264 Hits in 10.2 sec

Inferential Machine Comprehension: Answering Questions by Recursively Deducing the Evidence Chain from Text

Jianxing Yu, Zhengjun Zha, Jian Yin
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
This paper focuses on the topic of inferential machine comprehension, which aims to fully understand the meanings of given text to answer generic questions, especially the ones needed reasoning skills.  ...  By recursively linking the cells, the inferred results are synthesized together to form the evidence chain for reasoning, where the reasoning direction can be guided by imposing structural constraints  ...  The main contributions of this paper include, • We design a new network that can answer inferential question by recursively deducing the evidence chain from the text. • We propose an effective termination  ... 
doi:10.18653/v1/p19-1217 dblp:conf/acl/YuZY19 fatcat:nzgaavqmxrg43nh6n6twkxg7hq

From LSAT: The Progress and Challenges of Complex Reasoning [article]

Siyuan Wang, Zhongkun Liu, Wanjun Zhong, Ming Zhou, Zhongyu Wei, Zhumin Chen, Nan Duan
2021 arXiv   pre-print
In this paper, we take a step forward in complex reasoning by systematically studying the three challenging and domain-general tasks of the Law School Admission Test (LSAT), including analytical reasoning  ...  The experimental results demonstrate that our system endows itself a certain complex reasoning ability, especially the fundamental reading comprehension and challenging logical reasoning capacities.  ...  Further research can focus on improving evidence retrieval and predicting answers from noised evidence. VII.  ... 
arXiv:2108.00648v1 fatcat:q6oy5rzbs5dcfc2cdkrslhmmpi

MS-Ranker: Accumulating Evidence from Potentially Correct Candidates for Answer Selection [article]

Yingxue Zhang, Fandong Meng, Peng Li, Ping Jian, Jie Zhou
2020 arXiv   pre-print
As conventional answer selection (AS) methods generally match the question with each candidate answer independently, they suffer from the lack of matching information between the question and the candidate  ...  evidence for matching the question with a candidate.  ...  Inferential machine comprehension: Answering questions by recursively deducing the evidence chain from text. In ACL, pages 2241–2251.  ... 
arXiv:2010.04970v1 fatcat:suedwlhvs5frpcaoqifhcaqgoy

Epistemic Virtues, Metavirtues, and Computational Complexity

Adam Morton
2004 Noûs  
The necessity of these virtues follows in part from the nonexistence of shortcuts, or efficient ways of finding shortcuts, to cognitively expensive routines.  ...  complexity, epistemology, epistemic virtue, metavirtue, virtue. the text as it will appear in Nous appendix one: the naturalness of complexity classes appendix two: proofs notes references sections of  ...  And the reason is not very mysterious: the consistency question forces one to explore the branches of the tree of computations of answers to deducibility questions, and the number of branches of a tree  ... 
doi:10.1111/j.0029-4624.2004.00479.x fatcat:d45grjyygrbwplnxyt5jlytfbm


Wilfried Sieg
2009 Philosophy of Mathematics  
Here lies the key to answering the question, "What distinguishes Turing's proposal so dramatically from Church's?"  ...  This answers the first question formulated at the end of section 2.2.  ... 
doi:10.1016/b978-0-444-51555-1.50017-1 fatcat:7fjtsyt6izeizbzm4zgoastvuy

Metacognition in computation: A selected research review

Michael T. Cox
2005 Artificial Intelligence  
I examine metacognition with respect to both problem solving (e.g., planning) and to comprehension (e.g., story understanding) processes of cognition.  2005 Published by Elsevier B.V.  ...  I discuss some of these aspects of cognition about cognition and the results concerning them from the point of view of the psychologist and the computer scientist, and I attempt to place them in the context  ...  He argued that if a machine uses models to answer questions about events in the world and the machine itself is in the world, then it must also use a recursive self-model or simulation to answer questions  ... 
doi:10.1016/j.artint.2005.10.009 fatcat:6oghpyu5wrbe3djr6he4wvmx2y

Relevance theory and the scope of the grammar

Liliane Haegeman
1987 Behavioral and Brain Sciences  
indirect evidence (e.g., by "saying something").  ...  We analyse both the nature of cognitive effects and the inferential processes by which they are derived.  ...  Millikan and Pettit don't discuss this question, and the only answer we can think of is that it is supplemented by inference. Inference goes from evidence to conclusions warranted by the evidence.  ... 
doi:10.1017/s0140525x00055448 fatcat:3p7j2aff6nb2pi5f2u42ekigwe

