Cross-document Event Identity via Dense Annotation

Pratapa, Adithya; Liu, Zhengzhong; Hasegawa, Kimihiro; Li, Linwei; Yamakawa, Yukari; Zhang, Shikun; Mitamura, Teruko

doi:10.18653/v1/2021.conll-1.39

“…Event coreference resolution is closely related to event grounding but assumes a stricter notion of identity between mentions (Nothman et al, 2012). Multiple cross-document coreference resolution works made use of Wikipedia (Eirew et al, 2021) and Wikinews (Minard et al, 2016;Pratapa et al, 2021) for dataset collection. Minard et al (2016) obtained human translations of English Wikinews articles to create a crosslingual event coreference dataset.…”

Section: Event Coreferencementioning

confidence: 99%

“…The goal in CDEC is to understand the identity relationship between event mentions. This identity is often complicated by subevent and membership relations among events (Pratapa et al, 2021). Nothman et al (2012) proposed event linking as an alternative to coreference that helps ground report-worthy events to a KB.…”

Section: Introductionmentioning

confidence: 99%

Multilingual Event Linking to Wikidata

Pratapa¹,

Gupta²,

Mitamura³

2022

Proceedings of the Workshop on Multilingual Information Access (MIA)

Self Cite

View full text Add to dashboard Cite

We present a task of multilingual linking of events to a knowledge base. We automatically compile a large-scale dataset for this task, comprising of 1.8M mentions across 44 languages referring to over 10.9K events from Wikidata. We propose two variants of the event linking task: 1) multilingual, where event descriptions are from the same language as the mention, and 2) crosslingual, where all event descriptions are in English. On the two proposed tasks, we compare multiple event linking systems including BM25+ (Lv and Zhai, 2011a) and multilingual adaptations of the biencoder and crossencoder architectures from BLINK (Wu et al., 2020). In our experiments on the two task variants, we find both biencoder and crossencoder models significantly outperform the BM25+ baseline. Our results also indicate that the crosslingual task is in general more challenging than the multilingual task. To test the out-of-domain generalization of the proposed linking systems, we additionally create a Wikinews-based evaluation set. We present qualitative analysis highlighting various aspects captured by the proposed dataset, including the need for temporal reasoning over context and tackling diverse event descriptions across languages. 1

show abstract

“…Event coreference resolution is closely related to event grounding but assumes a stricter notion of identity between mentions (Nothman et al, 2012). Multiple cross-document coreference resolution works made use of Wikipedia (Eirew et al, 2021) and Wikinews (Minard et al, 2016;Pratapa et al, 2021) for dataset collection. Minard et al (2016) obtained human translations of English Wikinews articles to create a crosslingual event coreference dataset.…”

Section: Related Workmentioning

confidence: 99%

“…In CDEC, the goal is to understand the identity relationship between event mentions. This identity is often complicated by subevent and membership relations among events (Pratapa et al, 2021). Nothman et al (2012) proposed event linking as an alternative to coreference that helps ground report-worthy events to a KB.…”

Section: Introductionmentioning

confidence: 99%

Multilingual Event Linking to Wikidata

Pratapa¹,

Gupta²,

Mitamura³

2022

Preprint

Self Cite

0

View full text Add to dashboard Cite

We present a task of multilingual linking of events to a knowledge base. We automatically compile a large-scale dataset for this task, comprising of 1.8M mentions across 44 languages referring to over 10.9K events from Wikidata. We propose two variants of the event linking task: 1) multilingual, where event descriptions are from the same language as the mention, and 2) crosslingual, where all event descriptions are in English. On the two proposed tasks, we compare multiple event linking systems including BM25+ (Lv and Zhai, 2011a) and multilingual adaptations of the biencoder and crossencoder architectures from BLINK (Wu et al., 2020). In our experiments on the two task variants, we find both biencoder and crossencoder models significantly outperform the BM25+ baseline. Our results also indicate that the crosslingual task is in general more challenging than the multilingual task. To test the out-of-domain generalization of the proposed linking systems, we additionally create a Wikinews-based evaluation set. We present qualitative analysis highlighting various aspects captured by the proposed dataset, including the need for temporal reasoning over context and tackling diverse event descriptions across languages. 1

show abstract

“…The goal in CDEC is to understand the identity relationship between event mentions. This identity is often complicated by subevent and membership relations among events (Pratapa et al, 2021). Nothman et al (2012) proposed event linking as an alternative to coreference that helps ground report-worthy events to a KB.…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the Workshop on Multilingual Information Access (MIA)

2022

0

View full text Add to dashboard Cite

Stemming from the limited availability of datasets and textual resources for low-resource languages such as isiZulu, there is a significant need to be able to harness knowledge from pre-trained models to improve low resource machine translation. Moreover, a lack of techniques to handle the complexities of morphologically rich languages has compounded the unequal development of translation models, with many widely spoken African languages being left behind. This study explores the potential benefits of transfer learning in an English-isiZulu translation framework. The results indicate the value of transfer learning from closely related languages to enhance the performance of low-resource translation models, thus providing a key strategy for low-resource translation going forward. We gathered results from 8 different language corpora, including one multilingual corpus, and saw that isiXhosa-isiZulu outperformed all languages, with a BLEU score of 8.56 on the test set which was better from the multi-lingual corpora pre-trained model by 2.73. We also derived a new coefficient, Nasir's Geographical Distance Coefficient (NGDC) which provides an easy selection of languages for the pre-trained models. NGDC also indicated that isiXhosa should be selected as the language for the pre-trained model.

show abstract

Cross-document Event Identity via Dense Annotation

Cited by 3 publications

References 9 publications

Multilingual Event Linking to Wikidata

Multilingual Event Linking to Wikidata

Multilingual Event Linking to Wikidata

Proceedings of the Workshop on Multilingual Information Access (MIA)

Contact Info

Product

Resources

About