852 Hits in 3.4 sec

On Committee Representations of Adversarial Learning Models for Question-Answer Ranking

Sparsh Gupta, Vitor Carvalho
2019 Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)  
We start by empirically probing the effects of adversarial training over multiple QA ranking algorithms, including the state-of-the-art Multihop Attention Network model.  ...  In this paper we investigate how representing adversarial training models as committees can be used to effectively improve the performance of Question-Answer (QA) Ranking.  ...  For instance, Multihop Attention Network often displayed worse results with adversarial training.  ... 
doi:10.18653/v1/w19-4325 dblp:conf/rep4nlp/GuptaC19 fatcat:c43wc7ezlfdbfgjaocoulor33q

Dual-Channel Reasoning Model for Complex Question Answering

Xing Cao, Yun Liu, Bo Hu, Yu Zhang, Xuzhen Zhu
2021 Complexity  
Multihop question answering has attracted extensive studies in recent years because of the emergence of human annotated datasets and associated leaderboards.  ...  The two reasoning channels can simply use the same reasoning structure without additional network designs.  ...  Main Results. e performance of multihop QA on HotpotQA is evaluated by using the exact match (EM) and F1 as two evaluation metrics for answer prediction and evidence sentences extraction.  ... 
doi:10.1155/2021/7367181 fatcat:pk33ybw7ufcarp4dww355mzyuq

Application of Knowledge Map Based on BiLSTM-CRF Algorithm Model in Ideological and Political Education Question Answering System

Wei Zhao, Juan Liu, Chia-Huei Wu
2022 Mobile Information Systems  
Through the answer matching network, the similarity score is marked for the answers in the triplet set, and the threshold selection strategy is used to select the answers that meet the requirements.  ...  For the knowledge base question answering method with weak-dependent information, this paper combines BERT (Bidirectional Encoder Representation from Transformers) and BiLSTM-CRF network to extract the  ...  The answer matching network was used to label the similarity score for each answer. Finally, the alternative answers are filtered through threshold selection and the results are output.  ... 
doi:10.1155/2022/4139323 fatcat:yuagi7kpy5b45i4rrapyyme54i

Toward community answer selection by jointly static and dynamic user expertise modeling

Yuchao Liu, Meng Liu, Jianhua Yin
2021 APSIPA Transactions on Signal and Information Processing  
Answer selection, ranking high-quality answers first, is a significant problem for the community question answering sites.  ...  Existing approaches usually consider it as a text matching task, and then calculate the quality of answers via their semantic relevance to the given question.  ...  answer matching, in The Annual Meeting of the Association for Computational Linguistics, 2016, 464-473. 7 Khanh Tran, N.; Niedereée, C.: Multihop attention networks for question answer matching, in The  ... 
doi:10.1017/atsip.2020.28 fatcat:vb4tgretnbgmvmmwqhx5hqpiou

Asking Complex Questions with Multi-hop Answer-focused Reasoning [article]

Xiyao Ma, Qile Zhu, Yanlin Zhou, Xiaolin Li, Dapeng Wu
2020 arXiv   pre-print
Asking questions from natural language text has attracted increasing attention recently, and several schemes have been proposed with promising results by asking the right question words and copy relevant  ...  In this paper, we propose a new task called multihop question generation that asks complex and semantically relevant questions by additionally discovering and modeling the multiple entities and their semantic  ...  Semantic relatedness measures how well a generated question matches with the documents and the answer.  ... 
arXiv:2009.07402v1 fatcat:woidlj2rf5anrcwxgipkri5nmm

CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning [article]

Adam Dahlgren Lindström, Savitha Sam Abraham
2022 arXiv   pre-print
We apply state-of-the-art neural and neuro-symbolic models for visual question answering on CLEVR-Math and empirically evaluate their performances.  ...  Since the question posed may not be about the scene in the image, but about the state of the scene before or after the actions are applied, the solver envision or imagine the state changes due to these  ...  For multihop, training and validation sets with and without multihop questions are used, with the latter named multihop (0-shot).  ... 
arXiv:2208.05358v1 fatcat:whyrvcyqibapjb2trap5cnd5gi

MRNN: A Multi-Resolution Neural Network with Duplex Attention for Document Retrieval in the Context of Question Answering [article]

Tolgahan Cakaloglu, Xiaowei Xu
2019 arXiv   pre-print
The primary goal of ad-hoc retrieval (document retrieval in the context of question answering) is to find relevant documents satisfied the information need posted in a natural language query.  ...  In this paper, we devise a multi-resolution neural network(MRNN) to leverage the whole hierarchy of representations for document retrieval.  ...  Self-LSTM, Multihop-Sequential-LSTM [28] are developed to expose the relations between question and answer document captured by attention.  ... 
arXiv:1911.00964v1 fatcat:vxhhe4fbwrhcxbgdit36mwomqy

Reinforced Multi-task Approach for Multi-hop Question Generation [article]

Deepak Gupta, Hardik Chauhan, Akella Ravi Tej, Asif Ekbal, Pushpak Bhattacharyya
2020 arXiv   pre-print
Question generation (QG) attempts to solve the inverse of question answering (QA) problem by generating a natural language question given a document and an answer.  ...  For QG, we often require multiple supporting facts to generate high-quality questions.  ...  Acknowledgement Asif Ekbal gratefully acknowledges the Young Faculty Research Fellowship (YFRF) Award supported by the Visvesvaraya PhD scheme for Electronics and IT, Ministry of Electronics and Information  ... 
arXiv:2004.02143v4 fatcat:cwb6c4aq6vadlikttfl2kvxuwi

