A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering
[article]
2021
arXiv
pre-print
Preserved Fulltext
One of the main challenges in conversational question answering (CQA) is to resolve the conversational dependency, such as anaphora and ellipsis. ...
In this paper, we propose a novel framework, ExCorD (Explicit guidance on how to resolve Conversational Dependency) to enhance the abilities of QA models in comprehending conversational context. ...
Yi, Miyoung Ko, and Jinhyuk Lee for providing valuable comments and feedback. ...
arXiv:2106.11575v1
fatcat:xphiymkoubfnlibjphowgnmgx4
Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering
2021
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
One of the main challenges in conversational question answering (CQA) is to resolve the conversational dependency, such as anaphora and ellipsis. ...
In this paper, we propose a novel framework, EXCORD (Explicit guidance on how to resolve Conversational Dependency) to enhance the abilities of QA models in comprehending conversational context. ...
Yi, Miyoung Ko, and Jinhyuk Lee for providing valuable comments and feedback. ...
doi:10.18653/v1/2021.acl-long.478
fatcat:v7wdntskezfmlbmgbaeqbk7u5y
CQR-SQL: Conversational Question Reformulation Enhanced Context-Dependent Text-to-SQL Parsers
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we propose CQR-SQL, which uses auxiliary Conversational Question Reformulation (CQR) learning to explicitly exploit schema and decouple contextual dependency for SQL parsing. ...
Secondly, we train CQR-SQL models to map the semantics of multi-turn questions and auxiliary self-contained questions into the same latent space through schema grounding consistency task and tree-structured ...
For context-dependent text-to-SQL, it is common to train a model in an end-to-end manner. ...
arXiv:2205.07686v2
fatcat:nh2utaetdfes5noa4esf64ijyq
Dependency Parsing
2009
Synthesis Lectures on Human Language Technologies
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
After an introduction to dependency grammar and dependency parsing, followed by a formal characterization of the dependency parsing problem, the book surveys the three major classes of parsing models that ...
This book gives a thorough introduction to the methods that are most widely used today. ...
Memory-based classifiers are very efficient to train, since learning only consists in storing the training instances for efficient retrieval. ...
doi:10.2200/s00169ed1v01y200901hlt002
fatcat:e6bea7jadrbjjf2mweetf6a6mu
Context Dependent Semantic Parsing: A Survey
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
To address this issue, context dependent semantic parsing has recently drawn a lot of attention. ...
Currently, most semantic parsing methods are not able to utilize contextual information (e.g. dialogue and comments history), which has a great potential to boost semantic parsing performance. ...
Acknowledgements We thank Xuanli He and anonymous reviewers for their useful suggestions. ...
arXiv:2011.00797v1
fatcat:vagpeidcbrahhcpucioo7fabay
Semantic Role Labeling as Syntactic Dependency Parsing
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Based on this observation, we present a conversion scheme that packs SRL annotations into dependency tree representations through joint labels that permit highly accurate recovery back to the original ...
This representation allows us to train statistical dependency parsers to tackle SRL and achieve competitive performance with the current state of the art. ...
Tsai for discussion and comments. ...
arXiv:2010.11170v1
fatcat:qolkf4y7xze2pis6pzrxanbhlq
Learning Dependency-Based Compositional Semantics
[article]
2011
arXiv
pre-print
Preserved Fulltext
The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
Our goal is to learn a semantic parser from question-answer pairs instead, where the logical form is modeled as a latent variable. ...
Suppose we want to build a system that answers a natural language question by representing its semantics as a logical form and computing the answer given a structured database of facts. ...
Acknowledgments We thank Luke Zettlemoyer and Tom Kwiatkowski for providing us with data and answering questions. The first author was supported by an NSF Graduate Research Fellowship. ...
arXiv:1109.6841v1
fatcat:tim4m3ncefcl3ibkjyc6duc6ee
Learning Dependency-Based Compositional Semantics
2013
Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Our goal is to instead learn a semantic parser from question-answer pairs, where the logical form is modeled as a latent variable. ...
Suppose we want to build a system that answers a natural language question by representing its semantics as a logical form and computing the answer given a structured database of facts. ...
