Related papers: Inducing Syntactic Trees from BERT Representations
The skip-thought model has been proven to be effective at learning sentence representations and capturing sentence semantics. In this paper, we propose a suite of techniques to trim and improve it. First, we validate a hypothesis that,…
We propose a novel data augmentation method for labeled sentences called conditional BERT contextual augmentation. Data augmentation methods are often applied to prevent overfitting and improve generalization of deep neural network models.…
Learning effective representations of sentences is one of the core missions of natural language understanding. Existing models either train on a vast amount of text, or require costly, manually curated sentence relation datasets. We show…
Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these scales, and can we force them to better capture structure…
Recent research has shown that mixed-initiative conversational search, based on the interaction between users and computers to clarify and improve a query, provides enormous advantages. Nonetheless, incorporating additional information…
Representations derived from models such as BERT (Bidirectional Encoder Representations from Transformers) and HuBERT (Hidden units BERT), have helped to achieve state-of-the-art performance in dimensional speech emotion recognition.…
Subjective bias detection is critical for applications like propaganda detection, content recommendation, sentiment analysis, and bias neutralization. This bias is introduced in natural language via inflammatory words and phrases, casting…
Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information. Meanwhile, syntactic information has been proved to be crucial for the success of NLP…
Pre-trained models are widely used in the tasks of natural language processing nowadays. However, in the specific field of text simplification, the research on improving pre-trained models is still blank. In this work, we propose a…
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…
Pre-trained contextual language models are ubiquitously employed for language understanding tasks, but are unsuitable for resource-constrained systems. Noncontextual word embeddings are an efficient alternative in these settings. Such…
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…
Single document summarization has enjoyed renewed interests in recent years thanks to the popularity of neural network models and the availability of large-scale datasets. In this paper we develop an unsupervised approach arguing that it is…
In recent years, the introduction of the Transformer models sparked a revolution in natural language processing (NLP). BERT was one of the first text encoders using only the attention mechanism without any recurrent parts to achieve…
Fine-tuned Bidirectional Encoder Representations from Transformers (BERT)-based sequence classification models have proven to be effective for detecting Alzheimer's Disease (AD) from transcripts of human speech. However, previous research…
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…
Missing sentence generation (or sentence infilling) fosters a wide range of applications in natural language generation, such as document auto-completion and meeting note expansion. This task asks the model to generate intermediate missing…
Relation extraction is the task of determining the relation between two entities in a sentence. Distantly-supervised models are popular for this task. However, sentences can be long and two entities can be located far from each other in a…
We present an introductory investigation into continuous-space vector representations of sentences. We acquire pairs of very similar sentences differing only by a small alterations (such as change of a noun, adding an adjective, noun or…
Contextualized embeddings such as BERT can serve as strong input representations to NLP tasks, outperforming their static embeddings counterparts such as skip-gram, CBOW and GloVe. However, such embeddings are dynamic, calculated according…