1 |
Inflating Topic Relevance with Ideology: A Case Study of Political Ideology Bias in Social Topic Detection Models ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Inflating Topic Relevance with Ideology: A Case Study of Political Ideology Bias in Social Topic Detection Models ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
MimicProp: Learning to Incorporate Lexicon Knowledge into Distributed Word Representation for Social Media Analysis
|
|
|
|
In: Proceedings of the International AAAI Conference on Web and Social Media; Vol. 14 (2020): Fourteenth International AAAI Conference on Web and Social Media; 738-749 ; 2334-0770 ; 2162-3449 (2020)
|
|
BASE
|
|
Show details
|
|
4 |
Report on EMNLP Reviewer Survey
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-01660886 ; [Technical Report] Association for computational linguistics. 2017 (2017)
|
|
BASE
|
|
Show details
|
|
7 |
Heuristic Sample Selection to Minimize Reference Standard Training Set for a Part-Of-Speech Tagger
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Breaking the Resource Bottleneck for Multilingual Parsing
|
|
|
|
In: DTIC AND NTIS (2005)
|
|
BASE
|
|
Show details
|
|
14 |
Evaluating Translational Correspondence Using Annotation Projection
|
|
|
|
In: DTIC (2003)
|
|
BASE
|
|
Show details
|
|
15 |
Evaluating Translational Correspondence using Annotation Projection
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Improved Word-Level Alignment: Injecting Knowledge about MT Divergences
|
|
|
|
In: DTIC (2002)
|
|
BASE
|
|
Show details
|
|
17 |
Word-level Alignment for Multilingual Resource Acquisition
|
|
|
|
In: DTIC (2002)
|
|
BASE
|
|
Show details
|
|
19 |
On Minimizing Training Corpus for Parser Acquisition
|
|
|
|
In: DTIC (2001)
|
|
BASE
|
|
Show details
|
|
20 |
Supervised Grammar Induction Using Training Data with Limited Constituent Information ...
|
|
|
|
Abstract:
Corpus-based grammar induction generally relies on hand-parsed training data to learn the structure of the language. Unfortunately, the cost of building large annotated corpora is prohibitively expensive. This work aims to improve the induction strategy when there are few labels in the training data. We show that the most informative linguistic constituents are the higher nodes in the parse trees, typically denoting complex noun phrases and sentential clauses. They account for only 20% of all constituents. For inducing grammars from sparsely labeled training data (e.g., only higher-level constituent labels), we propose an adaptation strategy, which produces grammars that parse almost as well as grammars induced from fully labeled corpora. Our results suggest that for a partial parser to replace human annotators, it must be able to automatically extract higher-level constituents rather than base noun phrases. ... : 7 pages, 2 figures, to appear in the proc. of ACL '99 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; I.2.6; I.2.7
|
|
URL: https://arxiv.org/abs/cs/9905001 https://dx.doi.org/10.48550/arxiv.cs/9905001
|
|
BASE
|
|
Hide details
|
|
|
|