paper-with-me

홈 › Papers

Meta Answering for Machine Reading

2019-11-11 · Benjamin Borschinger, Jordan Boyd-Graber, Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Michelle Chen Huebscher, Wojciech Gajewski, Yannic Kilcher, Rodrigo Nogueira, Lierni Sestorain Saralegu

We investigate a framework for machine reading, inspired by real world information-seeking problems, where a meta question answering system interacts with a black box environment. The environment encapsulates a competitive machine reader based on BERT, providing candidate answers to questions, and possibly some context. To validate the realism of our formulation, we ask humans to play the role of a meta-answerer. With just a small snippet of text around an answer, humans can outperform the machine reader, improving recall. Similarly, a simple machine meta-answerer outperforms the environment, improving both precision and recall on the Natural Questions dataset. The system relies on joint training of answer scoring and the selection of conditioning information.

📄 PDF Abstract BibTeX arXiv:1911.04156

Code (0)

등록된 구현이 없습니다.

Tasks

Natural QuestionsQuestion AnsweringReading Comprehension

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
Residual Connection 설명 없음
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering

2020-07-01 · ACL 2020 6 · Ming Yan, Hao Zhang, Di Jin, Joey Tianyi Zhou

Multiple-choice question answering (MCQA) is one of the most challenging tasks in machine reading comprehension since it requires more advanced reading comprehension skills such as logical reasoning, summarization, and a…

Domain AdaptationLogical ReasoningMachine Reading ComprehensionMeta-Learning+5

Training a Ranking Function for Open-Domain Question Answering

2018-04-12 · NAACL 2018 6 · Phu Mon Htut, Samuel R. Bowman, Kyunghyun Cho

In recent years, there have been amazing advances in deep learning methods for machine reading. In machine reading, the machine reader has to extract the answer from the given ground truth paragraph. Recently, the state-…

Information RetrievalOpen-Domain Question AnsweringQuestion AnsweringReading Comprehension+3

Bridging Information-Seeking Human Gaze and Machine Reading Comprehension

2020-09-30 · CONLL 2020 · Jonathan Malmaud, Roger Levy, Yevgeni Berzak

In this work, we analyze how human gaze during reading comprehension is conditioned on the given reading comprehension question, and whether this signal can be beneficial for machine reading comprehension. To this end, w…

Machine Reading ComprehensionMultiple-choiceQuestion AnsweringReading Comprehension

Medical Knowledge Graph QA for Drug-Drug Interaction Prediction based on Multi-hop Machine Reading Comprehension

2022-12-19 · Peng Gao, Feng Gao, Jian-Cheng Ni, Yu Wang 외

Drug-drug interaction prediction is a crucial issue in molecular biology. Traditional methods of observing drug-drug interactions through medical experiments require significant resources and labor. This paper presents a…

Entity EmbeddingsGraph Neural NetworkGraph Question AnsweringMachine Reading Comprehension+2

Proceedings of the Workshop on Machine Reading for Question Answering

2018-07-01 · WS 2018 7 ·
Question AnsweringReading Comprehension