9 citations · 14 across the 5 of their papers we have counts for
7 papers
Do End-to-End Speech Recognition Models Care About Context?
Lasse Borgholt, Jakob Drachmann Havtorn, Željko Agić +3
The two most common paradigms for end-to-end speech recognition are connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models. It has been argued…
MultiQT: Multimodal Learning for Real-Time Question Tracking in Speech
Jakob D. Havtorn, Jan Latko, Joakim Edin +6
We address a challenging and practical task of labeling questions in speech in real time during telephone calls to emergency medical services in English, which embeds within a broa…
Towards Instance-Level Parser Selection for Cross-Lingual Transfer of Dependency Parsers
Robert Litschko, Ivan Vulić, Željko Agić +1
Current methods of cross-lingual parser transfer focus on predicting the best parser for a low-resource target language globally, that is, "at treebank level". In this work, we pro…
The Best of Both Worlds: Lexical Resources To Improve Low-Resource Part-of-Speech Tagging
Barbara Plank, Sigrid Klerke, Zeljko Agic
In natural language processing, the deep learning revolution has shifted the focus from conventional hand-crafted symbolic representations to dense inputs, which are adequate repre…
Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging
Barbara Plank, Željko Agić
We introduce DsDs: a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision, and realistically scales to hundreds of low-resource lang…
Baselines and test data for cross-lingual inference
Željko Agić, Natalie Schluter
The recent years have seen a revival of interest in textual entailment, sparked by i) the emergence of powerful deep neural network learners for natural language processing and ii)…
Parsing Universal Dependencies without training
Héctor Martínez Alonso, Željko Agić, Barbara Plank +1
We propose UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of head attachment rules. It features two-step de…