• Publications
  • Influence
Contextual String Embeddings for Sequence Labeling
This paper proposes to leverage the internal states of a trained character language model to produce a novel type of word embedding which they refer to as contextual string embeddings, which are fundamentally model words as sequences of characters and are contextualized by their surrounding text. Expand
FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP
The core idea of the FLAIR framework is to present a simple, unified interface for conceptually very different types of word and document embeddings, which effectively hides all embedding-specific engineering complexity and allows researchers to “mix and match” variousembeddings with little effort. Expand
Pooled Contextualized Embeddings for Named Entity Recognition
This work proposes a method in which it dynamically aggregate contextualized embeddings of each unique string that the authors encounter and uses a pooling operation to distill a ”global” word representation from all contextualized instances. Expand
Generating High Quality Proposition Banks for Multilingual Semantic Role Labeling
This paper presents a two-stage method to enable the construction of SRL models for resourcepoor languages by exploiting monolingual SRL and multilingual parallel data and shows that this method outperforms existing methods. Expand
Wanderlust : Extracting Semantic Relations from Natural Language Text Using Dependency Grammar Patterns
A great share of applications in modern information technology can benefit from large coverage, machine accessible knowledge bases. However, the bigger part of todays knowledge is provided in theExpand
KrakeN: N-ary Facts in Open Information Extraction
KrakeN is an OIE system specifically designed to capture N-ary facts, as well as the results of an experimental study on extracting facts from Web text in which the issue of fact completeness is examined. Expand
POLYGLOT: Multilingual Semantic Role Labeling with Unified Labels
POLYGLOT is a multilingual semantic role labeling system capable of semantically parsing sentences in 9 different languages from 4 different language groups and treats the semantic labels of the English Proposition Bank as “universal semantic labels”. Expand
Unsupervised Discovery of Relations and Discriminative Extraction Patterns
It is shown that an informed feature generation technique based on dependency trees significantly improves clustering quality, as measured by the F-score, and therefore the ability of the URE method to discover relations in text, and is extended to produce a set of weighted patterns for each identified relation. Expand
Towards Semi-Automatic Generation of Proposition Banks for Low-Resource Languages
An experimental study is presented where annotation projection is applied to three languages that lack high-quality parallel corpora and syntactic parsers: Tamil, Bengali and Malayalam, which indicates that annotation projection alone is insufficient in low-resource scenarios. Expand
The Weltmodell: A Data-Driven Commonsense Knowledge Base
The Weltmodell is presented, a commonsense knowledge base that was automatically generated from aggregated dependency parse fragments gathered from over 3.5 million English language books and a range of measures of association and distributional similarity on this data. Expand