Acknowledgments We thank Luke Zettlemoyer and Tom Kwiatkowski for providing us with data and answering questions, as well as the anonymous reviewers for their detailed feedback. P. ...
doi:10.1162/coli_a_00127
fatcat:ofx7l5tkyvezjfsslq2b73qsvu
Decreasing Authority Dependence During the First Year of College
2012
Journal of College Student Development
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
He explained: It's a real big change going from a class where there's a right answer and a wrong answer to a class where there's a million answers, none of which are right and none of which are wrong. ...
A reflective conversation guide based on the WNS interview (Baxter Magolda & King, 2008b ) is one resource for educators to solicit learners' meaning making in routine conversations. ...
doi:10.1353/csd.2012.0040
fatcat:pxbgtzg4knefvm4ndsw2bq2cwq
Dependency Annotation Choices: Assessing Theoretical and Practical Issues of Universal Dependencies
2016
Proceedings of the 10th Linguistic Annotation Workshop held in conjunction with ACL 2016 (LAW-X 2016)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This article attempts to place dependency annotation options on a solid theoretical and applied footing. ...
By verifying the validity of some basic choices of the current dependency reference framework, Universal Dependencies (UD), in a perspective of general annotation principles, we show how some choices can ...
This also causes the parser to have more similar training examples and fewer ambiguities to resolve (precision). ...
doi:10.18653/v1/w16-1715
dblp:conf/acllaw/GerdesK16
fatcat:ys6azh4tzffvrmv4zepmicxs6i
HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In view of the mismatch, we treat natural language and SQL as two modalities and propose a bimodal pre-trained model to bridge the gap between them. ...
Recently, context-dependent text-to-SQL semantic parsing which translates natural language into SQL in an interaction process has attracted a lot of attention. ...
to avoid leaking answers and help SQL-BERT learn the information structure of SQL better. ...
arXiv:2203.07376v2
fatcat:72rz6byvjrfmdkvvoaup43rf2i
Transforming Dependency Structures to Logical Forms for Semantic Parsing
2016
Transactions of the Association for Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
In contrast-partly due to the lack of a strong type system-dependency structures are easy to annotate and have become a widely used form of syntactic analysis for many languages. ...
Experiments on the Free917 and Web-Questions datasets show that our representation is superior to the original dependency trees and that it outperforms a CCG-based representation on this task. ...
The authors would also like to thank Christopher Potts and the three anonymous reviewers for their valuable feedback. ...
doi:10.1162/tacl_a_00088
fatcat:egsiqtgdtjfy7k6frmaymr26cm
From Dependence to Causation
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
First, we develop a framework for the study of statistical dependence based on copulas and random features. ...
Machine learning is the science of discovering statistical dependencies in data, and the use of those dependencies to perform predictions. ...
Instead, these discriminative dependence methods summarize the dependence structure of a multivariate data set into a low-dimensional statistic that answers the question at hand. ...
arXiv:1607.03300v1
fatcat:img5m23n5ncx5mfejgqkjft2ua
Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Learning representations that accurately capture long-range dependencies in sequential inputs -- including text, audio, and genomic data -- is a key problem in deep learning. ...
Feed-forward convolutional models capture only feature interactions within finite receptive fields while recurrent architectures can be slow and difficult to train due to vanishing gradients. ...
We train the model (with and without TFiLM layers) to fill in the missing values. We train for 50 epochs using the ADAM optimizer with a learning rate of 3 × 10 −4 . ...
arXiv:1909.06628v3
fatcat:4jcgn5gr65fdjlqyberafpuvvq
GraphSearchNet: Enhancing GNNs via Capturing Global Dependency for Semantic Code Search
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To address these challenges, in this paper, we design a novel neural network framework, named GraphSearchNet, to enable an effective and accurate source code search by jointly learning rich semantics of ...
Most existing deep learning-based approaches for code search rely on the sequential text i.e., feeding the program and the query as a flat sequence of tokens to learn the program semantics while the structural ...
Furthermore, due to the powerful relation learning capacity of GNNs, they also have been widely used in many NLP tasks, e.g., natural question generation (QG) [30] , [43] , conversational machine comprehension ...
arXiv:2111.02671v3
fatcat:lco2syw7ijbh7bfw4bhd53dvbq
« Previous
Showing results 1 — 15 out of 86,889 results