Joint Modeling of Arguments for Event Understanding

Chen, Yunmo; Chen, Tongfei; Durme, Benjamin Van

doi:10.18653/v1/2020.codi-1.10

Cited by 11 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our pipeline consisted of multilingual coreference resolution (using predetermined mention spans), the hierarchical entity typing model, and a separate state-of-the-art argument linking model (Chen et al, 2020b). We found improved performance 13 with entity coreference (from 29.1 F1 to 33.3 F1), especially in Russian (from 26.2 F1 to 33.3 F1), likely due to our use of multilingual data and encoders.…”

Section: And Match Modules: Sm-kbpmentioning

confidence: 99%

LOME: Large Ontology Multilingual Extraction

Xia¹,

Qin²,

Vashishtha³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present LOME, a system for performing multilingual information extraction. Given a text document as input, our core system identifies spans of textual entity and event mentions with a FrameNet (Baker et al., 1998) parser. It subsequently performs coreference resolution, fine-grained entity typing, and temporal relation prediction between events. By doing so, the system constructs an event and entity focused knowledge graph. We can further apply third-party modules for other types of annotation, like relation extraction. Our (multilingual) first-party modules either outperform or are competitive with the (monolingual) state-of-the-art. We achieve this through the use of multilingual encoders like XLM-R (Conneau et al., 2020) and leveraging multilingual training data. LOME is available as a Docker container on Docker Hub. In addition, a lightweight version of the system is accessible as a web demo. 1 * Equal Contribution 1 Information on using the Docker container and the web demo at https://nlp.jhu.edu/demos.

show abstract

Section: And Match Modules: Sm-kbpmentioning

confidence: 99%

LOME: Large Ontology Multilingual Extraction

Xia¹,

Qin²,

Vashishtha³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…We use Unified-QA (Khashabi et al, 2020) as the ENCODER described in Section 4.2. Since our experiment setting is inherently the same as by and Chen et al (2020c), we follow prior work and use span-level F1 as the evaluation metric. We take Chen et al (2020c) as our baseline, shown as JOINTARG in the tables, since it obtains previous state-of-the-art results on both ACE and RAMS using gold mention spans.…”

Section: Experimental Settingsmentioning

confidence: 99%

“…Since our experiment setting is inherently the same as by and Chen et al (2020c), we follow prior work and use span-level F1 as the evaluation metric. We take Chen et al (2020c) as our baseline, shown as JOINTARG in the tables, since it obtains previous state-of-the-art results on both ACE and RAMS using gold mention spans. As far as we are aware, we are the first to publish results on the Granular dataset with this experimental setup.…”

Section: Experimental Settingsmentioning

confidence: 99%

Asking the Right Questions in Low Resource Template Extraction

Holzenberger¹,

Yunmo²,

Durme³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Information Extraction (IE) researchers are mapping tasks to Question Answering (QA) in order to leverage existing large QA resources, and thereby improve data efficiency.Especially in template extraction (TE), mapping an ontology to a set of questions can be more time-efficient than collecting labeled examples. We ask whether end users of TE systems can design these questions, and whether it is beneficial to involve an NLP practitioner in the process. We compare questions to other ways of phrasing natural language prompts for TE. We propose a novel model to perform TE with prompts, and find it benefits from questions over other styles of prompts, and that they do not require an NLP background to author.

show abstract

“…Our pipeline consisted of the multilingual coreference resolution (using the predetermined mention from GAIA) and hierarchical entity typing models discussed in this paper, followed by a separate state-of-the-art argument linking model (Chen et al, 2020b). We found improved performance 17 with entity coreference (from 29.1 F1 to 33.3 F1), especially in Russian (from 26.2 F1 to 33.3 F1), likely due to our use of multilingual data and contextualized encoders.…”

Section: And Match Modules: Sm-kbpmentioning

confidence: 99%

LOME: Large Ontology Multilingual Extraction

Xia

Qin

Vashishtha

et al. 2021

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrati

Self Cite

View full text Add to dashboard Cite

We present LOME, a system for performing multilingual information extraction. Given a text document as input, our core system identifies spans of textual entity and event mentions with a FrameNet (Baker et al., 1998) parser. It subsequently performs coreference resolution, fine-grained entity typing, and temporal relation prediction between events. By doing so, the system constructs an event and entity focused knowledge graph. We can further apply third-party modules for other types of annotation, like relation extraction. Our (multilingual) first-party modules either outperform or are competitive with the (monolingual) state-of-the-art. We achieve this through the use of multilingual encoders like XLM-R (Conneau et al., 2020) and leveraging multilingual training data. LOME is available as a Docker container on Docker Hub. In addition, a lightweight version of the system is accessible as a web demo. * Equal Contribution 1 Information on using the Docker container, web demo, and demo video at https://nlp.jhu.edu/demos.

show abstract

Joint Modeling of Arguments for Event Understanding

Cited by 11 publications

References 18 publications

LOME: Large Ontology Multilingual Extraction

LOME: Large Ontology Multilingual Extraction

Asking the Right Questions in Low Resource Template Extraction

LOME: Large Ontology Multilingual Extraction

Contact Info

Product

Resources

About