Papers with OntoNotes 5.0
Cross-lingual Zero Pronoun Resolution (2020.lrec-1)
Copied to clipboard
| Challenge: | In pronoun-dropping languages, predicate arguments are not realized instead of being realized as overt pronounos. |
| Approach: | They propose a BERT-based model for zero pronoun resolution in Arabic and Chinese . they also evaluate BERT feature extraction and fine-tune models on the task . |
| Outcome: | The proposed model outperforms the state-of-the-art model for Arabic and Chinese on OntoNotes 5.0. |
Reliability-aware Dynamic Feature Composition for Name Tagging (P19-1)
Copied to clipboard
| Challenge: | Word embeddings are used to encode semantic information, but their quality is not consistent across the vocabulary due to the long-tail distribution of word frequency. |
| Approach: | They propose a reliability-aware name tagging model that uses word frequency to indicate word quality . they propose to use word frequency-based reliability signals to dynamically select and compose features . |
| Outcome: | The proposed model outperforms the baseline model on OntoNotes 5.0 and up to 5% gain on cross-genre data sets. |
When Speed Meets Intelligence: Scalable Conversational NER in an Ever-evolving World (2026.eacl-industry)
Copied to clipboard
| Challenge: | Large Language Models excel at understanding conversational semantics, but lack of data makes them impractical for production deployment. |
| Approach: | They propose a pipeline for generating multilingual conversational NER datasets with minimal human validation and a framework that leverages LLMs as semantic filters combined with catalog-based entity grounding to label live traffic data. |
| Outcome: | The proposed framework outperforms existing models on public and private conversations by 97.12% on CoNLL-2003 and 83.09% on OntoNotes 5.0. |
Deep Reinforcement Learning for Chinese Zero Pronoun Resolution (P18-1)
Copied to clipboard
| Challenge: | Recent models for zero pronoun resolution in Chinese are short-sighted and do not capture semantic information for zeros and candidate antecedents. |
| Approach: | They propose to integrate a deep reinforcement learning approach to Chinese zero pronoun resolution. |
| Outcome: | The proposed approach outperforms the state-of-the-art methods in three experimental settings. |
Subsequence Based Deep Active Learning for Named Entity Recognition (2021.acl-long)
Copied to clipboard
| Challenge: | Active Learning (AL) has been successfully applied to Deep Learning to drastically reduce the amount of data required to achieve high performance. |
| Approach: | They propose to query subsequences within sentences and propagate their labels to other sentences. |
| Outcome: | The proposed approach achieves high performance on OntoNotes 5.0 and CoNLL 2003 with only 13% of training data and 27% of the training data. |
Fine-grained Named Entity Annotations for German Biographic Interviews (2020.lrec-1)
Copied to clipboard
| Challenge: | a NER annotation scheme is adapted for a corpus of transcripts of biographic interviews with emigrants to German . a dataset of spoken data and teaser tweets from newspaper sites are used to test the NER inventory. |
| Approach: | They propose a fine-grained NER annotation scheme with 30 labels and apply it to German data. |
| Outcome: | The proposed NER annotations can be applied to spoken data and teaser tweets from newspaper sites and achieve good inter-annotator agreement. |
Incremental Neural Coreference Resolution in Constant Memory (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on coreference resolution has focused on improving pairwise span scoring functions and methods for decoding into globally consistent clusters. |
| Approach: | They extend an incremental clustering algorithm to utilize contextualized encoders and neural components to generate a high-performing model. |
| Outcome: | The proposed model reduces memory usage to constant space with only a 0.3% relative loss in F1 on OntoNotes 5.0. |