Alexey Romanov

GhostWriter: Using an LSTM for Automatic Rap Lyric Generation

This paper demonstrates the effectiveness of a Long Short-Term Memory 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. Unlike previous work, which defines explicit templates for lyric generation, our model defines its own rhyme scheme, line length, and verse length. Our experiments show that a Long Short-Term Memory language model produces better “ghostwritten” lyrics than a baseline model.

Serelex: search and visualization of semantically related words

We present Serelex, a system that provides, given a query in English, a list of semantically related words. The terms are ranked according to an original semantic similarity measure learnt from a huge corpus. The system performs comparably to dictionary-based baselines, but does not require any semantic resource such as WordNet. Our study shows that users are completely satisfied with 70% of the query results.

Combining Network and Language Indicators for Tracking Conflict Intensity.

This work seeks to analyze the dynamics of social or political conflict as it develops over time, using a combination of network-based and language-based measures of conflict intensity derived from social media data. Specifically, we look at the random-walk based measure of graph polarization, text-based sentiment analysis, and the corresponding shift in word meaning and use by the opposing sides. We analyze the interplay of these views of conflict using the Ukraine-Russian Maidan crisis as a case study.

Temporal Information Extraction for Question Answering Using Syntactic Dependencies in an LSTM-based Architecture

In this paper, we propose to use a set of simple, uniform in architecture LSTM-based models to recover different kinds of temporal relations from text. Using the shortest dependency path between entities as input, the same architecture is used to extract intra-sentence, cross-sentence, and document creation time relations. A “double-checking” technique reverses entity pairs in classification, boosting the recall of positive cases and reducing misclassifications between opposite classes. An efficient pruning algorithm resolves conflicts globally. Evaluated on QA-TempEval (SemEval2015 Task 5), our proposed technique outperforms state-of-the-art methods by a large margin. We also conduct intrinsic evaluation and post state-of-the-art results on Timebank-Dense.

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

This paper describes the SimiHawk system submission from UMass Lowell for the core Semantic Textual Similarity task at SemEval2016. We built four systems: a small featurebased system that leverages word alignment and machine translation quality evaluation metrics, two end-to-end LSTM-based systems, and an ensemble system. The LSTMbased systems used either a simple LSTM architecture or a Tree-LSTM structure. We found that of the three base systems, the feature-based model obtained the best results, outperforming each LSTM-based model’s correlation by .06. 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. We find that the ensemble system’s success comes largely from its ability to form a consensus and eliminate complementary noise from its base systems’ predictions.