Related papers: Gendered Pronoun Resolution using BERT and an extr…
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…
Users often assume that large language models (LLMs) share their cognitive alignment of context and intent, leading them to omit critical information in question-answering (QA) and produce ambiguous queries. Responses based on misaligned…
Gender bias exists in natural language datasets which neural language models tend to learn, resulting in biased text generation. In this research, we propose a debiasing approach based on the loss function modification. We introduce a new…
We present assertion based question answering (ABQA), an open domain question answering task that takes a question and a passage as inputs, and outputs a semi-structured assertion consisting of a subject, a predicate and a list of…
Medical Question Answering systems based on Retrieval Augmented Generation is promising for clinical decision support because they can integrate external knowledge, thus reducing inaccuracies inherent in standalone large language models…
Most Visual Question Answering (VQA) models suffer from the language prior problem, which is caused by inherent data biases. Specifically, VQA models tend to answer questions (e.g., what color is the banana?) based on the high-frequency…
In conversational question answering, users express their information needs through a series of utterances with incomplete context. Typical ConvQA methods rely on a single source (a knowledge base (KB), or a text corpus, or a set of…
This paper presents the first unsupervised approach to lexical semantic change that makes use of contextualised word representations. We propose a novel method that exploits the BERT neural language model to obtain representations of word…
Recent studies on open-domain question answering have achieved prominent performance improvement using pre-trained language models such as BERT. State-of-the-art approaches typically follow the "retrieve and read" pipeline and employ…
With the development of deep learning techniques and large scale datasets, the question answering (QA) systems have been quickly improved, providing more accurate and satisfying answers. However, current QA systems either focus on the…
We introduce VisoGender, a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas, where each image…
Datasets extracted from social networks and online forums are often prone to the pitfalls of natural language, namely the presence of unstructured and noisy data. In this work, we seek to enable the collection of high-quality…
Although syntactic information is beneficial for many NLP tasks, combining it with contextual information between words to solve the coreference resolution problem needs to be further explored. In this paper, we propose an end-to-end parser…
In this paper, we propose a novel method for a sentence-level answer-selection task that is a fundamental problem in natural language processing. First, we explore the effect of additional information by adopting a pretrained language model…
BERT-based text ranking models have dramatically advanced the state-of-the-art in ad-hoc retrieval, wherein most models tend to consider individual query-document pairs independently. In the mean time, the importance and usefulness to…
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…
Text is a vehicle to convey information that reflects the writer's linguistic style and communicative patterns. By studying these attributes, we can discover latent insights about the author and their underlying message. This article uses…
Noisy training data can significantly degrade the performance of language-model-based classifiers, particularly in non-topical classification tasks. In this study we designed a methodological framework to assess the impact of denoising.…
By virtue of being prevalently written in natural language (NL), requirements are prone to various defects, e.g., inconsistency and incompleteness. As such, requirements are frequently subject to quality assurance processes. These…
Disparate biases associated with datasets and trained classifiers in hateful and abusive content identification tasks have raised many concerns recently. Although the problem of biased datasets on abusive language detection has been…