DE eng

Search in the Catalogues and Directories

Page: 1 2 3
Hits 1 – 20 of 50

1
Denoising Word Embeddings by Averaging in a Shared Space ...
BASE
Show details
2
CDLM: Cross-Document Language Modeling ...
BASE
Show details
3
Cross-document Coreference Resolution over Predicted Mentions ...
BASE
Show details
4
Summary-Source Proposition-level Alignment: Task, Datasets and Supervised Baseline ...
BASE
Show details
5
Teach the Rules, Provide the Facts: Targeted Relational-knowledge Enhancement for Textual Inference ...
BASE
Show details
6
Denoising Word Embeddings by Averaging in a Shared Space ...
BASE
Show details
7
Realistic Evaluation Principles for Cross-document Coreference Resolution ...
Abstract: We point out that common evaluation practices for cross-document coreference resolution have been unrealistically permissive in their assumed settings, yielding inflated results. We propose addressing this issue via two evaluation methodology principles. First, as in other tasks, models should be evaluated on predicted mentions rather than on gold mentions. Doing this raises a subtle issue regarding singleton coreference clusters, which we address by decoupling the evaluation of mention detection from that of coreference linking. Second, we argue that models should not exploit the synthetic topic structure of the standard ECB+ dataset, forcing models to confront the lexical ambiguity challenge, as intended by the dataset creators. We demonstrate empirically the drastic impact of our more realistic evaluation principles on a competitive model, yielding a score which is 33 F1 lower compared to evaluating by prior lenient practices. ... : *SEM 2021 ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://arxiv.org/abs/2106.04192
https://dx.doi.org/10.48550/arxiv.2106.04192
BASE
Hide details
8
QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions ...
BASE
Show details
9
Asking It All: Generating Contextualized Questions for any Semantic Role ...
BASE
Show details
10
Paraphrasing vs Coreferring: Two Sides of the Same Coin ...
BASE
Show details
11
Revisiting the Binary Linearization Technique for Surface Realization
In: Proceedings of The 12th International Conference on Natural Language Generation ; https://hal.archives-ouvertes.fr/hal-02460309 ; Proceedings of The 12th International Conference on Natural Language Generation, 2019, pp.268 - 278 (2019)
BASE
Show details
12
Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution ...
BASE
Show details
13
ABSApp: A Portable Weakly-Supervised Aspect-Based Sentiment Extraction System ...
BASE
Show details
14
Still a Pain in the Neck: Evaluating Text Representations on Lexical Composition ...
Shwartz, Vered; Dagan, Ido. - : arXiv, 2019
BASE
Show details
15
Still a Pain in the Neck: Evaluating Text Representations on Lexical Composition
In: Transactions of the Association for Computational Linguistics, Vol 7, Pp 403-419 (2019) (2019)
BASE
Show details
16
Paraphrase to Explicate: Revealing Implicit Noun-Compound Relations ...
Shwartz, Vered; Dagan, Ido. - : arXiv, 2018
BASE
Show details
17
CogALex-V Shared Task: LexNET - Integrated Path-based and Distributional Method for the Identification of Semantic Relations ...
Shwartz, Vered; Dagan, Ido. - : arXiv, 2016
BASE
Show details
18
Path-based vs. Distributional Information in Recognizing Lexical Semantic Relations ...
Shwartz, Vered; Dagan, Ido. - : arXiv, 2016
BASE
Show details
19
SemEval-2013 Task 7: The Joint Student Response Analysis and 8th Recognizing Textual Entailment Challenge
In: DTIC (2013)
BASE
Show details
20
UKP-BIU: Similarity and Entailment Metrics for Student Response Analysis ...
Zesch, Torsten; Levy, Omer; Gurevych, Iryna. - : DuEPublico: Duisburg-Essen Publications online, University of Duisburg-Essen, Germany, 2013
BASE
Show details

Page: 1 2 3

Catalogues
2
1
5
0
0
0
0
Bibliographies
17
0
0
0
0
0
0
0
1
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
27
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern