Karen Hambardzumyan


pdf bib
WARP: Word-level Adversarial ReProgramming
Karen Hambardzumyan | Hrant Khachatrian | Jonathan May
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Transfer learning from pretrained language models recently became the dominant approach for solving many NLP tasks. A common approach to transfer learning for multiple tasks that maximize parameter sharing trains one or more task-specific layers on top of the language model. In this paper, we present an alternative approach based on adversarial reprogramming, which extends earlier work on automatic prompt generation. Adversarial reprogramming attempts to learn task-specific word embeddings that, when concatenated to the input text, instruct the language model to solve the specified task. Using up to 25K trainable parameters per task, this approach outperforms all existing methods with up to 25M trainable parameters on the public leaderboard of the GLUE benchmark. Our method, initialized with task-specific human-readable prompts, also works in a few-shot setting, outperforming GPT-3 on two SuperGLUE tasks with just 32 training samples.


pdf bib
YerevaNN’s Systems for WMT20 Biomedical Translation Task: The Effect of Fixing Misaligned Sentence Pairs
Karen Hambardzumyan | Hovhannes Tamoyan | Hrant Khachatrian
Proceedings of the Fifth Conference on Machine Translation

This report describes YerevaNN’s neural machine translation systems and data processing pipelines developed for WMT20 biomedical translation task. We provide systems for English-Russian and English-German language pairs. For the English-Russian pair, our submissions achieve the best BLEU scores, with enru direction outperforming the other systems by a significant margin. We explain most of the improvements by our heavy data preprocessing pipeline which attempts to fix poorly aligned sentences in the parallel data.


pdf bib
BioRelEx 1.0: Biological Relation Extraction Benchmark
Hrant Khachatrian | Lilit Nersisyan | Karen Hambardzumyan | Tigran Galstyan | Anna Hakobyan | Arsen Arakelyan | Andrey Rzhetsky | Aram Galstyan
Proceedings of the 18th BioNLP Workshop and Shared Task

Automatic extraction of relations and interactions between biological entities from scientific literature remains an extremely challenging problem in biomedical information extraction and natural language processing in general. One of the reasons for slow progress is the relative scarcity of standardized and publicly available benchmarks. In this paper we introduce BioRelEx, a new dataset of fully annotated sentences from biomedical literature that capture binding interactions between proteins and/or biomolecules. To foster reproducible research on the interaction extraction task, we define a precise and transparent evaluation process, tools for error analysis and significance tests. Finally, we conduct extensive experiments to evaluate several baselines, including SciIE, a recently introduced neural multi-task architecture that has demonstrated state-of-the-art performance on several tasks.


pdf bib
Towards JointUD: Part-of-speech Tagging and Lemmatization using Recurrent Neural Networks
Gor Arakelyan | Karen Hambardzumyan | Hrant Khachatrian
Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

This paper describes our submission to CoNLL UD Shared Task 2018. We have extended an LSTM-based neural network designed for sequence tagging to additionally generate character-level sequences. The network was jointly trained to produce lemmas, part-of-speech tags and morphological features. Sentence segmentation, tokenization and dependency parsing were handled by UDPipe 1.2 baseline. The results demonstrate the viability of the proposed multitask architecture, although its performance still remains far from state-of-the-art.