Related papers: False perspectives on human language: why statisti…
Language enables humans to share knowledge, reason about the world, and pass on strategies for survival and innovation across generations. At the heart of this process is not just the ability to communicate but also the remarkable…
Analysing whether neural language models encode linguistic information has become popular in NLP. One method of doing so, which is frequently cited to support the claim that models like BERT encode syntax, is called probing; probes are…
Statistics is sometimes described as the science of reasoning under uncertainty. Statistical models provide one view of this uncertainty, but what is frequently neglected is the 'invisible' portion of uncertainty: that assumed not to exist…
Nonsensical and anomalous sentences have been instrumental in the development of computational models of semantic interpretation. A core challenge is to distinguish between what is merely anomalous (but can be interpreted given a supporting…
Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these scales, and can we force them to better capture structure…
Languages emerge and change over time at the population level though interactions between individual speakers. It is, however, hard to directly observe how a single speaker's linguistic innovation precipitates a population-wide change in…
We introduce a new formal model -- based on the mathematical construct of sheaves -- for representing contradictory information in textual sources. This model has the advantage of letting us (a) identify the causes of the inconsistency; (b)…
Is it possible to develop a `physics of language' which can explain the spatial, temporal and social patterns we see, and which can predict future change like we forecast the weather? Such a theory is likely to involve ideas from…
We argue that the words "objectivity" and "subjectivity" in statistics discourse are used in a mostly unhelpful way, and we propose to replace each of them with broader collections of attributes, with objectivity replaced by transparency,…
Though current researches often study the properties of online social relationship from an objective view, we also need to understand individuals' subjective opinions on their interrelationships in social computing studies. Inspired by the…
Humans exhibit garden path effects: When reading sentences that are temporarily structurally ambiguous, they slow down when the structure is disambiguated in favor of the less preferred alternative. Surprisal theory (Hale, 2001; Levy,…
Time series are critical for decision-making in fields like finance and healthcare. Their importance has driven a recent influx of works passing time series into language models, leading to non-trivial forecasting on some datasets. But it…
Large Language Models are built on the so-called distributional semantic approach to linguistic meaning that has the distributional hypothesis at its core. The distributional hypothesis involves a holistic conception of word meaning: the…
While fine-tuned language models perform well on many tasks, they were also shown to rely on superficial surface features such as lexical overlap. Excessive utilization of such heuristics can lead to failure on challenging inputs. We…
Providing plausible responses to why questions is a challenging but critical goal for language based human-machine interaction. Explanations are challenging in that they require many different forms of abstract knowledge and reasoning.…
Latent semantic similarity (LSS) is a measure of the similarity of information exchanges in a conversation. Challenging the assumption that higher LSS bears more positive psychological meaning, we propose that this association might depend…
Neural language models (LMs) perform well on tasks that require sensitivity to syntactic structure. Drawing on the syntactic priming paradigm from psycholinguistics, we propose a novel technique to analyze the representations that enable…
People convey information extremely effectively through spoken interaction using multiple channels of information transmission: the lexical channel of what is said, and the non-lexical channel of how it is said. We propose studying human…
As is the case of many signals produced by complex systems, language presents a statistical structure that is balanced between order and disorder. Here we review and extend recent results from quantitative characterisations of the degree of…
A common assumption in Computational Linguistics is that text representations learnt by multimodal models are richer and more human-like than those by language-only models, as they are grounded in images or audio -- similar to how human…