Papers with mention detection

17 papers
Neural Mention Detection (2020.lrec-1)

Copied to clipboard

Challenge: Mention detection is an important preprocessing step for downstream applications such as NER and coreference resolution.
Approach: They propose and compare three approaches to mention detection using ELMO embeddings and a biaffine classifier.
Outcome: The proposed model outperforms state-of-the-art models on the GENIA corpora and improves on mention recall.
Leveraging syntactic parsing to improve event annotation matching (D19-59)

Copied to clipboard

Challenge: Evaluating annotator consistency is crucial when building datasets for mention detection.
Approach: They propose to use different fuzzy-matching functions to resolve this ambiguity by extracting syntactic heads present in annotations and using the Dice coefficient to measure similarity between sets.
Outcome: The proposed functions are tested against the judgment of a human evaluator and show that the best-performing function agrees with the human .
French Coreference for Spoken and Written Language (2020.lrec-1)

Copied to clipboard

Challenge: In French, most coreference resolution systems run different setups, making comparisons difficult.
Approach: They present a full-stack model that outperforms other approaches for coreference resolution in French . they compare it with the first end-to-end neural French coreference model trained on democrat .
Outcome: The proposed model outperforms the current systems for spoken and written French.
Realistic Evaluation Principles for Cross-document Coreference Resolution (2021.starsem-1)

Copied to clipboard

Challenge: Using permissive evaluation protocols, cross-document coreference resolution models produce inflated results.
Approach: They propose to decouple evaluation of mention detection from coreference linking . they argue that models should not exploit the synthetic topic structure of the standard ECB+ dataset .
Outcome: The proposed evaluation principles yield lower results than previous lenient evaluation methods.
PreCo: A Large-scale Dataset in Preschool Vocabulary for Coreference Resolution (D18-1)

Copied to clipboard

Challenge: Existing methods for coreference resolution are based on word2vec-like representations of entities.
Approach: They propose a large-scale English dataset for coreference resolution . they use 38K documents and 12.5M words from English-speaking preschoolers .
Outcome: The proposed dataset is more efficient with higher training-test overlap than OntoNotes . the study also shows that mention detection and clustering are more efficient on PreCo .
Neural Coreference Resolution with Deep Biaffine Attention by Joint Mention Detection and Mention Clustering (P18-2)

Copied to clipboard

Challenge: Existing methods for identifying and clustering mentions in text are complex and require heuristics to solve.
Approach: They propose to use a biaffine attention model to get antecedent scores for each possible mention and optimize mention detection and mention clustering accuracy given the mention cluster labels.
Outcome: The proposed model achieves the state-of-the-art performance on the CoNLL-2012 shared task English test set.
ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking (2022.naacl-industry)

Copied to clipboard

Challenge: Entity linking is the task of recognising mentions of entities in unstructured text documents and linking them to the corresponding entities in a Knowledge Base (KB) the largest public EL dataset is Wikipedia, which covers just 3% of the entities in Wikidata.
Approach: They propose a model which performs mention detection, fine-grained entity typing, and entity disambiguation for all mentions within a document in a single forward pass.
Outcome: The proposed model outperforms state-of-the-art methods on standard datasets by an average of 3.7 F1 and can generalise to large-scale knowledge bases such as Wikidata and zero-shot entity linking.
Contextualized End-to-End Neural Entity Linking (2020.aacl-main)

Copied to clipboard

Challenge: a proposed entity linking model that disjointly applies MD and ED from the same contextualized BERT embeddings is able to generalize better.
Approach: They propose an entity linking (EL) model that jointly learns mention detection (MD) and entity disambiguation (ED) they propose to use task-specific heads on top of shared BERT contextualized embeddings to learn MD and ED.
Outcome: The proposed model achieves state-of-the-art results across a standard EL dataset and under a setting where hand-crafted candidate sets are not available.
Figurative Usage Detection of Symptom Words to Improve Personal Health Mention Detection (P19-1)

