Related papers: Abstraction not Memory: BERT and the English Artic…
Learning representations that accurately model semantics is an important goal of natural language processing research. Many semantic phenomena depend on syntactic structure. Recent work examines the extent to which state-of-the-art models…
Probing complex language models has recently revealed several insights into linguistic and semantic patterns found in the learned representations. In this paper, we probe BERT specifically to understand and measure the relational knowledge…
Both humans and neural language models are able to perform subject-verb number agreement (SVA). In principle, semantics shouldn't interfere with this task, which only requires syntactic knowledge. In this work we test whether meaning…
Do state-of-the-art natural language understanding models care about word order - one of the most important characteristics of a sequence? Not always! We found 75% to 90% of the correct predictions of BERT-based classifiers, trained on many…
In this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several classification problems. We use a wide set…
Pre-trained models have brought significant improvements to many NLP tasks and have been extensively analyzed. But little is known about the effect of fine-tuning on specific tasks. Intuitively, people may agree that a pre-trained model…
Models based on large-pretrained language models, such as S(entence)BERT, provide effective and efficient sentence embeddings that show high correlation to human similarity ratings, but lack interpretability. On the other hand, graph…
Transformer-based pre-trained language models such as BERT have achieved remarkable results in Semantic Sentence Matching. However, existing models still suffer from insufficient ability to capture subtle differences. Minor noise like word…
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…
Pre-trained language models such as BERT have exhibited remarkable performances in many tasks in natural language understanding (NLU). The tokens in the models are usually fine-grained in the sense that for languages like English they are…
This paper focuses on the development of an advanced intelligent article scoring system that not only assesses the overall quality of written work but also offers detailed feature-based scoring tailored to various article genres. By…
We propose BERTScore, an automatic evaluation metric for text generation. Analogously to common metrics, BERTScore computes a similarity score for each token in the candidate sentence with each token in the reference sentence. However,…
A considerable number of texts encountered daily are somehow connected with each other. For example, Wikipedia articles refer to other articles via hyperlinks, scientific papers relate to others via citations or (co)authors, while tweets…
Pre-trained contextualized embedding models such as BERT are a standard building block in many natural language processing systems. We demonstrate that the sentence-level representations produced by some off-the-shelf contextualized…
Motivated by the promising performance of pre-trained language models, we investigate BERT in an evidence retrieval and claim verification pipeline for the FEVER fact extraction and verification challenge. To this end, we propose to use two…
We evaluate whether BERT, a widely used neural network for sentence processing, acquires an inductive bias towards forming structural generalizations through pretraining on raw data. We conduct four experiments testing its preference for…
Timely feedback is an important part of teaching and learning. Here we describe how a readily available neural network transformer (machine-learning) model (BERT) can be used to give feedback on the structure of the response to an…
More predictable words are easier to process - they are read faster and elicit smaller neural signals associated with processing difficulty, most notably, the N400 component of the event-related brain potential. Thus, it has been argued…
Recently, neural models pretrained on a language modeling task, such as ELMo (Peters et al., 2017), OpenAI GPT (Radford et al., 2018), and BERT (Devlin et al., 2018), have achieved impressive results on various natural language processing…
Generated hateful and toxic content by a portion of users in social media is a rising phenomenon that motivated researchers to dedicate substantial efforts to the challenging direction of hateful content identification. We not only need an…