Related papers: Answering Chinese Elementary School Social Study M…
Although large pre-trained language models have achieved great success in many NLP tasks, it has been shown that they reflect human biases from their pre-training corpora. This bias may lead to undesirable outcomes when these models are…
This paper presents new state-of-the-art models for three tasks, part-of-speech tagging, syntactic parsing, and semantic parsing, using the cutting-edge contextualized embedding framework known as BERT. For each task, we first replicate and…
In natural language processing, pre-trained language models have become essential infrastructures. However, these models often suffer from issues such as large size, long inference time, and challenging deployment. Moreover, most mainstream…
A BERT-based Neural Ranking Model (NRM) can be either a crossencoder or a bi-encoder. Between the two, bi-encoder is highly efficient because all the documents can be pre-processed before the actual query time. In this work, we show two…
The recently introduced BERT model exhibits strong performance on several language understanding benchmarks. In this paper, we describe a simple re-implementation of BERT for commonsense reasoning. We show that the attentions produced by…
The pre-trained BERT model achieves a remarkable state of the art across a wide range of tasks in natural language processing. For solving the gender bias in gendered pronoun resolution task, I propose a novel neural network model based on…
In multiple-choice exams, students select one answer from among typically four choices and can explain why they made that particular choice. Students are good at understanding natural language questions and based on their domain knowledge…
A sequence-to-sequence learning with neural networks has empirically proven to be an effective framework for Chinese Spelling Correction (CSC), which takes a sentence with some spelling errors as input and outputs the corrected one.…
We explore advanced fine-tuning techniques to boost BERT's performance in sentiment analysis, paraphrase detection, and semantic textual similarity. Our approach leverages SMART regularization to combat overfitting, improves hyperparameter…
The enormous growth of research publications has made it challenging for academic search engines to bring the most relevant papers against the given search query. Numerous solutions have been proposed over the years to improve the…
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…
With the rapid development of information technology, online platforms (e.g., news portals and social media) generate enormous web information every moment. Therefore, it is crucial to extract structured representations of events from…
Intelligent Tutoring Systems (ITS) enhance personalized learning by predicting student answers to provide immediate and customized instruction. However, recent research has primarily focused on the correctness of the answer rather than the…
Question-answering plays an important role in e-commerce as it allows potential customers to actively seek crucial information about products or services to help their purchase decision making. Inspired by the recent success of machine…
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…
Due to the ambiguity of homophones, Chinese Spell Checking (CSC) has widespread applications. Existing systems typically utilize BERT for text encoding. However, CSC requires the model to account for both phonetic and graphemic information.…
Recently, many studies have shown the efficiency of using Bidirectional Encoder Representations from Transformers (BERT) in various Natural Language Processing (NLP) tasks. Specifically, English spelling correction task that uses…
Article prediction is a task that has long defied accurate linguistic description. As such, this task is ideally suited to evaluate models on their ability to emulate native-speaker intuition. To this end, we compare the performance of…
We present a Chinese judicial reading comprehension (CJRC) dataset which contains approximately 10K documents and almost 50K questions with answers. The documents come from judgment documents and the questions are annotated by law experts.…
We present a systematic investigation of layer-wise BERT activations for general-purpose text representations to understand what linguistic information they capture and how transferable they are across different tasks. Sentence-level…