@InProceedings{frermann-klementiev:ACL2019,
    author    = {Frermann, Lea  and  Klementiev, Alexandre},
    title     = {Inducing Document Structure for Aspect-based Summarization},
    booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational
                 Linguistics},
    month     = {July},
    year      = {2019},
    address   = {Florence, Italy},
    publisher = {Association for Computational Linguistics}
}
    

Automatic summarization is typically treated as a 1-to-1 mapping from document to summary. Documents such as news articles, however, are structured and often cover multiple topics or aspects; and readers may be interested in only some of them. We tackle the task of aspect-based summarization, where, given a document and a target aspect, our models generate a summary centered around the aspect. We induce latent document structure jointly with an abstractive summarization objective, and train our models in a scalable synthetic setup. In addition to improvements in summarization over topic-agnostic baselines, we demonstrate the benefit of the learnt document structure: we show that our models (a) learn to accurately segment documents by aspect; (b) can leverage the structure to produce both abstractive and extractive aspect-based summaries; and (c) that structure is particularly advantageous for summarizing long documents. All results transfer from synthetic training documents to natural news articles from CNN/Daily Mail and RCV1.

@InProceedings{titov-klementiev:ACL2012,
    author    = {Titov, Ivan  and  Klementiev, Alexandre},
    title     = {Crosslingual Induction of Semantic Roles},
    booktitle = {Proceedings of the 50th Annual Meeting of the Association for Computational
                 Linguistics},
    month     = {July},
    year      = {2012},
    address   = {Jeju Island, South Korea},
    publisher = {Association for Computational Linguistics}
}
    

We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervised induction of semantic roles from sentences annotated with automatically-predicted syntactic dependency representations and use a state-of-the-art generative Bayesian non-parametric model. At inference time, instead of only seeking the model which explains the monolingual data available for each language, we regularize the objective by introducing a soft constraint penalizing for disagreement in argument labeling on aligned sentences. We propose a simple approximate learning algorithm for our set-up which results in efficient inference. When applied to multilingual parallel data, our method obtains a substantial improvement over the model trained without using the agreement signal, when both are tested on non-parallel sentences.

@InProceedings{klementiev-etal:EACL2012,
    author    = {Klementiev, Alexandre and Irvine, Ann and Callison-Burch, Chris and Yarowsky, David},
    title     = {Toward Statistical Machine Translation without Parallel Corpora},
    booktitle = {Proceedings of the 13th Conference of the European Chapter of the Association for
                 Computational Linguistics},
    month     = {April},
    year      = {2012},
    address   = {Avignon, France}
    publisher = {Association for Computational Linguistics},
}
    

We estimate the parameters of a phrasebased statistical machine translation system from monolingual corpora instead of a bilingual parallel corpus. We extend existing research on bilingual lexicon induction to estimate both lexical and phrasal translation probabilities for MT-scale phrasetables. We propose a novel algorithm to estimate reordering probabilities from monolingual data. We report translation results for an end-to-end translation system using these monolingual features alone. Our method only requires monolingual corpora in source and target languages, a small bilingual dictionary, and a small bitext for tuning feature weights. In this paper, we examine an idealization where a phrase-table is given. We examine the degradation in translation performance when bilingually estimated translation probabilities are removed and show that 80%+ of the loss can be recovered with monolingually estimated features alone. We further show that our monolingual features add 1.5 BLEU points when combined with standard bilingually estimated phrase table features.

@InProceedings{titov-klementiev:EACL2012,
    author    = {Titov, Ivan  and  Klementiev, Alexandre},
    title     = {A Bayesian Approach to Unsupervised Semantic Role Induction},
    booktitle = {Proceedings of the 13th Conference of the European Chapter of the Association for
                 Computational Linguistics},
    month     = {April},
    year      = {2012},
    address   = {Avignon, France}
    publisher = {Association for Computational Linguistics},
}   
    

We introduce two Bayesian models for unsupervised semantic role labeling (SRL) task. The models treat SRL as clustering of syntactic signatures of arguments with clusters corresponding to semantic roles. The first model induces these clusterings independently for each predicate, exploiting the Chinese Restaurant Process (CRP) as a prior. In a more refined hierarchical model, we inject the intuition that the clusterings are similar across different predicates, even though they are not necessarily identical. This intuition is encoded as a distance-dependent CRP with a distance between two syntactic signatures indicating how likely they are to correspond to a single semantic role. These distances are automatically induced within the model and shared across predicates. Both models achieve state-of-the-art results when evaluated on PropBank, with the coupled model consistently outperforming the factored counterpart in all experimental set-ups.

