Related papers: Statistical Inferences for Polarity Identification…
Human language has a distinct systematic structure, where utterances break into individually meaningful words which are combined to form phrases. We show that natural-language-like systematicity arises in codes that are constrained by a…
Decision-making is often dependent on uncertain data, e.g. data associated with confidence scores or probabilities. We present a comparison of different information presentations for uncertain data and, for the first time, measure their…
We present a hybrid statistical and grammar-based system for surface natural language generation (NLG) that uses grammar rules, conditions on using those grammar rules, and corpus statistics to determine the word order. We also describe how…
Prediction in language has traditionally been studied using simple designs in which neural responses to expected and unexpected words are compared in a categorical fashion. However, these designs have been contested as being `prediction…
Using human evaluation of 100,000 words spread across 24 corpora in 10 languages diverse in origin and culture, we present evidence of a deep imprint of human sociality in language, observing that (1) the words of natural human language…
With the increasing interest in using large language models (LLMs) for planning in natural language, understanding their behaviors becomes an important research question. This work conducts a systematic investigation of LLMs' ability to…
Despite the recent progress in language generation models, their outputs may not always meet user expectations. In this work, we study whether informational feedback in natural language can be leveraged to improve generation quality and…
The development of an automatic way to extract user opinions about products, movies, and foods from online social network (OSN) interactions is among the main interests of sentiment analysis and opinion mining studies. Existing approaches…
Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring…
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…
For propensity score analysis and sparse estimation, we develop an information criterion for determining the regularization parameters needed in variable selection. First, for Gaussian distribution-based causal inference models, we extend…
Despite alarm over the reliance of machine learning systems on so-called spurious patterns, the term lacks coherent meaning in standard statistical frameworks. However, the language of causality offers clarity: spurious associations are due…
Spoken communication occurs in a "noisy channel" characterized by high levels of environmental noise, variability within and between speakers, and lexical and syntactic ambiguity. Given these properties of the received linguistic input,…
The goal of this research was to find a way to extend the capabilities of computers through the processing of language in a more human way, and present applications which demonstrate the power of this method. This research presents a novel…
We present a setup for training, evaluating and interpreting neural language models, that uses artificial, language-like data. The data is generated using a massive probabilistic grammar (based on state-split PCFGs), that is itself derived…
There has been a lot of interest in understanding what information is captured by hidden representations of language models (LMs). Typically, interpretation methods i) do not guarantee that the model actually uses the encoded information,…
This paper presents a new method for automatically detecting words with lexical gender in large-scale language datasets. Currently, the evaluation of gender bias in natural language processing relies on manually compiled lexicons of…
When working with textual data, a natural application of disentangled representations is fair classification where the goal is to make predictions without being biased (or influenced) by sensitive attributes that may be present in the data…
Understanding human behaviour in decision problems and strategic interactions has wide-ranging applications in economics, psychology, and artificial intelligence. Game theory offers a robust foundation for this understanding, based on the…
Scientific information expresses human understanding of nature. This knowledge is largely disseminated in different forms of text, including scientific papers, news articles, and discourse among people on social media. While important for…