相关论文: Finding patterns in Knowledge Attribution for Tran…

We describe an "interpretability illusion" that arises when analyzing the BERT model. Activations of individual neurons in the network may spuriously appear to encode a single, simple concept, when in fact they are encoding something far…

Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with…

Sentence embedding is an important research topic in natural language processing (NLP) since it can transfer knowledge to downstream tasks. Meanwhile, a contextualized word representation, called BERT, achieves the state-of-the-art…

The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question…

In parallel to their overwhelming success across NLP tasks, language ability of deep Transformer networks, pretrained via language modeling (LM) objectives has undergone extensive scrutiny. While probing revealed that these models encode a…

Transformer-based models are now predominant in NLP. They outperform approaches based on static models in many respects. This success has in turn prompted research that reveals a number of biases in the language models generated by…

Multilingual Alignment is an effective and representative paradigm to enhance LLMs' multilingual capabilities, which transfers the capabilities from the high-resource languages to the low-resource languages. Meanwhile, some research on…

In this paper, we investigate whether Large Language Models (LLMs) actively recall or retrieve their internal repositories of factual knowledge when faced with reasoning tasks. Through an analysis of LLMs' internal factual recall at each…

Interpretability researchers have attempted to understand MLP neurons of language models based on both the contexts in which they activate and their output weight vectors. They have paid little attention to a complementary aspect: the…

Pretrained language models have achieved a new state of the art on many NLP tasks, but there are still many open questions about how and why they work so well. We investigate the contextualization of words in BERT. We quantify the amount of…

Contextualized representations trained over large raw text data have given remarkable improvements for NLP tasks including question answering and reading comprehension. There have been works showing that syntactic, semantic and word sense…

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Language models are known to encode a great amount of factual knowledge through pretraining. However, such knowledge might be insufficient to cater to user requests, requiring the model to integrate external knowledge sources and adhere to…

Progress in natural language processing (NLP) models that estimate representations of word sequences has recently been leveraged to improve the understanding of language processing in the brain. However, these models have not been…

BERT, which stands for Bidirectional Encoder Representations from Transformers, is a recently introduced language representation model based upon the transfer learning paradigm. We extend its fine-tuning procedure to address one of its…

The inference of politically-charged information from text data is a popular research topic in Natural Language Processing (NLP) at both text- and author-level. In recent years, studies of this kind have been implemented with the aid of…

In this paper, we propose convolutional neural networks for learning an optimal representation of question and answer sentences. Their main aspect is the use of relational information given by the matches between words from the two members…

The main approaches to sentiment analysis are rule-based methods and ma-chine learning, in particular, deep neural network models with the Trans-former architecture, including BERT. The performance of neural network models in the tasks of…

A typical architecture for end-to-end entity linking systems consists of three steps: mention detection, candidate generation and entity disambiguation. In this study we investigate the following questions: (a) Can all those steps be…

The Bidirectional Encoder Representations from Transformers (BERT) model has achieved the state-of-the-art performance for many natural language processing (NLP) tasks. Yet, limited research has been contributed to studying its…