اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدUndersensitivity in Neural Reading Comprehension
140
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Current reading comprehension models generalise well to in-distribution test sets, yet perform poorly on adversarially selected inputs. Most prior work on adversarial inputs studies oversensitivity: semantically invariant text perturbations that cause a models prediction to change when it should not. In this work we focus on the complementary problem: excessive prediction undersensitivity, where input text is meaningfully changed but the models prediction does not, even though it should. We formulate a noisy adversarial attack which searches among semantic variations of the question for which a model erroneously predicts the same answer, and with even higher probability. Despite comprising unanswerable questions, both SQuAD2.0 and NewsQA models are vulnerable to this attack. This indicates that although accurate, models tend to rely on spurious patterns and do not fully consider the information specified in a question. We experiment with data augmentation and adversarial training as defences, and find that both substantially decrease vulnerability to attacks on held out data, as well as held out attack spaces. Addressing undersensitivity also improves results on AddSent and AddOneSent, and models furthermore generalise better when facing train/evaluation distribution mismatch: they are less prone to overly rely on predictive cues present only in the training set, and outperform a conventional model by as much as 10.9% F1.
قيم البحث
اقرأ أيضاً
Reading comprehension is an important ability of human intelligence. Literacy and numeracy are two most essential foundation for people to succeed at study, at work and in life. Reading comprehension ability is a core component of literacy. In most o
f the education systems, developing reading comprehension ability is compulsory in the curriculum from year one to year 12. It is an indispensable ability in the dissemination of knowledge. With the emerging artificial intelligence, computers start to be able to read and understand like people in some context. They can even read better than human beings for some tasks, but have little clue in other tasks. It will be very beneficial if we can identify the levels of machine comprehension ability, which will direct us on the further improvement. Turing test is a well-known test of the difference between computer intelligence and human intelligence. In order to be able to compare the difference between people reading and machines reading, we proposed a test called (reading) Comprehension Ability Test (CAT).CAT is similar to Turing test, passing of which means we cannot differentiate people from algorithms in term of their comprehension ability. CAT has multiple levels showing the different abilities in reading comprehension, from identifying basic facts, performing inference, to understanding the intent and sentiment.
Standard accuracy metrics indicate that reading comprehension systems are making rapid progress, but the extent to which these systems truly understand language remains unclear. To reward systems with real language understanding abilities, we propose
an adversarial evaluation scheme for the Stanford Question Answering Dataset (SQuAD). Our method tests whether systems can answer questions about paragraphs that contain adversarially inserted sentences, which are automatically generated to distract computer systems without changing the correct answer or misleading humans. In this adversarial setting, the accuracy of sixteen published models drops from an average of $75%$ F1 score to $36%$; when the adversary is allowed to add ungrammatical sequences of words, average accuracy on four models decreases further to $7%$. We hope our insights will motivate the development of new models that understand language more precisely.
We study automatic question generation for sentences from text passages in reading comprehension. We introduce an attention-based sequence learning model for the task and investigate the effect of encoding sentence- vs. paragraph-level information. I
n contrast to all previous work, our model does not rely on hand-crafted rules or a sophisticated NLP pipeline; it is instead trainable end-to-end via sequence-to-sequence learning. Automatic evaluation results show that our system significantly outperforms the state-of-the-art rule-based system. In human evaluations, questions generated by our system are also rated as being more natural (i.e., grammaticality, fluency) and as more difficult to answer (in terms of syntactic and lexical divergence from the original text and reasoning needed to answer).
In this paper, we study machine reading comprehension (MRC) on long texts, where a model takes as inputs a lengthy document and a question and then extracts a text span from the document as an answer. State-of-the-art models tend to use a pretrained
transformer model (e.g., BERT) to encode the joint contextual information of document and question. However, these transformer-based models can only take a fixed-length (e.g., 512) text as its input. To deal with even longer text inputs, previous approaches usually chunk them into equally-spaced segments and predict answers based on each segment independently without considering the information from other segments. As a result, they may form segments that fail to cover the correct answer span or retain insufficient contexts around it, which significantly degrades the performance. Moreover, they are less capable of answering questions that need cross-segment information. We propose to let a model learn to chunk in a more flexible way via reinforcement learning: a model can decide the next segment that it wants to process in either direction. We also employ recurrent mechanisms to enable information to flow across segments. Experiments on three MRC datasets -- CoQA, QuAC, and TriviaQA -- demonstrate the effectiveness of our proposed recurrent chunking mechanisms: we can obtain segments that are more likely to contain complete answers and at the same time provide sufficient contexts around the ground truth answers for better predictions.
Achieving human-level performance on some of Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, the internal mechanism of these artifacts still remains unclear,
placing an obstacle for further understanding these models. This paper focuses on conducting a series of analytical experiments to examine the relations between the multi-head self-attention and the final performance, trying to analyze the potential explainability in PLM-based MRC models. We perform quantitative analyses on SQuAD (English) and CMRC 2018 (Chinese), two span-extraction MRC datasets, on top of BERT, ALBERT, and ELECTRA in various aspects. We discover that {em passage-to-question} and {em passage understanding} attentions are the most important ones, showing strong correlations to the final performance than other parts. Through visualizations and case studies, we also observe several general findings on the attention maps, which could be helpful to understand how these models solve the questions.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
