Related papers: Connecting degree and polarity: An artificial lang…

Representation of linguistic phenomena in computational language models is typically assessed against the predictions of existing linguistic theories of these phenomena. Using the notion of polarity as a case study, we show that this is not…

Previous studies investigating the syntactic abilities of deep learning models have not targeted the relationship between the strength of the grammatical generalization and the amount of evidence to which the model is exposed during…

Aspect-based sentiment analysis (ABSA) predicts sentiment polarity towards a specific aspect in the given sentence. While pre-trained language models such as BERT have achieved great success, incorporating dynamic semantic changes into ABSA…

When performing Polarity Detection for different words in a sentence, we need to look at the words around to understand the sentiment. Massively pretrained language models like BERT can encode not only just the words in a document but also…

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…

Models trained to estimate word probabilities in context have become ubiquitous in natural language processing. How do these models use lexical cues in context to inform their word probabilities? To answer this question, we present a case…

We propose an effective technique to solving review-level sentiment classification problem by using sentence-level polarity correction. Our polarity correction technique takes into account the consistency of the polarities (positive and…

Aspect-based sentiment analysis(ABSA) is a textual analysis methodology that defines the polarity of opinions on certain aspects related to specific targets. The majority of research on ABSA is in English, with a small amount of work…

Recent work has shown evidence that the knowledge acquired by multilingual BERT (mBERT) has two components: a language-specific and a language-neutral one. This paper analyses the relationship between them, in the context of fine-tuning on…

Assigning a positive or negative score to a word out of context (i.e. a word's prior polarity) is a challenging task for sentiment analysis. In the literature, various approaches based on SentiWordNet have been proposed. In this paper, we…

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…

Student opinions for a course are important to educators and administrators, regardless of the type of the course or the institution. Reading and manually analyzing open-ended feedback becomes infeasible for massive volumes of comments at…

Multitask learning often helps improve the performance of related tasks as these often have inter-dependence on each other and perform better when solved in a joint framework. In this paper, we present a deep multitask learning framework…

Although large pre-trained language models have achieved great success in many NLP tasks, it has been shown that they reflect human biases from their pre-training corpora. This bias may lead to undesirable outcomes when these models are…

Unsupervised pretraining models have been shown to facilitate a wide range of downstream NLP applications. These models, however, retain some of the limitations of traditional static word embeddings. In particular, they encode only the…

Pre-training by language modeling has become a popular and successful approach to NLP tasks, but we have yet to understand exactly what linguistic capacities these pre-training processes confer upon models. In this paper we introduce a…

Multimodal learning pipelines have benefited from the success of pretrained language models. However, this comes at the cost of increased model parameters. In this work, we propose Adapted Multimodal BERT (AMB), a BERT-based architecture…

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…

Transformer-based language models have recently achieved remarkable results in many natural language tasks. However, performance on leaderboards is generally achieved by leveraging massive amounts of training data, and rarely by encoding…

Artificial intelligence and machine learning have significantly bolstered the technological world. This paper explores the potential of transfer learning in natural language processing focusing mainly on sentiment analysis. The models…