1 |
Denoising Word Embeddings by Averaging in a Shared Space ...
|
|
|
|
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 ...
|
|
|
|
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 ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
CogALex-V Shared Task: LexNET - Integrated Path-based and Distributional Method for the Identification of Semantic Relations ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Path-based vs. Distributional Information in Recognizing Lexical Semantic Relations ...
|
|
|
|
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 ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|