Cooperative Learning of Zero-Shot Machine Reading Comprehension
- URL: http://arxiv.org/abs/2103.07449v1
- Date: Fri, 12 Mar 2021 18:22:28 GMT
- Title: Cooperative Learning of Zero-Shot Machine Reading Comprehension
- Authors: Hongyin Luo, Seunghak Yu, James Glass
- Abstract summary: We propose a cooperative, self-play learning model for question generation and answering.
We can train question generation and answering models on any textual corpora without annotation.
Our model outperforms the state-of-the-art pretrained language models on standard question answering benchmarks.
- Score: 9.868221447090855
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Pretrained language models have significantly improved the performance of
down-stream tasks, for example extractive question answering, by providing
high-quality contextualized word embeddings. However, learning question
answering models still need large-scale data annotation in specific domains. In
this work, we propose a cooperative, self-play learning model for question
generation and answering. We implemented a masked answer entity extraction task
with an interactive learning environment, containing a question generator and a
question extractor. Given a passage with a mask, a question generator asks a
question about the masked entity, meanwhile the extractor is trained to extract
the masked entity with the generated question and raw texts. With this
strategy, we can train question generation and answering models on any textual
corpora without annotation. To further improve the performances of the question
answering model, we propose a reinforcement learning method that rewards
generated questions that improves the extraction learning. Experimental results
showed that our model outperforms the state-of-the-art pretrained language
models on standard question answering benchmarks, and reaches the
state-of-the-art performance under the zero-shot learning setting.
Related papers
- Crafting Interpretable Embeddings by Asking LLMs Questions [89.49960984640363]
Large language models (LLMs) have rapidly improved text embeddings for a growing array of natural-language processing tasks.
We introduce question-answering embeddings (QA-Emb), embeddings where each feature represents an answer to a yes/no question asked to an LLM.
We use QA-Emb to flexibly generate interpretable models for predicting fMRI voxel responses to language stimuli.
arXiv Detail & Related papers (2024-05-26T22:30:29Z) - SEMQA: Semi-Extractive Multi-Source Question Answering [94.04430035121136]
We introduce a new QA task for answering multi-answer questions by summarizing multiple diverse sources in a semi-extractive fashion.
We create the first dataset of this kind, QuoteSum, with human-written semi-extractive answers to natural and generated questions.
arXiv Detail & Related papers (2023-11-08T18:46:32Z) - Adapting Pre-trained Generative Models for Extractive Question Answering [4.993041970406846]
We introduce a novel approach that uses the power of pre-trained generative models to address extractive QA tasks.
We demonstrate the superior performance of our proposed approach compared to existing state-of-the-art models.
arXiv Detail & Related papers (2023-11-06T09:01:02Z) - Weakly Supervised Visual Question Answer Generation [2.7605547688813172]
We present a weakly supervised method that synthetically generates question-answer pairs procedurally from visual information and captions.
We perform an exhaustive experimental analysis on VQA dataset and see that our model significantly outperforms SOTA methods on BLEU scores.
arXiv Detail & Related papers (2023-06-11T08:46:42Z) - Momentum Contrastive Pre-training for Question Answering [54.57078061878619]
MCROSS introduces a momentum contrastive learning framework to align the answer probability between cloze-like and natural query-passage sample pairs.
Our method achieves noticeable improvement compared with all baselines in both supervised and zero-shot scenarios.
arXiv Detail & Related papers (2022-12-12T08:28:22Z) - Automatic Short Math Answer Grading via In-context Meta-learning [2.0263791972068628]
We study the problem of automatic short answer grading for students' responses to math questions.
We use MathBERT, a variant of the popular language model BERT adapted to mathematical content, as our base model.
Second, we use an in-context learning approach that provides scoring examples as input to the language model.
arXiv Detail & Related papers (2022-05-30T16:26:02Z) - Asking Questions Like Educational Experts: Automatically Generating
Question-Answer Pairs on Real-World Examination Data [10.353009081072992]
This paper addresses the question-answer pair generation task on the real-world examination data, and proposes a new unified framework on RACE.
We propose a multi-agent communication model to generate and optimize the question and keyphrases iteratively, and then apply the generated question and keyphrases to guide the generation of answers.
Experimental results show that our model makes great breakthroughs in the question-answer pair generation task.
arXiv Detail & Related papers (2021-09-11T04:10:57Z) - Learning to Ask Conversational Questions by Optimizing Levenshtein
Distance [83.53855889592734]
We introduce a Reinforcement Iterative Sequence Editing (RISE) framework that optimize the minimum Levenshtein distance (MLD) through explicit editing actions.
RISE is able to pay attention to tokens that are related to conversational characteristics.
Experimental results on two benchmark datasets show that RISE significantly outperforms state-of-the-art methods.
arXiv Detail & Related papers (2021-06-30T08:44:19Z) - Understanding Unnatural Questions Improves Reasoning over Text [54.235828149899625]
Complex question answering (CQA) over raw text is a challenging task.
Learning an effective CQA model requires large amounts of human-annotated data.
We address the challenge of learning a high-quality programmer (parser) by projecting natural human-generated questions into unnatural machine-generated questions.
arXiv Detail & Related papers (2020-10-19T10:22:16Z) - Visual Question Answering with Prior Class Semantics [50.845003775809836]
We show how to exploit additional information pertaining to the semantics of candidate answers.
We extend the answer prediction process with a regression objective in a semantic space.
Our method brings improvements in consistency and accuracy over a range of question types.
arXiv Detail & Related papers (2020-05-04T02:46:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.