@InProceedings{klementiev-etal:COLING2012,
    author    = {Klementiev, Alexandre and Titov, Ivan and Bhattarai, Binod},
    title     = {Inducing Crosslingual Distributed Representations of Words},
    booktitle = {Proceedings of the International Conference on Computational Linguistics
                 (COLING)},
    month     = {December},
    year      = {2012},
    address   = {Bombay, India}
}
    

Distributed representations of words have proven extremely useful in numerous natural language processing tasks. Their appeal is that they can help alleviate data sparsity problems common to supervised learning. Methods for inducing these representations require only unlabeled language data, which are plentiful for many natural languages. In this work, we induce distributed representations for a pair of languages jointly. We treat it as a multitask learning problem where each task corresponds to a single word, and task relatedness is derived from co-occurrence statistics in bilingual parallel data. These representations can be used for a number of crosslingual learning tasks, where a learner can be trained on annotations present in one language and applied to test data in another. We show that our representations are informative by using them for crosslingual document classification, where classifiers trained on these representations substantially outperform strong baselines (e.g. machine translation) when applied to a new language.

@InProceedings{titov-klementiev:COLING2012,
    author    = {Titov, Ivan  and  Klementiev, Alexandre},
    title     = {Semi-Supervised Semantic Role Labeling: Approaching from an Unsupervised
                 Perspective},
    booktitle = {Proceedings of the International Conference on Computational Linguistics
                 (COLING)},
    month     = {December},
    year      = {2012},
    address   = {Bombay, India}
}
    

Reducing the reliance of semantic role labeling (SRL) methods on human-annotated data has become an active area of research. However, the prior work has largely focused on either (1) looking into ways to improve supervised SRL systems by producing surrogate annotated data and reducing sparsity of lexical features or (2) considering completely unsupervised semantic role induction settings. In this work, we aim to link these two veins of research by studying how unsupervised techniques can be improved by exploiting small amounts of labeled data. We extend a state-of-the-art Bayesian model for unsupervised semantic role induction to better accommodate for annotated sentences. Our semi-supervised method outperforms a strong supervised baseline when only a small amount of labeled data is available.

@InProceedings{modi-etal:NAACL2012,
    author    = {Modi, Ashutosh and Titov, Ivan  and  Klementiev, Alexandre},
    title     = {Unsupervised Induction of Frame-Semantic Representations},
    booktitle = {Proceedings of the NAACL-HLT 2012 Workshop on Inducing Linguistic Structure},
    month     = {June},
    year      = {2012},
    address   = {Montreal, Canada}
}
    

The frame-semantic parsing task is challenging for supervised techniques, even for those few languages where relatively large amounts of labeled data are available. In this preliminary work, we consider unsupervised induction of frame-semantic representations. An existing state-of-the-art Bayesian model for PropBank-style unsupervised semantic role induction (Titov and Klementiev, EACL 2012) is extended to jointly induce semantic frames and their roles. We evaluate the model performance both quantitatively and qualitatively by comparing the induced representation against FrameNet annotations.

@InProceedings{klementiev-et-al:DL2012,
    author    = {Klementiev, Alexander and Titov, Ivan and Bhattarai, Binod},
    title     = {Crosslingual Distributed Representations of Words},
    booktitle = {NIPS 2012 Workshop on Deep Learning},
    month     = {December},
    year      = {2012},
    address   = {Tahoe Lake, USA}
}
    

@InProceedings{titov-klementiev:ACL2011,
    author    = {Titov, Ivan  and  Klementiev, Alexandre},
    title     = {A Bayesian Model for Unsupervised Semantic Parsing},
    booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational
                 Linguistics},
    month     = {June},
    year      = {2011},
    address   = {Portland, Oregon, USA},
    publisher = {Association for Computational Linguistics},
    pages     = {1445--1455},
    url       = {http://www.aclweb.org/anthology/P11-1145}
}
    

We propose a non-parametric Bayesian model for unsupervised semantic parsing. Following Poon and Domingos (2009), we consider a semantic parsing setting where the goal is to (1) decompose the syntactic dependency tree of a sentence into fragments, (2) assign each of these fragments to a cluster of semantically equivalent syntactic structures, and (3) predict predicate-argument relations between the fragments. We use hierarchical Pitman-Yor processes to model statistical dependencies between meaning representations of predicates and those of their arguments, as well as the clusters of their syntactic realizations. We develop a modification of the Metropolis-Hastings split-merge sampler, resulting in an efficient inference algorithm for the model. The method is experimentally evaluated by using the induced semantic representation for the question answering task in the biomedical domain.

@InProceedings{irvine-et-al:AMTA2010,
    author    = {Irvine, Ann and Callison-Burch, Chris and Klementiev, Alexandre},
    title     = {Transliterating From All Languages},
    booktitle = {Proceedings of the 9th Conference of the Association for Machine Translation
                in the Americas},
    month     = {October},
    year      = {2010},
    address   = {Denver, Colorado, USA},
    url = {http://www.mt-archive.info/AMTA-2010-Irvine.pdf}
}
    

Much of the previous work on transliteration has depended on resources and attributes specific to particular language pairs. In this work, rather than focus on a single language pair, we create robust models for transliterating from all languages in a large, diverse set to English. We create training data for 150 languages by mining name pairs from Wikipedia. We train 13 systems and analyze the effects of the amount of training data on transliteration performance. We also present an analysis of the types of errors that the systems make. Our analyses are particularly valuable for building machine translation systems for low resource languages, where creating and integrating a transliteration module for a language with few NLP resources may provide substantial gains in translation performance.