Copied to clipboard

Challenge: Past work in personal health mention detection uses classification-based methods with human-engineered features or word embedding-based features.
Approach: They propose to combine a pipeline-based and a feature augmentation-based approach to combine personal health mention detection with figurative usage detection to improve the accuracy of the prediction.
Outcome: The proposed method improves the F-score of personal health mention detection by 2.21% over the pipeline-based approach and feature augmentation-based approaches.
Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem (2022.findings-acl)

Copied to clipboard

Challenge: Existing methods for entity linking do not use a knowledge base or candidate sets.
Approach: They propose an autoregressive entity linking model that is trained with two auxiliary tasks and learns to re-rank generated samples at inference time.
Outcome: The proposed model improves on two biomedical datasets and a news domain dataset without the use of a knowledge base or candidate sets.
Efficient One-Pass End-to-End Entity Linking for Questions (2020.emnlp-main)

Copied to clipboard

Challenge: Existing models for entity linking are limited to entity disambiguation and require mention boundaries to be given in the input.
Approach: They propose a fast end-to-end entity linking model that uses a biencoder to jointly detect mentions and link in one pass.
Outcome: The proposed model outperforms the current state of the art on WebQSP and GraphQuestions with extended annotations that cover multiple entities per question.
Hedwig: A Named Entity Linker (2020.lrec-1)

Copied to clipboard

Challenge: Named entity linking is the task of identifying mentions of named things in text . e.g., "Barack Obama" or "New York" are examples of named entities .
Approach: They propose an end-to-end named entity linker that uses BILSTM models for mention detection and a PageRank algorithm for entity linking.
Outcome: The proposed named entity linker performs better than the previous generation, and is trilingually better.
Annotating Mentions Alone Enables Efficient Domain Adaptation for Coreference Resolution (2023.acl-long)

Copied to clipboard

Challenge: Recent results show that annotating mentions is twice as fast as annotation of full coreference chains.
Approach: They propose a method for efficiently adapting coreference models using only mentions in the target domain without increasing annotator time.
Outcome: The proposed method improves average F1 without increasing annotator time.
ner and pos when nothing is capitalized (D19-1)

Copied to clipboard

Challenge: Named entity recognition and part of speech tagging require capitalization in training.
Approach: They propose to modify only the casing of the train or test data using lowercasing and truecasing methods to modify the cassing of a model with high performance on both cased and uncased text.
Outcome: The proposed model improves mention detection on noisy out-of-domain Twitter data by 8%.
Major Entity Identification: A Generalizable Alternative to Coreference Resolution (2024.emnlp-main)

Copied to clipboard

Challenge: Prior work identified annotation differences as one of the main reasons for the limited generalization gap in coreference resolution models.
Approach: They propose an alternative referential task where the target entities are assumed to be specified in the input and the task is limited to the frequent entities.
Outcome: The proposed model generalizes well across domains on multiple datasets with supervised models and LLM-based few-shot prompting.
Adversarial Removal of Demographic Attributes Revisited (D19-1)

Copied to clipboard

Challenge: Several approaches have been proposed to learn classifiers that are invariant (unbiased with respect) to protected attributes.
Approach: They propose to use a diagnostic classifier trained on a held-out subsample to find protected attributes for mention detection at above-chance levels.
Outcome: The proposed classifier generalizes poorly to new in-domain and new domains, suggesting it relies on correlations specific to their particular data sample.
SPLICE: A Singleton-Enhanced PipeLIne for Coreference REsolution (2024.lrec-main)

Copied to clipboard

Challenge: Existing attempts to integrate singleton mention detection into end-to-end coreference resolution for English have been hampered by the lack of singletont mention spans in the OntoNotes benchmark.
Approach: They propose a two-step neural mention and coreference resolution system that integrates singleton mentions with OntoNotes syntax trees to achieve a near approximation of the Ontonotes dataset with all singletont mentions.
Outcome: The proposed system achieves 94% recall on a sample of gold singletons.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations