Related papers: Learning to Write Rationally: How Information Is D…
Grammaticality and likelihood are distinct notions in human language. Pretrained language models (LMs), which are probabilistic models of language fitted to maximize corpus likelihood, generate grammatically well-formed text and…
Can self-organization of scientific communication be specified by using literature-based indicators? In this study, we explore this question by applying entropy measures to typical "Mode-2" fields of knowledge production. We hypothesized…
The intelligibility of speech relies on the ability of interlocutors to dynamically align their expectations about the rates at which informative changes in signals occur. Exactly how this is achieved remains an open question. We propose…
Recent advances in generative AI technologies like large language models have boosted the incorporation of AI assistance in writing workflows, leading to the rise of a new paradigm of human-AI co-creation in writing. To understand how…
We study distributed knowledge, which is what privately informed agents come to know by communicating freely with one another and sharing everything they know. Knowledge is not necessarily partitional: agents may be boundedly rational and…
Automated Essay Scoring (AES) has been quite popular and is being widely used. However, lack of appropriate methodology for rating nonnative English speakers' essays has meant a lopsided advancement in this field. In this paper, we report…
Large language models (LLMs) tend to generate homogenous texts, which may impact the diversity of knowledge generated across different outputs. Given their potential to replace existing forms of knowledge acquisition, this poses a risk of…
This paper explores the impact of variable pragmatic competence on communicative success through simulating language learning and conversing between speakers and listeners with different levels of reasoning abilities. Through studying this…
Organisms and algorithms learn probability distributions from previous observations, either over evolutionary time or on the fly. In the absence of regularities, estimating the underlying distribution from data would require observing each…
Despite LLMs' explicit alignment against demographic stereotypes, they have been shown to exhibit biases under various social contexts. In this work, we find that LLMs exhibit concerning biases in how they associate solution veracity with…
Distributed representations of meaning are a natural way to encode covariance relationships between words and phrases in NLP. By overcoming data sparsity problems, as well as providing information about semantic relatedness which is not…
Sequence-processing neural networks led to remarkable progress on many NLP tasks. As a consequence, there has been increasing interest in understanding to what extent they process language as humans do. We aim here to uncover which biases…
Natural languages display a trade-off among different strategies to convey syntactic structure, such as word order or inflection. This trade-off, however, has not appeared in recent simulations of iterated language learning with neural…
The dependence of the frequency distributions due to multiple meanings of words in a text is investigated by deleting letters. By coding the words with fewer letters the number of meanings per coded word increases. This increase is measured…
This paper presents an architecture for the generation of spoken monologues with contextually appropriate intonation. A two-tiered information structure representation is used in the high-level content planning and sentence planning stages…
The number of research papers written has been growing at least linearly -- if not exponentially -- in recent years. In proportion, the amount of time a reader allocates per paper has been decreasing. While an accessible paper will be…
Pretrained language models (PLMs), such as GPT2, have achieved remarkable empirical performance in text generation tasks. However, pretrained on large-scale natural language corpora, the generated text from PLMs may exhibit social bias…
Word embeddings allow natural language processing systems to share statistical information across related words. These embeddings are typically based on distributional statistics, making it difficult for them to generalize to rare or unseen…
As natural language processing (NLP) has recently seen an unprecedented level of excitement, and more people are eager to enter the field, it is unclear whether current research reproducibility efforts are sufficient for this group of…
Prevalent ungrammatical expressions and disfluencies in spontaneous speech from second language (L2) learners pose unique challenges to Automatic Speech Recognition (ASR) systems. However, few datasets are tailored to L2 learner speech. We…