OntoNotes

Annotated corpora are only useful if their annotations are consistent. Most large-scale annotation efforts take special measures to reconcile inter-annotator disagreement. To date, however, no-one has investigated how to automatically …...

The accuracy of current word sense disam- biguation (WSD) systems is affected by the fine-grained sense inventory of WordNet as well as a lack of training examples. Using the WSD …...

. Information Extraction (IE) is becoming increasingly useful, but it is a costly task to discover and annotate novel events, event arguments, and event types. We exploit both monolingual texts …...

We describe our system for the CoNLL-2012 shared task, which seeks to model corefer- ence in OntoNotes for English, Chinese, and Arabic. We adopt a hybrid approach to coreference resolution, …...

The CoNLL-2012 shared task involved pre- dicting coreference in English, Chinese, and Arabic, using the final version, v5.0, of the OntoNotes corpus. It was a follow-on to the English-only task …...

The current work presents the participa- tion of UBIU (Zhekova and K¨ubler, 2010) in the CoNLL-2012 Shared Task: Model- ing Multilingual Unrestricted Coreference in OntoNotes (Pradhan et al., 2012). Our …...

Coreference resolution is a well known clus- tering task in Natural Language Processing. In this paper, we describe the Latent Left Linking model (L3M), a novel, principled, and linguis- tically …...

We extend Zhao and Ng's (2007) Chinese anaphoric zero pronoun resolver by (1) using a richer set of features and (2) exploiting the coreference links between zero pronouns dur- ing …...

AbstractWe present a joint model of three core tasks in the entity analysis stack: coreference resolution (within-document clustering), named entity recognition (coarse semantic typing), and entity linking (matching to Wikipedia …...

Most state-of-the-art approaches for named-entity recognition (NER) use semi supervised information in the form of word clusters and lexicons. Recently neural network-based language models have been explored, as they as …...

AbstractIn this paper we present an alignment experiment between patterns of verb use discovered by Corpus Pattern Analysis (CPA; Hanks 2004, 2008, 2012) and verb senses in OntoNotes (ON; Hovy …...

We propose a novel search-based approach for greedy coreference resolution, where the mentions are processed in order and added to previous coreference clusters. Our method is distinguished by the use …...

AbstractThis paper describes the extension of the Ontologies of Linguistic Annotation (OLiA) with respect to discourse features. The OLiA ontologies provide a a terminology repository that can be employed to …...

AbstractWe present coreference annotation on parallel Czech-English texts of the Prague Czech-English Dependency Treebank (PCEDT). The paper describes innovations made to PCEDT 2.0 concerning coreference, as well as coreference information …...

AbstractHigh accuracy for automated translation and information retrieval calls for linguistic annotations at various language levels. The plethora of informal internet content sparked the demand for porting state-of-art natural language …...

This paper presents WiFiNE, an English corpus annotated with fine-grained entity types. We propose simple but effective heuristics we applied to English Wikipedia to build a large, high quality, annotated …...

AbstractNoise is inherent in real world datasets and modeling noise is critical during training as it is effective in regularization. Recently, novel semi-supervised deep learning techniques have demonstrated tremendous potential …...

AbstractThe performance of standard coreference resolution is known to drop significantly on Twitter texts. We improve the performance of the (Lee et al., 2018) system, which is originally trained on …...

AbstractLong document coreference resolution remains a challenging task due to the large memory and runtime requirements of current models. Recent work doing incremental coreference resolution using just the global representation …...

AbstractWe present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. Our approach extends BERT by (1) masking contiguous random spans, rather than random …...

AbstractIn response to (i) inconclusive results in the literature as to the properties of coreference chains in written versus spoken language, and (ii) a general lack of work on automatic …...

AbstractA common issue in real-world applications of named entity recognition and classification (NERC) is the absence of annotated data for the target entity classes during training. Zero-shot learning approaches address …...

AbstractTo audit the robustness of named entity recognition (NER) models, we propose RockNER, a simple yet effective method to create natural adversarial examples. Specifically, at the entity level, we replace …...

AbstractThe number of senses of a given word, or polysemy, is a very subjective notion, which varies widely across annotators and resources. We propose a novel method to estimate polysemy …...

AbstractNamed Entity Recognition (NER) in Few-Shot setting is imperative for entity tagging in low resource domains. Existing approaches only learn class-specific semantic features and intermediate representations from source domains. This …...

AbstractIn this paper we investigate the application of active learning to semantic role labeling (SRL) using Bayesian Active Learning by Disagreement (BALD). Our new predicate-focused selection method quickly improves efficiency …...

AbstractOntonotes has served as the most important benchmark for coreference resolution. However, for ease of annotation, several long documents in Ontonotes were split into smaller parts. In this work, we …...