Discovering Entities with Just a Little Help from You

Singh, Jaspreet; Hoffart, Johannes; Anand, Avishek

doi:10.1145/2983323.2983798

Cited by 10 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, we showed that there seems to be a sweet spot in the choice of sparsity that varies depending on the dataset. We believe that the applicability of a sparsity-inducing component can extend beyond document ranking to other ranking [20,21,58], graph [13] and Web tasks [2,51,57].…”

Section: Discussionmentioning

confidence: 99%

Extractive Explanations for Interpretable Text Ranking

Leonhardt¹,

Rudra²,

Anand³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Machine learning models for the ad-hoc retrieval of documents and passages have recently shown impressive improvements due to better language understanding using large pre-trained language models. However, these over-parameterized models are inherently non-interpretable and do not provide any information on the parts of the documents that were used to arrive at a certain prediction.In this paper we introduce the select and rank paradigm for document ranking, where interpretability is explicitly ensured when scoring longer documents. Specifically, we first select sentences in a document based on the input query and then predict the querydocument score based only on the selected sentences, acting as an explanation. We treat sentence selection as a latent variable trained jointly with the ranker from the final output. We conduct extensive experiments to demonstrate that our inherently interpretable select-and-rank approach is competitive in comparison to other state-of-the-art methods and sometimes even outperforms them. This is due to our novel end-to-end training approach based on weighted reservoir sampling that manages to train the selector despite the stochastic sentence selection. We also show that our sentence selection approach can be used to provide explanations for models that operate on only parts of the document, such as BERT.

show abstract

Section: Discussionmentioning

confidence: 99%

Extractive Explanations for Interpretable Text Ranking

Leonhardt¹,

Rudra²,

Anand³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition to academic efforts, model debugging tools like [28,36], SageMaker 1 provided by Amazon are also available. Other human-in-the loop systems include [8,30] to update models and knowledge bases. However, they mostly focus on training process and do not provide a post-hoc model risk assessment.…”

Section: Related Workmentioning

confidence: 99%

SparCAssist: A Model Risk Assessment Assistant Based on Sparse Generated Counterfactuals

Zhang,

Setty,

Anand

2022

Preprint

Self Cite

View full text Add to dashboard Cite

We introduce SparCAssist, a general-purpose risk assessment tool for the machine learning models trained for language tasks. It evaluates models' risk by inspecting their behavior on counterfactuals, namely out-of-distribution instances generated based on the given data instance. The counterfactuals are generated by replacing tokens in rational subsequences identified by ExPred, while the replacements are retrieved using HotFlip or Masked Language Model based algorithms. The main purpose of our system is to help the human annotators to assess the model's risk on deployment. The counterfactual instances generated during the assessment are the by-product and can be used to train more robust NLP models in the future. CCS CONCEPTS• Information systems → Online analytical processing; • Humancentered computing → User interface toolkits; • Computing methodologies → Reasoning about belief and knowledge.

show abstract

“…Many research projects have entangled with the different problems described in this work, i.e. news aggregation [5,9,12,20,35], event pattern extraction [15,43], entity linking [12,19,20,23], emerging entity detection [14,17,25,30,34], event ontology population [29,42] and automatically answering journalist Ws [10,11]. However, only a few big projects are comparable to our system as end-to-end online pipelines for event detection and encoding.…”

Section: Related Workmentioning

confidence: 99%

VLX-Stories: Building an Online Event Knowledge Base with Emerging Entity Detection

Fernàndez-Cañellas

Espadaler²,

Rodríguez³

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We present an online multilingual system for event detection and comprehension from media feeds. The system retrieves information from news sites, aggregates them into events (event detection), and summarizes them by extracting semantic labels of its most relevant entities (event representation) in order to answer the journalism Ws: who, what, when and where. The generated events populate VLX-Stories-an event ontology-transforming unstructured text data to a structured knowledge base representation. Our system exploits an external entity Knowledge Graph (VKG) to help populate VLX-Stories. At the same time, this external knowledge graph can also be extended with a Dynamic Entity Linking (DEL) module, which detects emerging entities (EE) on unstructured data. The system is currently deployed in production and used by media producers in the editorial process, providing real-time access to breaking news. Each month, VLX-Stories detects over 9000 events from over 4000 news feeds from seven different countries and in three different languages. At the same time, it detects over 1300 EE per month, which populate VKG.

show abstract

Discovering Entities with Just a Little Help from You

Cited by 10 publications

References 22 publications

Extractive Explanations for Interpretable Text Ranking

Extractive Explanations for Interpretable Text Ranking

SparCAssist: A Model Risk Assessment Assistant Based on Sparse Generated Counterfactuals

VLX-Stories: Building an Online Event Knowledge Base with Emerging Entity Detection

Contact Info

Product

Resources

About