• Publications
  • Influence
Cheap Translation for Cross-Lingual Named Entity Recognition
A simple method for cross-lingual named entity recognition (NER) that works well in settings with very minimal resources, and makes use of a lexicon to “translate” annotated data available in one or several high resource language(s) into the target language, and learns a standard monolingual NER model there.
Cross-Lingual Named Entity Recognition via Wikification
A language independent method for NER is introduced, building on cross-lingual wikification, a technique that grounds words and phrases in nonEnglish text into English Wikipedia entries, yielding strong language-independent features.
Concept-based analysis of scientific literature
An unsupervised bootstrapping algorithm for identifying and categorizing mentions of concepts and a new clustering algorithm that uses citations' context as a way to cluster the extracted mentions into coherent concepts are proposed.
Zero-Shot Open Entity Typing as Type-Compatible Grounding
A zero-shot entity typing approach that requires no annotated data and can flexibly identify newly defined types is proposed that is shown to be competitive with state-of-the-art supervised NER systems, and to outperform them on out- of-training datasets.
Named Entity Recognition with Partially Annotated Training Data
This work introduces a constraint-driven iterative algorithm that learns to detect false negatives in the noisy set and downweigh them, resulting in a weighted NER model, and evaluates the algorithm with weighted variants of neural and non-neural NER models on data in 8 languages from several language and script families, showing strong ability to learn from partial data.
Open Domain Question Answering via Semantic Enrichment
A new QA system that mines answers directly from the Web, and meanwhile employs KBs as a significant auxiliary to further boost the QA performance, and makes the first attempt to link answer candidates to entities in Freebase, during answer candidate generation.
Cross-lingual Wikification Using Multilingual Embeddings
This paper jointly training multilingual embeddings for words and Wikipedia titles in 12 languages and shows that the proposed approach outperforms various baselines on the TAC KBP2015 Entity Linking task.
A Linear Ensemble of Individual and Blended Models for Music Rating Prediction
The four stages: individual model building, non-linear blending, linear ensemble and post-processing lead to a successful final solution, within which techniques on feature engineering and aggregation (blending and ensemble learning) play crucial roles.
Concept Grounding to Multiple Knowledge Bases via Indirect Supervision
  • Chen-Tse Tsai, D. Roth
  • Computer Science
    Transactions of the Association for Computational…
  • 25 April 2016
This work develops an algorithmic approach that generates an indirect supervision signal it uses to train a ranking model that accurately chooses knowledge base entries for a given mention, and shows that considering multiple knowledge bases together has an advantage over grounding concepts to each knowledge base individually.
Overview of UI-CCG Systems for Event Argument Extraction , Entity Discovery and Linking , and Slot Filler Validation
In this paper, we describe the University of Illinois (UI CCG) submission to the 2013 TAC KBP Event Argument Extraction (EAE), English Entity Discovery and Linking (EDL), and Slot Filler Validation