Related papers: Feature Engineering vs BERT on Twitter Data
Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…
Developing high-performance entity normalization algorithms that can alleviate the term variation problem is of great interest to the biomedical community. Although deep learning-based methods have been successfully applied to biomedical…
Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-ofthe-art results in…
Identifying feature requests and bug reports in user comments holds great potential for development teams. However, automated mining of RE-related information from social media and app stores is challenging since (1) about 70% of user…
This study introduces novel methods for sentiment and opinion classification of tweets to support the New Product Development (NPD) process. Two popular word embedding techniques, Word2Vec and BERT, were evaluated as inputs for classic…
Contextualized word embeddings (CWE) such as provided by ELMo (Peters et al., 2018), Flair NLP (Akbik et al., 2018), or BERT (Devlin et al., 2019) are a major recent innovation in NLP. CWEs provide semantic vector representations of words…
Automatically localizing software bugs to the changesets that induced them has the potential to improve software developer efficiency and to positively affect software quality. To facilitate this automation, a bug report has to be…
Twitter and other social media platforms have become vital sources of real time information during disasters and public safety emergencies. Automatically classifying disaster related tweets can help emergency services respond faster and…
The large number of parameters of some prominent language models, such as BERT, makes their fine-tuning on downstream tasks computationally intensive and energy hungry. Previously researchers were focused on lower bit-width integer data…
Prior research notes that BERT's computational cost grows quadratically with sequence length thus leading to longer training times, higher GPU memory constraints and carbon emissions. While recent work seeks to address these scalability…
How does word frequency in pre-training data affect the behavior of similarity metrics in contextualized BERT embeddings? Are there systematic ways in which some word relationships are exaggerated or understated? In this work, we explore…
Contextualized word embeddings, i.e. vector representations for words in context, are naturally seen as an extension of previous noncontextual distributional semantic models. In this work, we focus on BERT, a deep neural network that…
Manually labelling large collections of text data is a time-consuming, expensive, and laborious task, but one that is necessary to support machine learning based on text datasets. Active learning has been shown to be an effective way to…
Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…
Morphosyntactic lexicons and word vector representations have both proven useful for improving the accuracy of statistical part-of-speech taggers. Here we compare the performances of four systems on datasets covering 16 languages, two of…
We explore advanced fine-tuning techniques to boost BERT's performance in sentiment analysis, paraphrase detection, and semantic textual similarity. Our approach leverages SMART regularization to combat overfitting, improves hyperparameter…
The main approaches to sentiment analysis are rule-based methods and ma-chine learning, in particular, deep neural network models with the Trans-former architecture, including BERT. The performance of neural network models in the tasks of…
The current dominance of deep neural networks in natural language processing is based on contextual embeddings such as ELMo, BERT, and BERT derivatives. Most existing work focuses on English; in contrast, we present here the first…
This paper describes a machine learning algorithm for document (re)ranking, in which queries and documents are firstly encoded using BERT [1], and on top of that a learning-to-rank (LTR) model constructed with TF-Ranking (TFR) [2] is…
We study the utility of the lexical translation model (IBM Model 1) for English text retrieval, in particular, its neural variants that are trained end-to-end. We use the neural Model1 as an aggregator layer applied to context-free or…