Alexey Romanov

A Ph.D. Student at UMass Lowell


I am currently a second year Ph.D. student at UMass Lowell in the Text-Machine Lab working with Anna Rumshisky. My research interests at this moment are particulary focused on applying Deep Learning methods in Natural Language Procrocessing.

Projects and Papers

#HashtagWars: Learning a Sense of Humor

This work presents a new dataset for computational humor, specifically comparative humor ranking, which attempts to eschew the ubiquitous binary approach to humor detection. The dataset consists of tweets that are humorous responses submitted to a Comedy Central TV show @midnight. While a strong RNN token-level system can only achieve 55% accuracy, a character-level CNN system achieved 63.7% accuracy, likely due to a large amount of puns that can be captured by a character-level model.

We are running a SemEval 2017 task using this dataset: SemEval-2017 Task 6. Everybody is welcome to participate!

SimiHawk at SemEval-2016 Task 1: A Deep Ensemble System for Semantic Textual Similarity

As part of the Text Machine's team, I participated in the Semantic Textual Similarity task at SemEval-2016. We built four systems: a small feature-based system that leverages word alignment and machine translation quality evaluation metrics, two end-to-end LSTM-based systems, and an ensemble system. Ultimately, the ensemble system was able to outperform the base systems substantially, obtaining a weighted Pearson correlation of 0.738, and placing 7th out of 115 participating systems.
[pdf] [poster]

GhostWriter: Using an LSTM for Automatic Rap Lyric Generation

Image from This paper demonstrates the effectiveness of a Long Short-Term Memory (LSTM) language model in our initial efforts to generate unconstrained rap lyrics. The goal of this model is to generate lyrics that are similar in style to that of a given rapper, but not identical to existing lyrics: this is the task of ghostwriting.

Knowledge Evolution Project

Knowledge Evolution Project The Knowledge Evolution project is an experiment in tracking and mapping the evolution of knowledge domains as well as the reputations and intellectual networks of the past. The project uses the history of the Library of Congress book acquisitions and classification, and the text of historical and contemporary editions of Encyclopedia Britannica and Wikipedia.


  • Potash, P., Romanov, A., & Rumshisky, A. (2016)
    #HashtagWars: Learning a Sense of Humor
    arXiv e-print [arXiv]
  • Potash, P., Romanov, A., & Rumshisky, A. (2016)
    Evaluating Creative Language Generation: The Case of Rap Lyric Ghostwriting
    arXiv e-print [arXiv]
  • Potash, P., Boag, W., Romanov, A., Ramanishka, V., & Rumshisky, A. (2016)
    SimiHawk at SemEval-2016 Task 1: A Deep Ensemble System for Semantic Textual Similarity.
    In Proceedings of SemEval [pdf]
  • Potash, P., Romanov, A., & Rumshisky, A. (2015)
    GhostWriter: Using an LSTM for Automatic Rap Lyric Generation.
    In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing [pdf]
  • Panchenko, A., Romanov, P., Morozova, O., Naets, H., Philippovich, A., Romanov, A., & Fairon, C. (2013).
    Serelex: Search and visualization of semantically related words.
    In European Conference on Information Retrieval [pdf] [demo]
  • Panchenko, A., Adeykin, S., Romanov, A., & Romanov, P. (2012).
    Extraction of Semantic Relations between Concepts with KNN Algorithms on Wikipedia.
    In CDUD 2012–Concept Discovery in Unstructured Data [pdf] [github]