相关论文: BERT-kNN: Adding a kNN Search Component to Pretrai…

Neural language representation models such as BERT, pre-trained on large-scale unstructured corpora lack explicit grounding to real-world commonsense knowledge and are often unable to remember facts required for reasoning and inference.…

Previous knowledge graph embedding approaches usually map entities to representations and utilize score functions to predict the target entities, yet they typically struggle to reason rare or emerging unseen entities. In this paper, we…

Recent works have proven the effectiveness of k-nearest-neighbor machine translation(a.k.a kNN-MT) approaches to produce remarkable improvement in cross-domain translations. However, these models suffer from heavy retrieve overhead on the…

Recently, transformer-based language models such as BERT have shown tremendous performance improvement for a range of natural language processing tasks. However, these language models usually are computation expensive and memory intensive…

Existing literature on Question Answering (QA) mostly focuses on algorithmic novelty, data augmentation, or increasingly large pre-trained language models like XLNet and RoBERTa. Additionally, a lot of systems on the QA leaderboards do not…

The use of BERT, one of the most popular language models, has led to improvements in many Natural Language Processing (NLP) tasks. One such task is Named Entity Recognition (NER) i.e. automatic identification of named entities such as…

Contextualized entity representations learned by state-of-the-art transformer-based language models (TLMs) like BERT, GPT, T5, etc., leverage the attention mechanism to learn the data context from training data corpus. However, these models…

Semi-parametric models, which augment generation with retrieval, have led to impressive results in language modeling and machine translation, due to their ability to retrieve fine-grained information from a datastore of examples. One of the…

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…

Knowledge enhanced pre-trained language models (K-PLMs) are shown to be effective for many public tasks in the literature but few of them have been successfully applied in practice. To address this problem, we propose K-AID, a systematic…

Retrieval-based dialogue systems select the best response from many candidates. Although many state-of-the-art models have shown promising performance in dialogue response selection tasks, there is still quite a gap between R@1 and R@10…

Deep Neural Networks require large amounts of labeled data for their training. Collecting this data at scale inevitably causes label noise.Hence,the need to develop learning algorithms that are robust to label noise. In recent years, k…

Recent years have witnessed a substantial increase in the use of deep learning to solve various natural language processing (NLP) problems. Early deep learning models were constrained by their sequential or unidirectional nature, such that…

Recent advances in Named Entity Recognition (NER) show that document-level contexts can significantly improve model performance. In many application scenarios, however, such contexts are not available. In this paper, we propose to find…

The K-Nearest Neighbors (KNN) algorithm is widely used for classification and regression; however, it suffers from limitations, including the equal treatment of all samples. We propose Information-Modified KNN (IM-KNN), a novel approach…

Nearest Neighbor Machine Translation ($k$NN-MT) has achieved great success in domain adaptation tasks by integrating pre-trained Neural Machine Translation (NMT) models with domain-specific token-level retrieval. However, the reasons…

In the field of information retrieval, query expansion (QE) has long been used as a technique to deal with the fundamental issue of word mismatch between a user's query and the target information. In the context of the relationship between…

In recent years, Question Answering systems have become more popular and widely used by users. Despite the increasing popularity of these systems, the their performance is not even sufficient for textual data and requires further research.…

The emergence of structured databases for Question Answering (QA) systems has led to developing methods, in which the problem of learning the correct answer efficiently is based on a linking task between the constituents of the question and…

Currently, the most widespread neural network architecture for training language models is the so called BERT which led to improvements in various Natural Language Processing (NLP) tasks. In general, the larger the number of parameters in a…