English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Speech Entity Linking aims to recognize and disambiguate named entities inspoken languages. Conventional methods suffer gravely from the unfetteredspeech styles and the noisy transcripts generated by ASR systems. In thispaper, we propose a novel approach called Knowledge Enhanced Named EntityRecognition (KENER), which focuses on improving robustness through painlesslyincorporating proper knowledge in the entity recognition stage and thusimproving the overall performance of entity linking. KENER first retrievescandidate entities for a sentence without mentions, and then utilizes theentity descriptions as extra information to help recognize mentions. Thecandidate entities retrieved by a dense retrieval module are especially usefulwhen the input is short or noisy. Moreover, we investigate various datasampling strategies and design effective loss functions, in order to improvethe quality of retrieved entities in both recognition and disambiguationstages. Lastly, a linking with filtering module is applied as the finalsafeguard, making it possible to filter out wrongly-recognized mentions. Oursystem achieves 1st place in Track 1 and 2nd place in Track 2 of NLPCC-2022Shared Task 2.

DAMO-NLP at NLPCC-2022 Task 2: Knowledge Enhanced Robust NER for Speech Entity Linking