Overview of the English Slot Filling Track at the TAC2014 Knowledge Base Population Evaluation

By Mihai Surdeanu, Heng Ji. 2014

Subfields: Information Retrieval & Search, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Language Models as Knowledge Bases? (2019, methodology): “This requires complex NLP pipelines involving entity extraction, coreference resolution, entity linking and relation extraction (Surdeanu and Ji, 2014)— components that often need supervised data and ﬁxed schemas.”
KILT: a Benchmark for Knowledge Intensive Language Tasks (2020, background): “Likewise, while the classical approach of information extraction for populating a Knowledge Base (KB, Riedel et al., 2013; Surdeanu and Ji, 2014) seems outof-fashion, recent results show that they remain contenders (Fan et al.”
Learning How to Ask: Querying LMs with Mixtures of Soft Prompts (2021, methodology): “Factual knowledge is traditionally extracted from large corpora using a pipeline of NLP tools (Surdeanu and Ji, 2014), including entity extraction (Lample et al., 2016), entity linking (Rao et al., 2013) and relation extraction (Sorokin and Gurevych, 2017).”
Modifying Memories in Transformer Models (2020, background): “In addition to improving generalization with better language understanding, Transformers may also replace or assist traditional knowledge bases (KBs) that are either manually curated or require signiﬁcant amount of supervision (Roth and Yih, 2002; Kambhatla, 2004; Surdeanu and Ji, 2014).”
Data Programming: Creating Large Training Sets, Quickly (2016, neutral): “Under conditions similar to those in Section 3, we can again provide a bound the accuracy of these results.”
Stacked Ensembles of Information Extractors for Knowledge-Base Population (2015, methodology): “each extracted slot-filler must include a pointer to a document passage that supports it (Surdeanu and Ji, 2014).”
Stacking With Auxiliary Features (2016, background): “The speciﬁc auxiliary features depend on the task under consideration as described in the sections below.”
Cross-Sentence N-ary Relation Extraction with Graph LSTMs (2017, background): “, 2005) or entity-centric attributes that can be extracted largely independently (Chinchor, 1998; Surdeanu and Heng, 2014).”
Effective Crowd Annotation for Relation Extraction (2016, background): “Despite these technical innovations, the best systems at the TAC-KBP evaluation1 still require substantial human effort, typically handwritten extraction rules (Surdeanu and Ji, 2014).”