Page: 1... 56 57 58 59 60 61 62 63
Hits 1.181 – 1.200 of 1.255
1181 |
Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claims ...
|
|
|
|
BASE
|
|
Show details
|
|
1182 |
AMBERT: A Pre-trained Language Model with Multi-Grained Tokenization ...
|
|
|
|
BASE
|
|
Show details
|
|
1183 |
Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights ...
|
|
|
|
BASE
|
|
Show details
|
|
1184 |
As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
1185 |
Hell Hath No Fury? Correcting Bias in the NRC Emotion Lexicon ...
|
|
|
|
BASE
|
|
Show details
|
|
1186 |
*SEM 2021: The 10th Joint Conference on Lexical and Computational Semantics - Part 1 ...
|
|
|
|
BASE
|
|
Show details
|
|
1187 |
Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction ...
|
|
|
|
BASE
|
|
Show details
|
|
1188 |
MIN_PT: An European Portuguese Lexicon for Minorities Related Terms ...
|
|
|
|
BASE
|
|
Show details
|
|
1190 |
System Description for the CommonGen task with the POINTER model ...
|
|
|
|
BASE
|
|
Show details
|
|
1191 |
Using surprisal and fMRI to map the neural bases of broad and local contextual prediction during natural language comprehension ...
|
|
|
|
BASE
|
|
Show details
|
|
1194 |
Grammar-Constrained Neural Semantic Parsing with LR Parsers ...
|
|
|
|
BASE
|
|
Show details
|
|
1195 |
Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR Alignments ...
|
|
|
|
Abstract:
Read paper: https://www.aclanthology.org/2021.acl-long.257 Abstract: We present algorithms for aligning components of Abstract Meaning Representation (AMR) graphs to spans in English sentences. We leverage unsupervised learning in combination with heuristics, taking the best of both worlds from previous AMR aligners. Our unsupervised models, however, are more sensitive to graph substructures, without requiring a separate syntactic parse. Our approach covers a wider variety of AMR substructures than previously considered, achieves higher coverage of nodes and edges, and does so with higher accuracy. We will release our LEAMR datasets and aligner for use in research on AMR parsing, generation, and evaluation. ...
|
|
Keyword:
Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
|
|
URL: https://dx.doi.org/10.48448/rkxj-hp53 https://underline.io/lecture/25593-probabilistic,-structure-aware-algorithms-for-improved-variety,-accuracy,-and-coverage-of-amr-alignments
|
|
BASE
|
|
Hide details
|
|
1196 |
Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger ...
|
|
|
|
BASE
|
|
Show details
|
|
1197 |
Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
1198 |
Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
1200 |
A Targeted Assessment of Incremental Processing in Neural Language Models and Humans ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1... 56 57 58 59 60 61 62 63
|
|