Related papers: BERMo: What can BERT learn from ELMo?
Probes, supervised models trained to predict properties (like parts-of-speech) from representations (like ELMo), have achieved high accuracy on a range of linguistic tasks. But does this mean that the representations encode linguistic…
Pre-trained language models such as BERT have been a key ingredient to achieve state-of-the-art results on a variety of tasks in natural language processing and, more recently, also in information retrieval.Recent research even claims that…
Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. However, their hefty computational and memory demands make them challenging to deploy to…
The mental health assessment of middle school students has always been one of the focuses in the field of education. This paper introduces a new ensemble learning network based on BERT, employing the concept of enhancing model performance…
Recently, pre-trained models have been the dominant paradigm in natural language processing. They achieved remarkable state-of-the-art performance across a wide range of related tasks, such as textual entailment, natural language inference,…
Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from…
We apply contextualised word embeddings to lexical semantic change detection in the SemEval-2020 Shared Task 1. This paper focuses on Subtask 2, ranking words by the degree of their semantic drift over time. We analyse the performance of…
Transfer learning in natural language processing (NLP), as realized using models like BERT (Bi-directional Encoder Representation from Transformer), has significantly improved language representation with models that can tackle challenging…
Recently developed large pre-trained language models, e.g., BERT, have achieved remarkable performance in many downstream natural language processing applications. These pre-trained language models often contain hundreds of millions of…
This paper introduces HeBERT and HebEMO. HeBERT is a Transformer-based model for modern Hebrew text, which relies on a BERT (Bidirectional Encoder Representations for Transformers) architecture. BERT has been shown to outperform alternative…
Language models have been supervised with both language-only objective and visual grounding in existing studies of visual-grounded language learning. However, due to differences in the distribution and scale of visual-grounded datasets and…
Fine-tuning pre-trained models provides significant advantages in downstream performance. The ubiquitous nature of pre-trained models such as BERT and its derivatives in natural language processing has also led to a proliferation of…
Recently, Natural Language Processing (NLP) has witnessed an impressive progress in many areas, due to the advent of novel, pretrained contextual representation models. In particular, Devlin et al. (2019) proposed a model, called BERT…
In this work we leverage recent advances in context-sensitive language models to improve the task of query expansion. Contextualized word representation models, such as ELMo and BERT, are rapidly replacing static embedding models. We…
We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their…
Identifying algorithms for computational efficient unsupervised training of large language models is an important and active area of research. In this work, we develop and study a straightforward, dynamic always-sparse pre-training approach…
Transformer-based NLP models are trained using hundreds of millions or even billions of parameters, limiting their applicability in computationally constrained environments. While the number of parameters generally correlates with…
Estimation of semantic similarity is an important research problem both in natural language processing and the natural language understanding, and that has tremendous application on various downstream tasks such as question answering,…
Pre-training a language model and then fine-tuning it for downstream tasks has demonstrated state-of-the-art results for various NLP tasks. Pre-training is usually independent of the downstream task, and previous works have shown that this…
Neural network-based representations ("embeddings") have dramatically advanced natural language processing (NLP) tasks, including clinical NLP tasks such as concept extraction. Recently, however, more advanced embedding methods and…