The relevance of Relevance for fiction

Anne Reboul
1987 Behavioral and Brain Sciences  
indirect evidence (e.g., by "saying something").  ...  We analyse both the nature of cognitive effects and the inferential processes by which they are derived.  ...  Millikan and Pettit don't discuss this question, and the only answer we can think of is that it is supplemented by inference. Inference goes from evidence to conclusions warranted by the evidence.  ... 
doi:10.1017/s0140525x00055539 fatcat:3thm73jktjht3kc5ikzw67jk6i

Perspectives in deductive databases

Jack Minker
1988 The Journal of Logic Programming  
., Theorem Proving by Resolution as a Basis for Question-Answering Systems, in: B. Meltzer and D.  ...  ., chains of inferences that were of the form Because of the questionable reliability of the information, the analysts were not willing to accept reasoning based on chains of deductions, but wanted reconfirmation  ... 
doi:10.1016/0743-1066(88)90006-4 fatcat:nte73kgo2fhcjcahpxz65huysy

Mining meaning from Wikipedia

Olena Medelyan, David Milne, Catherine Legg, Ian H. Witten
2009 International Journal of Human-Computer Studies  
We identify the research groups and individuals involved, and how their work has developed in the last few years. We provide a comprehensive list of the open-source software they have produced. r  ...  This article provides a comprehensive description of this work.  ...  Medelyan is supported by a scholarship from Google, Milne by the New Zealand Tertiary Education Commission.  ... 
doi:10.1016/j.ijhcs.2009.05.004 fatcat:mzxszf4jlfcizbgxuemgdwzdiy

Procedural semantics

Philip N. Johnson-Laird
1977 Cognition  
A uniji'ed model of the comprehension and production of sentences is drscribed in order to illustrate the central "compile and execute" metaphor underlying procedural semantics.  ...  The role of general knowledge within the lexicon, and the mechanism mediating selectional restrictions, are re-anall'zed in the light of the procedural theory.  ...  by deducing it from other facts in the data-base.  ... 
doi:10.1016/0010-0277(77)90001-4 fatcat:ph2som347vbrnd2qpepthfcvc4

Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods [article]

Wei Li, Wenhao Wu, Moye Chen, Jiachen Liu, Xinyan Xiao, Hua Wu
2022 arXiv   pre-print
However, the faithfulness problem that the generated text usually contains unfaithful or non-factual information has become the biggest challenge, which makes the performance of text generation unsatisfactory  ...  translation, and data-to-text generation.  ...  The additional procedure generated question-answer pairs from the source document and answered the questions from the generated text.  ... 
arXiv:2203.05227v1 fatcat:q2u3ojyi6vb7pjt6ajwbinjmpa


Paul Deane, Nora Odendahl, Thomas Quinlan, Mary Fowles, Cyndi Welsh, Jennifer Bivens-Tatum
2008 ETS Research Report Series  
The model that emerges from a review of the literature on writing places a strong emphasis on writing as an integrated, socially situated skill that cannot be assessed properly without taking into account  ...  course of the school year.  ...  This is also the case with claims that easily can be deduced from what is known.  ... 
doi:10.1002/j.2333-8504.2008.tb02141.x fatcat:ait7mqqqtfgybce4rv3iuwiake

From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony

Lokendra Shastri, Venkat Ajjanagadde
1993 Behavioral and Brain Sciences  
This remarkable human ability seems paradoxical given the results about the complexity of reasoning reported by researchers in artificial intelligence.  ...  Our model achieves this by i) representing dynamic bindings as the synchronous firing of appropriate nodes, ii) rules as interconnection patterns that direct the propagation of rhythmic activity, iii)  ...  This research was supported by NSF grants IRI 88-05465, ARO grants DAA29-84-9-0027 and DAAL03-89-C-0031, and the DFG grant Schr 275/7-1.  ... 
doi:10.1017/s0140525x00030910 fatcat:t74nkr32nvau7jce2lzsmkhrxe

Philosophical Perspectives

Jochen Albrecht, Hunter College
2020 Geographic Information Science & Technology Body of Knowledge  
Version 1.0 4.1 Introduction: Ethics and information 4.2 Historical overview 4.3 Towards a unified approach to information ethics 4.4 Floridi's information ethics 4.5 The fundamental principles of Floridi's  ...  SAM is given a story like the one above and then is asked to answer some comprehension questions.  ...  In testing whether computers can imitate us in answering questions, we are testing only whether machines can answer questions like us.  ... 
doi:10.22224/gistbok/2020.2.1 fatcat:ppcm2igyora3reqolttwmfn7o4
« Previous Showing results 1 — 15 out of 264 results