Related papers: Probing for targeted syntactic knowledge through g…

Language model pre-training has shown promising results in various downstream tasks. In this context, we introduce a cross-modal pre-trained language model, called Speech-Text BERT (ST-BERT), to tackle end-to-end spoken language…

In this paper, we extend previous self-supervised approaches for language identification by experimenting with Conformer based architecture in a multilingual pre-training paradigm. We find that pre-trained speech models optimally encode…

Emotion detection can provide us with a window into understanding human behavior. Due to the complex dynamics of human emotions, however, constructing annotated datasets to train automated models can be expensive. Thus, we explore the…

Deep generative models have been enjoying success in modeling continuous data. However it remains challenging to capture the representations for discrete structures with formal grammars and semantics, e.g., computer programs and molecular…

Syntactic information contains structures and rules about how text sentences are arranged. Incorporating syntax into text modeling methods can potentially benefit both representation learning and generation. Variational autoencoders (VAEs)…

Language models (LMs) are capable of acquiring elements of human-like syntactic knowledge. Targeted syntactic evaluation tests have been employed to measure how well they form generalizations about syntactic phenomena in high-resource…

In targeted adversarial attacks on vision models, the selection of the target label is a critical yet often overlooked determinant of attack success. This target label corresponds to the class that the attacker aims to force the model to…

The same multi-word expressions may have different meanings in different sentences. They can be mainly divided into two categories, which are literal meaning and idiomatic meaning. Non-contextual-based methods perform poorly on this…

The dominant probing approaches rely on the zero-shot performance of image-text matching tasks to gain a finer-grained understanding of the representations learned by recent multimodal image-language transformer models. The evaluation is…

Morphological and syntactic changes in word usage (as captured, e.g., by grammatical profiles) have been shown to be good predictors of a word's meaning change. In this work, we explore whether large pre-trained contextualised language…

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…

In the realm of Sign Language Translation (SLT), reliance on costly gloss-annotated datasets has posed a significant barrier. Recent advancements in gloss-free SLT methods have shown promise, yet they often largely lag behind gloss-based…

Recently, many pre-trained language models for source code have been proposed to model the context of code and serve as a basis for downstream code intelligence tasks such as code completion, code search, and code summarization. These…

The goal of this paper is to learn more about how idiomatic information is structurally encoded in embeddings, using a structural probing method. We repurpose an existing English verbal multi-word expression (MWE) dataset to suit the…

Structured language models for speech recognition have been shown to remedy the weaknesses of n-gram models. All current structured language models are, however, limited in that they do not take into account dependencies between…

Knowledge-enhanced pre-trained models for language representation have been shown to be more effective in knowledge base construction tasks (i.e.,~relation extraction) than language models such as BERT. These knowledge-enhanced language…

Although transformer-based Neural Language Models demonstrate impressive performance on a variety of tasks, their generalization abilities are not well understood. They have been shown to perform strongly on subject-verb number agreement in…

This paper makes a simple increment to state-of-the-art in sarcasm detection research. Existing approaches are unable to capture subtle forms of context incongruity which lies at the heart of sarcasm. We explore if prior work can be…

This study is focused on understanding and quantifying the change in phoneme and prosody information encoded in the Self-Supervised Learning (SSL) model, brought by an accent identification (AID) fine-tuning task. This problem is addressed…

Targeted syntactic evaluations of language models ask whether models show stable preferences for syntactically acceptable content over minimal-pair unacceptable inputs. Most targeted syntactic evaluation datasets ask models to make these…