Related papers: GEMINI: A Natural Language System for Spoken-Langu…
We develop a formal grammatical system called a link grammar, show how English grammar can be encoded in such a system, and give algorithms for efficiently parsing with a link grammar. Although the expressive power of link grammars is…
Artificial intelligence systems exhibit many useful capabilities, but they appear to lack understanding. This essay describes how we could go about constructing a machine capable of understanding. As John Locke (1689) pointed out words are…
Natural language is compositional; the meaning of a sentence is a function of the meaning of its parts. This property allows humans to create and interpret novel sentences, generalizing robustly outside their prior experience. Neural…
It has recently become feasible to run personal digital assistants on phones and other personal devices. In this paper we describe a design for a natural language understanding system that runs on device. In comparison to a server-based…
An important component of achieving language understanding is mastering the composition of sentence meaning, but an immediate challenge to solving this problem is the opacity of sentence vector representations produced by current neural…
We present an approach to natural language understanding based on a computable grammar of constructions. A "construction" consists of a set of features of form and a description of meaning in a context. A grammar is a set of constructions.…
The Gemini theorem asserts that, given certain reasonable assumptions, no physical system can be certainly aware of its own existence. The theorem can be proved algorithmically, but the proof of this theorem is somewhat obscure, and there…
Many Machine Reading and Natural Language Understanding tasks require reading supporting text in order to answer questions. For example, in Question Answering, the supporting text can be newswire or Wikipedia articles; in Natural Language…
A class of explainable NLP models for reasoning tasks support their decisions by generating free-form or structured explanations, but what happens when these supporting structures contain errors? Our goal is to allow users to interactively…
Providing natural language-based explanations to justify recommendations helps to improve users' satisfaction and gain users' trust. However, as current explanation generation methods are commonly trained with an objective to mimic existing…
Providing natural language explanations for recommendations is particularly useful from the perspective of a non-expert user. Although several methods for providing such explanations have recently been proposed, we argue that an important…
We introduce a method to measure uncertainty in large language models. For tasks like question answering, it is essential to know when we can trust the natural language outputs of foundation models. We show that measuring uncertainty in…
Natural language processing for programming aims to use NLP techniques to assist programming. It is increasingly prevalent for its effectiveness in improving productivity. Distinct from natural language, a programming language is highly…
The pattern matching capabilities of neural networks can be used to locate syntactic constituents of natural language. This paper describes a fully automated hybrid system, using neural nets operating within a grammatic framework. It…
We argue that grammatical processing is a viable alternative to concept spotting for processing spoken input in a practical dialogue system. We discuss the structure of the grammar, the properties of the parser, and a method for achieving…
Natural language is among the most accessible tools for explaining decisions to humans, and large pretrained language models (PLMs) have demonstrated impressive abilities to generate coherent natural language explanations (NLE). The…
Recently, there has been much interest in the question of whether deep natural language understanding models exhibit systematicity; generalizing such that units like words make consistent contributions to the meaning of the sentences in…
Multilinear Grammar provides a framework for integrating the many different syntagmatic structures of language into a coherent semiotically based Rank Interpretation Architecture, with default linear grammars at each rank. The architecture…
Traditional evaluation metrics like BLEU and ROUGE fall short when capturing the nuanced qualities of generated text, particularly when there is no single ground truth. In this paper, we explore the potential of Large Language Models…
Native language identification (NLI) is the task of training (via supervised machine learning) a classifier that guesses the native language of the author of a text. This task has been extensively researched in the last decade, and the…