skip to main content

Explore Research Products in the NSF-PAR

Title: Benchmarking Scalable Methods for Streaming Cross Document Entity Coreference
Streaming cross document entity coreference (CDC) systems disambiguate mentions of named entities in a scalable manner via incremental clustering. Unlike other approaches for named entity disambiguation (e.g., entity linking), streaming CDC allows for the disambiguation of entities that are unknown at inference time. Thus, it is well-suited for processing streams of data where new entities are frequently introduced. Despite these benefits, this task is currently difficult to study, as existing approaches are either evaluated on datasets that are no longer available, or omit other crucial details needed to ensure fair comparison. In this work, we address this issue by compiling a large benchmark adapted from existing free datasets, and performing a comprehensive evaluation of a number of novel and existing baseline models. We investigate: how to best encode mentions, which clustering algorithms are most effective for grouping mentions, how models transfer to different domains, and how bounding the number of mentions tracked during inference impacts performance. Our results show that the relative performance of neural and feature-based mention encoders varies across different domains, and in most cases the best performance is achieved using a combination of both approaches. We also find that performance is minimally impacted by limiting the number of tracked mentions.  more » « less
Award ID(s):
1817183
NSF-PAR ID:
10291544
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Page Range / eLocation ID:
4717 to 4731
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ( , Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies)
    null (Ed.)
    Due to large number of entities in biomedical knowledge bases, only a small fraction of entities have corresponding labelled training data. This necessitates entity linking models which are able to link mentions of unseen entities using learned representations of entities. Previous approaches link each mention independently, ignoring the relationships within and across documents between the entity mentions. These relations can be very useful for linking mentions in biomedical text where linking decisions are often difficult due mentions having a generic or a highly specialized form. In this paper, we introduce a model in which linking decisions can be made not merely by linking to a knowledge base entity but also by grouping multiple mentions together via clustering and jointly making linking predictions. In experiments on the largest publicly available biomedical dataset, we improve the best independent prediction for entity linking by 3.0 points of accuracy, and our clustering-based inference model further improves entity linking by 2.3 points. 
    more » « less
  2. ; ; ; ( , AAAI Conference on Artificial Intelligence (AAAI))
    Entity linking is the task of linking mentions of named entities in natural language text, to entities in a curated knowledge-base. This is of significant importance in the biomedical domain, where it could be used to semantically annotate a large volume of clinical records and biomedical literature, to standardized concepts described in an ontology such as Unified Medical Language System (UMLS). We observe that with precise type information, entity disambiguation becomes a straightforward task. However, fine-grained type information is usually not available in biomedical domain. Thus, we propose LATTE, a LATent Type Entity Linking model, that improves entity linking by modeling the latent fine-grained type information about mentions and entities. Unlike previous methods that perform entity linking directly between the mentions and the entities, LATTE jointly does entity disambiguation, and latent fine-grained type learning, without direct supervision. We evaluate our model on two biomedical datasets: MedMentions, a large scale public dataset annotated with UMLS concepts, and a de-identified corpus of dictated doctor’s notes that has been annotated with ICD concepts. Extensive experimental evaluation shows our model achieves significant performance improvements over several state-of-the-art techniques. 
    more » « less
  3. ; ; ; ; ; ( , Proceedings of the Association for Computational Linguistics (ACL))
    Pre-trained language models induce dense entity representations that offer strong performance on entity-centric NLP tasks, but such representations are not immediately interpretable. This can be a barrier to model uptake in important domains such as biomedicine.There has been recent work on general interpretable representation learning (Onoe and Durrett, 2020), but these domain-agnostic representations do not readily transfer to the important domain of biomedicine. In this paper, we create a new entity type system and train-ing set from a large corpus of biomedical texts by mapping entities to concepts in a medical ontology, and from these to Wikipedia pages whose categories are our types. From this map-ping we deriveBiomedical Interpretable Entity Representations(BIERs), in which dimensions correspond to fine-grained entity types, and values are predicted probabilities that a given entity is of the corresponding type. We propose a novel method that exploits BIER’s final sparse and intermediate dense representations to facilitate model and entity type debugging. We show that BIERs achieve strong performance in biomedical tasks including named entity disambiguation and entity linking, and we provide error analysis to highlight the utility of their interpretability, particularly in low-supervision settings. Finally, we provide our induced 68K biomedical type system, the corresponding 37 million triples of derived data used to train BIER models and our best per-forming model. 
    more » « less
  4. ; ; ( , ICDE)
    An important task for Information Extraction from Microblogs is Named Entity Recognition (NER) that extracts mentions of real-world entities from microblog messages and meta-information like entity type for better entity characterization. A lot of microblog NER systems have rightly sought to prioritize modeling the non-literary nature of microblog text. These systems are trained on offline static datasets and extract a combination of surface-level features – orthographic, lexical, and semantic – from individual messages for noisy text modeling and entity extraction. But given the constantly evolving nature of microblog streams, detecting all entity mentions from such varying yet limited context in short messages remains a difficult problem to generalize. In this paper, we propose the NER Globalizer pipeline better suited for NER on microblog streams. It characterizes the isolated message processing by existing NER systems as modeling local contextual embeddings, where learned knowledge from the immediate context of a message is used to suggest seed entity candidates. Additionally, it recognizes that messages within a microblog stream are topically related and often repeat mentions of the same entity. This suggests building NER systems that go beyond localized processing. By leveraging occurrence mining, the proposed system therefore follows up traditional NER modeling by extracting additional mentions of seed entity candidates that were previously missed. Candidate mentions are separated into well-defined clusters which are then used to generate a pooled global embedding drawn from the collective context of the candidate within a stream. The global embeddings are utilized to separate false positives from entities whose mentions are produced in the final NER output. Our experiments show that the proposed NER system exhibits superior effectiveness on multiple NER datasets with an average Macro F1 improvement of 47.04% over the best NER baseline while adding only a small computational overhead. 
    more » « less
  5. ; ; ( , The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022))
    Entity linking, the task of linking potentially ambiguous mentions in texts to corresponding knowledge-base entities, is an important component for language understanding. We address two challenge in entity linking: how to leverage wider contexts surrounding a mention, and how to deal with limited training data. We propose a fully unsupervised model called SumMC that first generates a guided summary of the contexts conditioning on the mention, and then casts the task to a multiple-choice problem where the model chooses an entity from a list of candidates. In addition to evaluating our model on existing datasets that focus on named entities, we create a new dataset that links noun phrases from WikiHow to Wikidata. We show that our SumMC model achieves state-of-the-art unsupervised performance on our new dataset and on exiting datasets. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email