no code implementations • ACL (IWPT) 2021 • Christoph Teichmann, Antoine Venant
When learned without exploration, local models for structured prediction tasks are subject to exposure bias and cannot be trained without detailed guidance.
no code implementations • EMNLP (NLP+CSS) 2020 • Katherine A. Keith, Christoph Teichmann, Brendan O'Connor, Edgar Meij
We find for this application (1) some annotator disagreements of economic policy uncertainty can be attributed to ambiguity in language, and (2) switching measurements from keyword-matching to supervised machine learning classifiers results in low correlation, a concerning implication for the validity of the index.
no code implementations • WS 2019 • Chunyang Xiao, Christoph Teichmann, Konstantine Arkoudas
While sequence-to-sequence (seq2seq) models achieve state-of-the-art performance in many natural language processing tasks, they can be too slow for real-time applications.
no code implementations • WS 2018 • Nikos Engonopoulos, Christoph Teichmann, Alexander Koller
We present a model which predicts how individual users of a dialog system understand and produce utterances based on user groups.
no code implementations • WS 2017 • Christoph Teichmann, Alex Koller, er, Jonas Groschwitz
We generalize coarse-to-fine parsing to grammar formalisms that are more expressive than PCFGs and/or describe languages of trees or graphs.
no code implementations • ACL 2017 • Mart{\'\i}n Villalba, Christoph Teichmann, Alex Koller, er
The referring expressions (REs) produced by a natural language generation (NLG) system can be misunderstood by the hearer, even when they are semantically correct.
no code implementations • EACL 2017 • Johannes Gontrum, Jonas Groschwitz, Alex Koller, er, Christoph Teichmann
We present Alto, a rapid prototyping tool for new grammar formalisms.