Related papers: Modeling Probabilistic Reduction using Information…
The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question…
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…
In spite of their superior performance, neural probabilistic language models (NPLMs) remain far less widely used than n-gram models due to their notoriously long training times, which are measured in weeks even for moderately-sized…
To measure how well pretrained representations encode some linguistic property, it is common to use accuracy of a probe, i.e. a classifier trained to predict the property from the representations. Despite widespread adoption of probes,…
Recent work has found that contemporary language models such as transformers can become so good at next-word prediction that the probabilities they calculate become worse for predicting reading time. In this paper, we propose that this can…
In many applications of natural language processing (NLP) it is necessary to determine the likelihood of a given word combination. For example, a speech recognizer may need to determine which of the two word combinations ``eat a peach'' and…
An exhaustive study on neural network language modeling (NNLM) is performed in this paper. Different architectures of basic neural network language models are described and examined. A number of different improvements over basic neural…
In this work, we investigate the effect of language models (LMs) with different context lengths and label units (phoneme vs. word) used in sequence discriminative training for phoneme-based neural transducers. Both lattice-free and…
We propose to train bi-directional neural network language model(NNLM) with noise contrastive estimation(NCE). Experiments are conducted on a rescore task on the PTB data set. It is shown that NCE-trained bi-directional NNLM outperformed…
The logical negation property (LNP), which implies generating different predictions for semantically opposite inputs, is an important property that a trustworthy language model must satisfy. However, much recent evidence shows that…
Chinese input recommendation plays an important role in alleviating human cost in typing Chinese words, especially in the scenario of mobile applications. The fundamental problem is to predict the conditional probability of the next word…
It's better to say "I can't answer" than to answer incorrectly. This selective prediction ability is crucial for NLP systems to be reliably deployed in real-world applications. Prior work has shown that existing selective prediction…
Syntactic structures used to play a vital role in natural language processing (NLP), but since the deep learning revolution, NLP has been gradually dominated by neural models that do not consider syntactic structures in their design. One…
The primary research questions of this paper center on defining the amount of context that is necessary and/or appropriate when investigating the relationship between language model probabilities and cognitive phenomena. We investigate…
Pre-trained language models (PLMs) have made significant advances in natural language inference (NLI) tasks, however their sensitivity to textual perturbations and dependence on large datasets indicate an over-reliance on shallow…
Discrete diffusion models offer global context awareness and flexible parallel generation. However, uniform random noise schedulers in standard DLLM training overlook the highly non-uniform information density inherent in real-world…
By positing a relationship between naturalistic reading times and information-theoretic surprisal, surprisal theory (Hale, 2001; Levy, 2008) provides a natural interface between language models and psycholinguistic models. This paper…
Internal language model (ILM) subtraction has been widely applied to improve the performance of the RNN-Transducer with external language model (LM) fusion for speech recognition. In this work, we show that sequence discriminative training…
Many inductive logic programming (ILP) methods are incapable of learning programs from probabilistic background knowledge, e.g. coming from sensory data or neural networks with probabilities. We propose Propper, which handles flawed and…
A neural probabilistic language model (NPLM) provides an idea to achieve the better perplexity than n-gram language model and their smoothed language models. This paper investigates application area in bilingual NLP, specifically…