Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userRelying on Discourse Analysis to Answer Complex Questions by Neural Machine Reading Comprehension
الاعتماد على تحليل الخطاب للإجابة على أسئلة معقدة من خلال الفهم القراءة الآلة العصبية
213
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
آلة قراءة الآلة (MRC) هي واحدة من أكثر المهام تحديا في مجال معالجة اللغة الطبيعية. تم تحقيق نتائج أحدث حديثة ل MRC بنماذج اللغة المدربة مسبقا، مثل بيرت وتعديلاتها. على الرغم من ارتفاع الأداء لهذه النماذج، إلا أنهم لا يزالون يعانون من عدم القدرة على استرداد الإجابات الصحيحة من الممرات التفصيلية الطويلة. في هذا العمل، نقدم مخططا جديدا لإدماج هيكل الخطاب للنص في شبكة انتباهي، وبالتالي إثراء التضمين الذي تم الحصول عليه من ترميز بيرت القياسي مع المعرفة اللغوية الإضافية. نحقق أيضا في تأثير أنواع مختلفة من المعلومات اللغوية عن قدرة النموذج على الإجابة على الأسئلة المعقدة التي تتطلب فهم عميق للنص بأكمله. أظهرت التجارب التي تم إجراؤها على مرجع الفريق وأكثر تعقيدا عن مجموعات بيانات الأجابة أن المعزز اللغوي يعزز أداء نموذج بيرت القياسي بشكل كبير.
Machine reading comprehension (MRC) is one of the most challenging tasks in natural language processing domain. Recent state-of-the-art results for MRC have been achieved with the pre-trained language models, such as BERT and its modifications. Despite the high performance of these models, they still suffer from the inability to retrieve correct answers from the detailed and lengthy passages. In this work, we introduce a novel scheme for incorporating the discourse structure of the text into a self-attention network, and, thus, enrich the embedding obtained from the standard BERT encoder with the additional linguistic knowledge. We also investigate the influence of different types of linguistic information on the model's ability to answer complex questions that require deep understanding of the whole text. Experiments performed on the SQuAD benchmark and more complex question answering datasets have shown that linguistic enhancing boosts the performance of the standard BERT model significantly.
References used
https://aclanthology.org/
rate research
Read More
Adversarial training (AT) as a regularization method has proved its effectiveness on various tasks. Though there are successful applications of AT on some NLP tasks, the distinguishing characteristics of NLP tasks have not been exploited. In this pap
er, we aim to apply AT on machine reading comprehension (MRC) tasks. Furthermore, we adapt AT for MRC tasks by proposing a novel adversarial training method called PQAT that perturbs the embedding matrix instead of word vectors. To differentiate the roles of passages and questions, PQAT uses additional virtual P/Q-embedding matrices to gather the global perturbations of words from passages and questions separately. We test the method on a wide range of MRC tasks, including span-based extractive RC and multiple-choice RC. The results show that adversarial training is effective universally, and PQAT further improves the performance.
Machine reading comprehension is a challenging task especially for querying documents with deep and interconnected contexts. Transformer-based methods have shown advanced performances on this task; however, most of them still treat documents as a fla
t sequence of tokens. This work proposes a new Transformer-based method that reads a document as tree slices. It contains two modules for identifying more relevant text passage and the best answer span respectively, which are not only jointly trained but also jointly consulted at inference time. Our evaluation results show that our proposed method outperforms several competitive baseline approaches on two datasets from varied domains.
Machine Reading Comprehension (MRC), which requires a machine to answer questions given the relevant documents, is an important way to test machines' ability to understand human language. Multiple-choice MRC is one of the most studied tasks in MRC du
e to the convenience of evaluation and the flexibility of answer format. Post-hoc interpretation aims to explain a trained model and reveal how the model arrives at the prediction. One of the most important interpretation forms is to attribute model decisions to input features. Based on post-hoc interpretation methods, we assess attributions of paragraphs in multiple-choice MRC and improve the model by punishing the illogical attributions. Our method can improve model performance without any external information and model structure change. Furthermore, we also analyze how and why such a self-training method works.
The pivot for the unified Aspect-based Sentiment Analysis (ABSA) is to couple aspect terms with their corresponding opinion terms, which might further derive easier sentiment predictions. In this paper, we investigate the unified ABSA task from the p
erspective of Machine Reading Comprehension (MRC) by observing that the aspect and the opinion terms can serve as the query and answer in MRC interchangeably. We propose a new paradigm named Role Flipped Machine Reading Comprehension (RF-MRC) to resolve. At its heart, the predicted results of either the Aspect Term Extraction (ATE) or the Opinion Terms Extraction (OTE) are regarded as the queries, respectively, and the matched opinion or aspect terms are considered as answers. The queries and answers can be flipped for multi-hop detection. Finally, every matched aspect-opinion pair is predicted by the sentiment classifier. RF-MRC can solve the ABSA task without any additional data annotation or transformation. Experiments on three widely used benchmarks and a challenging dataset demonstrate the superiority of the proposed framework.
Previous work indicates that discourse information benefits summarization. In this paper, we explore whether this synergy between discourse and summarization is bidirectional, by inferring document-level discourse trees from pre-trained neural summar
izers. In particular, we generate unlabeled RST-style discourse trees from the self-attention matrices of the transformer model. Experiments across models and datasets reveal that the summarizer learns both, dependency- and constituency-style discourse information, which is typically encoded in a single head, covering long- and short-distance discourse dependencies. Overall, the experimental results suggest that the learned discourse information is general and transferable inter-domain.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
