Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSummarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension
تلخيص - ثم الإجابة: توليد تفسيرات موجزة لفهم القراءة متعددة القفز
709
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
كيف يمكننا أن نولد تفسيرات موجزة لفهم القراءة متعددة القفز (RC)؟ يمكن اعتبار الاستراتيجيات الحالية لتحديد الجمل الداعمة كأخصات تركز على الأسئلة الاستخراجية لنص المدخلات. ومع ذلك، فإن هذه التفسيرات الاستخراجية ليست بالضرورة موجزة، وليس كافية على الأقل للإجابة على سؤال. بدلا من ذلك، ندعو إلى نهج إغراق، حيث نقترح إنشاء ملخص ركز على أسئلة غير مركزة لفقرات الإدخال ثم إطعامها لنظام RC. بالنظر إلى كمية محدودة من التفسيرات الموضحة البشرية المشروح البشرية، فإننا نربع الشرح الإفجي بطريقة شبه إشراف، حيث نبدأ من النموذج الخاضع للإشراف، ثم تدريب عليه من خلال التجربة والخطأ تعظيم وظيفة المكافآت التي تمت ترقيتها على الحجز. توضح تجاربنا أن المفسر المفسد المقترح يمكن أن يولد توضيحات أكثر إحكاما من الشرح الاستخراجي مع إشراف محدود (مثيلات 2K فقط) مع الحفاظ على الاكتفاء.
How can we generate concise explanations for multi-hop Reading Comprehension (RC)? The current strategies of identifying supporting sentences can be seen as an extractive question-focused summarization of the input text. However, these extractive explanations are not necessarily concise i.e. not minimally sufficient for answering a question. Instead, we advocate for an abstractive approach, where we propose to generate a question-focused, abstractive summary of input paragraphs and then feed it to an RC system. Given a limited amount of human-annotated abstractive explanations, we train the abstractive explainer in a semi-supervised manner, where we start from the supervised model and then train it further through trial and error maximizing a conciseness-promoted reward function. Our experiments demonstrate that the proposed abstractive explainer can generate more compact explanations than an extractive explainer with limited supervision (only 2k instances) while maintaining sufficiency.
References used
https://aclanthology.org/
rate research
Read More
We propose a simple method to generate multilingual question and answer pairs on a large scale through the use of a single generative model. These synthetic samples can be used to improve the zero-shot performance of multilingual QA models on target
languages. Our proposed multi-task training of the generative model only requires labeled training samples in English, thus removing the need for such samples in the target languages, making it applicable to far more languages than those with labeled data. Human evaluations indicate the majority of such samples are grammatically correct and sensible. Experimental results show our proposed approach can achieve large gains on the XQuAD dataset, reducing the gap between zero-shot and supervised performance of smaller QA models on various languages.
In education, quiz questions have become an important tool for assessing the knowledge of students. Yet, manually preparing such questions is a tedious task, and thus automatic question generation has been proposed as a possible alternative. So far,
the vast majority of research has focused on generating the question text, relying on question answering datasets with readily picked answers, and the problem of how to come up with answer candidates in the first place has been largely ignored. Here, we aim to bridge this gap. In particular, we propose a model that can generate a specified number of answer candidates for a given passage of text, which can then be used by instructors to write questions manually or can be passed as an input to automatic answer-aware question generators. Our experiments show that our proposed answer candidate generation model outperforms several baselines.
Web search is an essential way for humans to obtain information, but it's still a great challenge for machines to understand the contents of web pages. In this paper, we introduce the task of web-based structural reading comprehension. Given a web pa
ge and a question about it, the task is to find an answer from the web page. This task requires a system not only to understand the semantics of texts but also the structure of the web page. Moreover, we proposed WebSRC, a novel Web-based Structural Reading Comprehension dataset. WebSRC consists of 400K question-answer pairs, which are collected from 6.4K web pages with corresponding HTML source code, screenshots, and metadata. Each question in WebSRC requires a certain structural understanding of a web page to answer, and the answer is either a text span on the web page or yes/no. We evaluate various strong baselines on our dataset to show the difficulty of our task. We also investigate the usefulness of structural information and visual features. Our dataset and baselines have been publicly available.
We develop a system for the FEVEROUS fact extraction and verification task that ranks an initial set of potential evidence and then pursues missing evidence in subsequent hops by trying to generate it, with a next hop prediction module'' whose output
is matched against page elements in a predicted article. Seeking evidence with the next hop prediction module continues to improve FEVEROUS score for up to seven hops. Label classification is trained on possibly incomplete extracted evidence chains, utilizing hints that facilitate numerical comparison. The system achieves .281 FEVEROUS score and .658 label accuracy on the development set, and finishes in second place with .259 FEVEROUS score and .576 label accuracy on the test set.
In this paper, we propose a simple few-shot domain adaptation paradigm for reading comprehension. We first identify the lottery subnetwork structure within the Transformer-based source domain model via gradual magnitude pruning. Then, we only fine-tu
ne the lottery subnetwork, a small fraction of the whole parameters, on the annotated target domain data for adaptation. To obtain more adaptable subnetworks, we introduce self-attention attribution to weigh parameters, beyond simply pruning the smallest magnitude parameters, which can be seen as combining structured pruning and unstructured magnitude pruning softly. Experimental results show that our method outperforms the full model fine-tuning adaptation on four out of five domains when only a small amount of annotated data available for adaptation. Moreover, introducing self-attention attribution reserves more parameters for important attention heads in the lottery subnetwork and improves the target domain model performance. Our further analyses reveal that, besides exploiting fewer parameters, the choice of subnetworks is critical to the effectiveness.
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
