Related papers: Construction Identification and Disambiguation Usi…
We investigate the extent to which modern, neural language models are susceptible to structural priming, the phenomenon whereby the structure of a sentence makes the same structure more probable in a follow-up sentence. We explore how…
Transformer language models have shown remarkable ability in detecting when a word is anomalous in context, but likelihood scores offer no information about the cause of the anomaly. In this work, we use Gaussian models for density…
Pre-trained Language Models (PLMs) have shown to be consistently successful in a plethora of NLP tasks due to their ability to learn contextualized representations of words (Ethayarajh, 2019). BERT (Devlin et al., 2018), ELMo (Peters et…
Several studies have been carried out on revealing linguistic features captured by BERT. This is usually achieved by training a diagnostic classifier on the representations obtained from different layers of BERT. The subsequent…
Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social…
Natural language numbers are an example of compositional structures, where larger numbers are composed of operations on smaller numbers. Given that compositional reasoning is a key to natural language understanding, we propose novel…
A central quest of probing is to uncover how pre-trained models encode a linguistic property within their representations. An encoding, however, might be spurious-i.e., the model might not rely on it when making predictions. In this paper,…
Traditional hand-crafted linguistically-informed features have often been used for distinguishing between translated and original non-translated texts. By contrast, to date, neural architectures without manual feature engineering have been…
Pre-trained text encoders have rapidly advanced the state of the art on many NLP tasks. We focus on one such model, BERT, and aim to quantify where linguistic information is captured within the network. We find that the model represents the…
Heavily pre-trained transformer models such as BERT have recently shown to be remarkably powerful at language modelling by achieving impressive results on numerous downstream tasks. It has also been shown that they are able to implicitly…
We propose SentiBERT, a variant of BERT that effectively captures compositional sentiment semantics. The model incorporates contextualized representation with binary constituency parse tree to capture semantic composition. Comprehensive…
The rise of language models such as BERT allows for high-quality text paraphrasing. This is a problem to academic integrity, as it is difficult to differentiate between original and machine-generated content. We propose a benchmark…
In creating sentence embeddings for Natural Language Inference (NLI) tasks, using transformer-based models like BERT leads to high accuracy, but require hundreds of millions of parameters. These models take in sentences as a sequence of…
Cross-lingual word sense disambiguation (WSD) tackles the challenge of disambiguating ambiguous words across languages given context. The pre-trained BERT embedding model has been proven to be effective in extracting contextual information…
Peeking into the inner workings of BERT has shown that its layers resemble the classical NLP pipeline, with progressively more complex tasks being concentrated in later layers. To investigate to what extent these results also hold for a…
Construction Grammar (CxG) is a paradigm from cognitive linguistics emphasising the connection between syntax and semantics. Rather than rules that operate on lexical items, it posits constructions as the central building blocks of…
Advances in Natural Language Processing (NLP) have revolutionized the way researchers and practitioners address crucial societal problems. Large language models are now the standard to develop state-of-the-art solutions for text detection…
Deep learning approaches are superior in NLP due to their ability to extract informative features and patterns from languages. The two most successful neural architectures are LSTM and transformers, used in large pretrained language models…
This study investigates the internal representations of verb-particle combinations, called multi-word verbs, within transformer-based large language models (LLMs), specifically examining how these models capture lexical and syntactic…
Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLP tasks with appropriate fine-tuning. However,…