A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction

• URL: http://arxiv.org/abs/2005.05189v2
• Date: Fri, 19 Jun 2020 04:02:57 GMT
• Title: A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction
• Authors: Yilin Niu, Fangkai Jiao, Mantong Zhou, Ting Yao, Jingfang Xu, Minlie Huang
• Abstract summary: We present a Self-Training method (STM) to train machine reading comprehension models. At each iteration, a base MRC model is trained with golden answers and noisy evidence labels. The trained model will predict pseudo evidence labels as extra supervision in the next iteration.
• Score: 89.88061141170512
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural models have achieved great success on machine reading comprehension (MRC), many of which typically consist of two components: an evidence extractor and an answer predictor. The former seeks the most relevant information from a reference text, while the latter is to locate or generate answers from the extracted evidence. Despite the importance of evidence labels for training the evidence extractor, they are not cheaply accessible, particularly in many non-extractive MRC tasks such as YES/NO question answering and multi-choice MRC. To address this problem, we present a Self-Training method (STM), which supervises the evidence extractor with auto-generated evidence labels in an iterative process. At each iteration, a base MRC model is trained with golden answers and noisy evidence labels. The trained model will predict pseudo evidence labels as extra supervision in the next iteration. We evaluate STM on seven datasets over three MRC tasks. Experimental results demonstrate the improvement on existing MRC models, and we also analyze how and why such a self-training method works in MRC. The source code can be obtained from https://github.com/SparkJiao/Self-Training-MRC

Related papers

• Multi-grained Evidence Inference for Multi-choice Reading Comprehension [62.0773160298008]
  Multi-choice Machine Reading (MRC) is a major and challenging task for machines to answer questions according to provided options. We propose a novel general-purpose model enhancement which integrates multi-grained evidence comprehensively, named Multi-grained evidence inferencer (Mugen) Mugen extracts three different granularities of evidence, and integrates evidence with the original passages, achieving significant and consistent performance improvement on four multi-choice MRC benchmarks.
  arXiv  Detail & Related papers  (2023-10-27T11:36:18Z)
• From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader [130.45769668885487]
  Pre-trained Machine Reader (PMR) is a novel method for retrofitting masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data. To build the proposed PMR, we constructed a large volume of general-purpose and high-quality MRC-style training data. PMR has the potential to serve as a unified model for tackling various extraction and classification tasks in the MRC formulation.
  arXiv  Detail & Related papers  (2022-12-09T10:21:56Z)
• Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation [19.551623461082617]
  Open-domain question answering answers a question based on evidence retrieved from a large corpus. This paper investigates whether models can learn to find evidence from a large corpus, with only distant supervision from answer labels for model training. We introduce a novel approach (DistDR) that iteratively improves over a weak retriever by alternately finding evidence from the up-to-date model and encouraging the model to learn the most likely evidence.
  arXiv  Detail & Related papers  (2021-10-10T20:01:27Z)
• Why Machine Reading Comprehension Models Learn Shortcuts? [56.629192589376046]
  We argue that larger proportion of shortcut questions in training data make models rely on shortcut tricks excessively. A thorough empirical analysis shows that MRC models tend to learn shortcut questions earlier than challenging questions.
  arXiv  Detail & Related papers  (2021-06-02T08:43:12Z)
• REPT: Bridging Language Models and Machine Reading Comprehensionvia Retrieval-Based Pre-training [45.21249008835556]
  We present REPT, a REtrieval-based Pre-Training approach to bridge the gap between general PLMs and MRC. In particular, we introduce two self-supervised tasks to strengthen evidence extraction during pre-training. Our approach is able to enhance the capacity of evidence extraction without explicit supervision.
  arXiv  Detail & Related papers  (2021-05-10T08:54:46Z)
• ExpMRC: Explainability Evaluation for Machine Reading Comprehension [42.483940360860096]
  We propose a new benchmark called ExpMRC for evaluating the explainability of the Machine Reading systems. We use state-of-the-art pre-trained language models to build baseline systems and adopt various unsupervised approaches to extract evidence without a human-annotated training set.
  arXiv  Detail & Related papers  (2021-05-10T06:00:20Z)
• SRQA: Synthetic Reader for Factoid Question Answering [21.28441702154528]
  We introduce a new model called SRQA, which means Synthetic Reader for Factoid Question Answering. This model enhances the question answering system in the multi-document scenario from three aspects. We perform SRQA on the WebQA dataset, and experiments show that our model outperforms the state-of-the-art models.
  arXiv  Detail & Related papers  (2020-09-02T13:16:24Z)
• Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension [59.80926970481975]
  We study machine reading comprehension (MRC) on long texts. A model takes as inputs a lengthy document and a question and then extracts a text span from the document as an answer. We propose to let a model learn to chunk in a more flexible way via reinforcement learning.
  arXiv  Detail & Related papers  (2020-05-16T18:08:58Z)
• Retrospective Reader for Machine Reading Comprehension [90.6069071495214]
  Machine reading comprehension (MRC) is an AI challenge that requires machine to determine the correct answers to questions based on a given passage. When unanswerable questions are involved in the MRC task, an essential verification module called verifier is especially required in addition to the encoder. This paper devotes itself to exploring better verifier design for the MRC task with unanswerable questions.
  arXiv  Detail & Related papers  (2020-01-27T11:14:34Z)

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.