Multi-hop Question Generation with Graph Convolutional Network [article]

Dan Su, Yan Xu, Wenliang Dai, Ziwei Ji, Tiezheng Yu, Pascale Fung
2020 arXiv   pre-print
To address the additional challenges in multi-hop QG, we propose Multi-Hop Encoding Fusion Network for Question Generation (MulQG), which does context encoding in multiple hops with Graph Convolutional  ...  Multi-hop Question Generation (QG) aims to generate answer-related questions by aggregating and reasoning over multiple scattered evidence from different paragraphs.  ...  HotpotQA is a multihop question answering dataset, which contains Wikipedia-based question-answer pairs, with each question requiring multi-hop reasoning across multiple paragraphs to infer the answer.  ... 
arXiv:2010.09240v1 fatcat:n3q7bpc54fgvxhhndj5z5ao2du

Hopper: Multi-hop Transformer for Spatiotemporal Reasoning [article]

Honglu Zhou, Asim Kadav, Farley Lai, Alexandru Niculescu-Mizil, Martin Renqiang Min, Mubbasir Kapadia, Hans Peter Graf
2021 arXiv   pre-print
We propose Hopper, which uses a Multi-hop Transformer for reasoning object permanence in videos.  ...  Learning to reason: End-to-end module networks for visual question answering. In Proceedings of the IEEE International Conference on Computer Vision, pp. 804-813, 2017.  ...  Further, datasets for realworld visual reasoning and compositional question answering are released such as GQA (Hudson & Manning, 2019b) .  ... 
arXiv:2103.10574v2 fatcat:xgyssgeiy5cghkjvm5ufk6rbp4

Few-Shot Multihop Question Answering over Knowledge Base

Meihao Fan, Lei Zhang, Siyao Xiao, Yuru Liang
2022 Wireless Communications and Mobile Computing  
KBQA is a task that requires to answer questions by using semantic structured information in knowledge base.  ...  We evaluate our model on an open-domain complex Chinese question answering task CCKS2019 and achieve F1-score of 62.55% on the test dataset.  ...  Acknowledgments This work was partially supported by the Group Building Scientific Innovation Project for Universities in Chongqing (CXQT21021), the Innovation and Entrepreneurship Training Program for  ... 
doi:10.1155/2022/8045535 doaj:fa72643d652b458e80e0463aa25bb74f fatcat:t7w7ysbg4zg47hjb4leh43cvmq

SGEITL: Scene Graph Enhanced Image-Text Learning for Visual Commonsense Reasoning [article]

Zhecan Wang, Haoxuan You, Liunian Harold Li, Alireza Zareian, Suji Park, Yiqing Liang, Kai-Wei Chang, Shih-Fu Chang
2021 arXiv   pre-print
To exploit the scene graph structure, at the model structure level, we propose a multihop graph transformer for regularizing attention interaction among hops.  ...  Answering complex questions about images is an ambitious goal for machine intelligence, which requires a joint understanding of images, text, and commonsense knowledge, as well as a strong reasoning ability  ...  Given an image and a question, four possible answers and four possi- ble rationales for the correct answer are included.  ... 
arXiv:2112.08587v1 fatcat:7bpj6jmqb5fy5hznrry7t4tcsa

Prompt-based Conservation Learning for Multi-hop Question Answering [article]

Zhenyun Deng, Yonghua Zhu, Yang Chen, Qianqian Qi, Michael Witbrock, Patricia Riddle
2022 arXiv   pre-print
Moreover, to condition pre-trained language models to stimulate the kind of reasoning required for specific multi-hop questions, we learn soft prompts for the novel sub-networks to perform type-specific  ...  Multi-hop question answering (QA) requires reasoning over multiple documents to answer a complex question and provide interpretable supporting evidence.  ...  answer questions in a principled way that matches human expectations by answering sub-questions and integrating the answers.  ... 
arXiv:2209.06923v1 fatcat:okjalyoygncy5cninfbzu62egy

Coarse and Fine Granularity Graph Reasoning for Interpretable Multi-hop Question Answering

Min Zhang, Feng Li, Yang Wang, Zequn Zhang, Yanhai Zhou, Xiaoyu Li
2020 IEEE Access  
Interpretable multi-hop question answering requires step-by-step reasoning over multiple documents and finding scattered supporting facts to answer the question.  ...  In this paper, we propose the Coarse and Fine Granularity Graph Network (CFGGN), a novel interpretable model that combines both sentence information and entity information to answer the multi-hop questions  ...  ACKNOWLEDGMENT The authors thank their colleagues for helpful suggestions and discussions with regard to this work.  ... 
doi:10.1109/access.2020.2981134 fatcat:ixvp4axhsrfhreexfrihtuox2q

MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension [article]

Boyuan Pan, Hao Li, Zhou Zhao, Bin Cao, Deng Cai, Xiaofei He
2017 arXiv   pre-print
In this paper, we introduce a novel neural network architecture called Multi-layer Embedding with Memory Network(MEMEN) for machine reading task.  ...  Machine comprehension(MC) style question answering is a representative problem in natural language processing.  ...  portance of every part of the hierarchical attention vectors and the benefit of multi-hops in memory network.  ... 
arXiv:1707.09098v1 fatcat:uyrcsbkko5aqjkzqlqtzo72hpu
« Previous Showing results 1 — 15 out of 852 results