相关论文: Expoiting Syntactic Structure for Language Modelin…

The eventual goal of a language model is to accurately predict the value of a missing word given its context. We present an approach to word prediction that is based on learning a representation for each word as a function of words and…

Word representations induced from models with discrete latent variables (e.g.\ HMMs) have been shown to be beneficial in many NLP applications. In this work, we exploit labeled syntactic dependency trees and formalize the induction problem…

With the advent of powerful neural language models over the last few years, research attention has increasingly focused on what aspects of language they represent that make them so successful. Several testing methodologies have been…

Transformer-based language models have recently achieved remarkable results in many natural language tasks. However, performance on leaderboards is generally achieved by leveraging massive amounts of training data, and rarely by encoding…

In many current speech recognizers, a statistical language model is used to indicate how likely it is that a certain word will be spoken next, given the words recognized so far. How can statistical language models be improved so that more…

A stochastic model of short-term verbal memory is proposed, in which the psychological state of the subject is encoded as the instantaneous position of a particle diffusing over a semantic graph with a probabilistic structure. The model is…

Prompted models have demonstrated impressive few-shot learning abilities. Repeated interactions at test-time with a single model, or the composition of multiple models together, further expands capabilities. These compositions are…

This study introduces a groundbreaking approach to simultaneous interpretation by directly leveraging the predictive capabilities of Large Language Models (LLMs). We present a novel algorithm that generates real-time translations by…

The goal of this thesis is to advance the exploration of the statistical language learning design space. In pursuit of that goal, the thesis makes two main theoretical contributions: (i) it identifies a new class of designs by specifying an…

Many successful approaches to semantic parsing build on top of the syntactic analysis of text, and make use of distributional representations or statistical models to match parses to ontology-specific queries. This paper presents a novel…

Learning structural information from observational data is central to producing new knowledge outside the training corpus. This holds for mechanistic understanding in scientific discovery as well as flexible test-time compositional…

The dominant language modeling paradigm handles text as a sequence of discrete tokens. While that approach can capture the latent structure of the text, it is inherently constrained to sequential dynamics for text generation. We propose a…

It is recently demonstrated that cortical activity can track the time courses of phrases and sentences during speech listening. Here, we propose a plausible neural processing framework to explain this phenomenon. It is argued that the brain…

Recent language models, especially those based on recurrent neural networks (RNNs), make it possible to generate natural language from a learned probability. Language generation has wide applications including machine translation,…

Dependency parsing is a fundamental task in natural language processing (NLP), aiming to identify syntactic dependencies and construct a syntactic tree for a given sentence. Traditional dependency parsing models typically construct…

Accurate syntactic representations are essential for robust generalization in natural language. Recent work has found that pre-training can teach language models to rely on hierarchical syntactic features - as opposed to incorrect linear…

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…

Most current word prediction systems make use of n-gram language models (LM) to estimate the probability of the following word in a phrase. In the past years there have been many attempts to enrich such language models with further…

This chapter critically examines the potential contributions of modern language models to theoretical linguistics. Despite their focus on engineering goals, these models' ability to acquire sophisticated linguistic knowledge from mere…

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,…