper addresses the problem of classifying observations when features are context-sensitive, specifically when the testing set involves a context that is different from the training set. The paper begins with a precise definition of…

The effect of surprisal on processing difficulty has been a central topic of investigation in psycholinguistics. Here, we use eyetracking data to examine three language processing regimes that are common in daily life but have not been…

Due to their similarity-based learning objectives, pretrained sentence encoders often internalize stereotypical assumptions that reflect the social biases that exist within their training corpora. In this paper, we describe several kinds of…

Rhetorical Role Labeling (RRL) assigns a functional role to each sentence in a document and is widely used in legal, medical, and scientific domains. While language models (LMs) achieve strong average performance, they remain unreliable on…

We propose an unsupervised method for sentence summarization using only language modeling. The approach employs two language models, one that is generic (i.e. pretrained), and the other that is specific to the target domain. We show that by…

This paper addresses the problem of classifying observations when features are context-sensitive, especially when the testing set involves a context that is different from the training set. The paper begins with a precise definition of the…

In-context learning is a surprising and important phenomenon that emerged when modern language models were scaled to billions of learned parameters. Without modifying a large language model's weights, it can be tuned to perform various…

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…

With the rapid growth in language processing applications, fairness has emerged as an important consideration in data-driven solutions. Although various fairness definitions have been explored in the recent literature, there is lack of…

We present a clustering-based language model using word embeddings for text readability prediction. Presumably, an Euclidean semantic space hypothesis holds true for word embeddings whose training is done by observing word co-occurrences.…