Julia Proskurnia

My current interests are user behavior analysis and modeling using social media traces. In particular, I focus in summarization and filtering of the topically relevant information in both short and long texts. Moreover, I worked with multi-dimensional time-series prediction, knowledge-base construction, relation extraction and natural language processing.
Authored Publications
Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    REPLACING HUMAN-RECORDED AUDIO WITH SYNTHETIC AUDIOFOR ON-DEVICE UNSPOKEN PUNCTUATION PREDICTION
    Bogdan Prisacari
    Daria Soboleva
    Felix Weissenberger
    Justin Lu
    Márius Šajgalík
    ICASSP 2021: International Conference on Acoustics, Speech and Signal Processing (2021) (to appear)
    Preview abstract We present a novel multi-modal unspoken punctuation prediction system for the English language, which relies on Quasi-Recurrent Neural Networks (QRNNs) applied jointly on the text output from automatic speech recognition and acoustic features. % We show significant improvements from adding acoustic features compared to the text-only baseline. Because annotated acoustic data is hard to obtain, we demonstrate that relying on only 20% of human-annotated audio and replacing the rest with synthetic text-to-speech (TTS) predictions, does not suffer from quality loss on LibriTTS corpus. % Furthermore, we demonstrate that through data augmentation using TTS models, we can remove human-recorded audio completely and outperform models trained on it. View details
    Insertion-Deletion Transformer
    Laura Ruis
    Mitchell Stern
    William Chan
    EMNLP WNGT (2020)
    Preview abstract We propose the Insertion-Deletion Transformer, a novel transformer-based neural architecture and training method for sequence generation. The model consists of two phases that are executed iteratively, 1) an insertion phase and 2) a deletion phase. The insertion phase parameterizes a distribution of insertions on the current output hypothesis, while the deletion phase parameterizes a distribution of deletions over the current output hypothesis. The training method is a principled and simple algorithm, where the deletion model obtains its signal directly on-policy from the insertion model output. We demonstrate the effectiveness of our Insertion-Deletion Transformer on synthetic translation tasks, obtaining significant BLEU score improvement over an insertion-only model. View details
    Template Induction over Unstructured Email Corpora
    Lluís Garcia-Pueyo
    Ivo Krka
    Tobias Kaufmann
    Proc. of the 26th International World Wide Web Conference (2017), pp. 1521-1530
    Preview abstract Unsupervised template induction over email data is a central component in applications such as information extraction, document classification, and auto-reply. The benefits of automatically generating such templates are known for structured data, e.g. machine generated HTML emails. However much less work has been done in performing the same task over unstructured email data. We propose a technique for inducing high quality templates from plain text emails at scale based on the suffix array data structure. We evaluate this method against an industry-standard approach for finding similar content based on shingling, running both algorithms over two corpora: a synthetically created email corpus for a high level of experimental control, as well as user-generated emails from the well-known Enron email corpus. Our experimental results show that the proposed method is more robust to variations in cluster quality than the baseline and templates contain more text from the emails, which would benefit extraction tasks by identifying transient parts of the emails. Our study indicates templates induced using suffix arrays contain approximately half as much noise (measured as entropy) as templates induced using shingling. Furthermore, the suffix array approach is substantially more scalable, proving to be an order of magnitude faster than shingling even for modestly-sized training clusters. Public corpus analysis shows that email clusters contain on average 4 segments of common phrases, where each of the segments contains on average 9 words, thus showing that templatization could help users reduce the email writing effort by an average of 35 words per email in an assistance or auto-reply related task. View details