Related papers: A Comparative Study on Vocabulary Reduction for Ph…
Unsupervised learning of cross-lingual word embedding offers elegant matching of words across languages, but has fundamental limitations in translating sentences. In this paper, we propose simple yet effective methods to improve…
Recent advances in large language model (LLM) pruning have shown state-of-the-art (SotA) compression results in post-training and retraining-free settings while maintaining high predictive performance. However, previous research mainly…
Language models have been shown to be very effective in predicting brain recordings of subjects experiencing complex language stimuli. For a deeper understanding of this alignment, it is important to understand the correspondence between…
Embedding matrices are key components in neural natural language processing (NLP) models that are responsible to provide numerical representations of input tokens.\footnote{In this paper words and subwords are referred to as \textit{tokens}…
Large language models are ubiquitous in natural language processing because they can adapt to new tasks without retraining. However, their sheer scale and complexity present unique challenges and opportunities, prompting researchers and…
Recent advances in the field of abstractive summarization leverage pre-trained language models rather than train a model from scratch. However, such models are sluggish to train and accompanied by a massive overhead. Researchers have…
Retrieval-augmented language models pose a promising alternative to standard language modeling. During pretraining, these models search in a corpus of documents for contextually relevant information that could aid the language modeling…
Label smoothing is commonly used in training deep learning models, wherein one-hot training labels are mixed with uniform label vectors. Empirically, smoothing has been shown to improve both predictive performance and model calibration. In…
Training neural network language models over large vocabularies is still computationally very costly compared to count-based models such as Kneser-Ney. At the same time, neural language models are gaining popularity for many applications…
The positive effect of adding subword information to word embeddings has been demonstrated for predictive models. In this paper we investigate whether similar benefits can also be derived from incorporating subwords into counting models. We…
Generative neural conversational systems are generally trained with the objective of minimizing the entropy loss between the training "hard" targets and the predicted logits. Often, performance gains and improved generalization can be…
Realignment is a promising strategy to improve cross-lingual transfer in multilingual language models. However, empirical results are mixed and often unreliable, particularly for typologically distant or low-resource languages (LRLs)…
Reduced articulatory precision is common in speech, but for dialog its acoustic properties and pragmatic functions have been little studied. We here try to remedy this gap. This technical report contains content that was omitted from the…
Sample efficiency is a crucial property of language models with practical implications for training efficiency. In real-world text, information follows a long-tailed distribution. Yet, we expect models to learn and recall frequent and…
Transformer models have revolutionized natural language processing with their unparalleled ability to grasp complex contextual relationships. However, the vast number of parameters in these models has raised concerns regarding computational…
Neural language models do not scale well when the vocabulary is large. Noise-contrastive estimation (NCE) is a sampling-based method that allows for fast learning with large vocabularies. Although NCE has shown promising performance in…
Recently abstractive spoken language summarization raises emerging research interest, and neural sequence-to-sequence approaches have brought significant performance improvement. However, summarizing long meeting transcripts remains…
Many multilingual NLP applications need to translate words between different languages, but cannot afford the computational expense of inducing or applying a full translation model. For these applications, we have designed a fast algorithm…
In learning-based functionality stealing, the attacker is trying to build a local model based on the victim's outputs. The attacker has to make choices regarding the local model's architecture, optimization method and, specifically for NLP…
Subword-level models have been the dominant paradigm in NLP. However, character-level models have the benefit of seeing each character individually, providing the model with more detailed information that ultimately could lead to better…