Igor Malioutov


pdf bib
Diversity-Aware Batch Active Learning for Dependency Parsing
Tianze Shi | Adrian Benton | Igor Malioutov | Ozan İrsoy
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

While the predictive performance of modern statistical dependency parsers relies heavily on the availability of expensive expert-annotated treebank data, not all annotations contribute equally to the training of the parsers. In this paper, we attempt to reduce the number of labeled examples needed to train a strong dependency parser using batch active learning (AL). In particular, we investigate whether enforcing diversity in the sampled batches, using determinantal point processes (DPPs), can improve over their diversity-agnostic counterparts. Simulation experiments on an English newswire corpus show that selecting diverse batches with DPPs is superior to strong selection strategies that do not enforce batch diversity, especially during the initial stages of the learning process. Additionally, our diversity-aware strategy is robust under a corpus duplication setting, where diversity-agnostic sampling strategies exhibit significant degradation.

pdf bib
Learning Syntax from Naturally-Occurring Bracketings
Tianze Shi | Ozan İrsoy | Igor Malioutov | Lillian Lee
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Naturally-occurring bracketings, such as answer fragments to natural language questions and hyperlinks on webpages, can reflect human syntactic intuition regarding phrasal boundaries. Their availability and approximate correspondence to syntax make them appealing as distant information sources to incorporate into unsupervised constituency parsing. But they are noisy and incomplete; to address this challenge, we develop a partial-brackets-aware structured ramp loss in learning. Experiments demonstrate that our distantly-supervised models trained on naturally-occurring bracketing data are more accurate in inducing syntactic structures than competing unsupervised systems. On the English WSJ corpus, our models achieve an unlabeled F1 score of 68.9 for constituency parsing.

pdf bib
Cross-Register Projection for Headline Part of Speech Tagging
Adrian Benton | Hanyang Li | Igor Malioutov
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Part of speech (POS) tagging is a familiar NLP task. State of the art taggers routinely achieve token-level accuracies of over 97% on news body text, evidence that the problem is well understood. However, the register of English news headlines, “headlinese”, is very different from the register of long-form text, causing POS tagging models to underperform on headlines. In this work, we automatically annotate news headlines with POS tags by projecting predicted tags from corresponding sentences in news bodies. We train a multi-domain POS tagger on both long-form and headline text and show that joint training on both registers improves over training on just one or naïvely concatenating training sets. We evaluate on a newly-annotated corpus of over 5,248 English news headlines from the Google sentence compression corpus, and show that our model yields a 23% relative error reduction per token and 19% per headline. In addition, we demonstrate that better headline POS tags can improve the performance of a syntax-based open information extraction system. We make POSH, the POS-tagged Headline corpus, available to encourage research in improved NLP models for news headlines.


pdf bib
Semantic Role Labeling as Syntactic Dependency Parsing
Tianze Shi | Igor Malioutov | Ozan Irsoy
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

We reduce the task of (span-based) PropBank-style semantic role labeling (SRL) to syntactic dependency parsing. Our approach is motivated by our empirical analysis that shows three common syntactic patterns account for over 98% of the SRL annotations for both English and Chinese data. Based on this observation, we present a conversion scheme that packs SRL annotations into dependency tree representations through joint labels that permit highly accurate recovery back to the original format. This representation allows us to train statistical dependency parsers to tackle SRL and achieve competitive performance with the current state of the art. Our findings show the promise of syntactic dependency trees in encoding semantic role relations within their syntactic domain of locality, and point to potential further integration of syntactic methods into semantic role labeling in the future.

pdf bib
NSTM: Real-Time Query-Driven News Overview Composition at Bloomberg
Joshua Bambrick | Minjie Xu | Andy Almonte | Igor Malioutov | Guim Perarnau | Vittorio Selo | Iat Chong Chan
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

Millions of news articles from hundreds of thousands of sources around the globe appear in news aggregators every day. Consuming such a volume of news presents an almost insurmountable challenge. For example, a reader searching on Bloomberg’s system for news about the U.K. would find 10,000 articles on a typical day. Apple Inc., the world’s most journalistically covered company, garners around 1,800 news articles a day. We realized that a new kind of summarization engine was needed, one that would condense large volumes of news into short, easy to absorb points. The system would filter out noise and duplicates to identify and summarize key news about companies, countries or markets. When given a user query, Bloomberg’s solution, Key News Themes (or NSTM), leverages state-of-the-art semantic clustering techniques and novel summarization methods to produce comprehensive, yet concise, digests to dramatically simplify the news consumption process. NSTM is available to hundreds of thousands of readers around the world and serves thousands of requests daily with sub-second latency. At ACL 2020, we will present a demo of NSTM.


pdf bib
Language Acquisition and Probabilistic Models: keeping it simple
Aline Villavicencio | Marco Idiart | Robert Berwick | Igor Malioutov
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)


pdf bib
Making Sense of Sound: Unsupervised Topic Segmentation over Acoustic Input
Igor Malioutov | Alex Park | Regina Barzilay | James Glass
Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics


pdf bib
Minimum Cut Model for Spoken Lecture Segmentation
Igor Malioutov | Regina Barzilay
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics