COLING 2018 Papers

Capturing interactions among multiple predicate-argument structures (PASs) is a crucial issue in the task of analyzing PAS in Japanese. In this paper, we propose new Japanese PAS analysis models that integrate the label prediction information of arguments in multiple PASs by extending the input and last layers of a standard deep bidirectional recurrent neural network (bi-RNN) model. In these models, using the mechanisms of pooling and attention, we aim to directly capture the potential interactions among multiple PASs, without being disturbed by the word order and distance. Our experiments show that the proposed models improve the prediction accuracy specifically for cases where the predicate and argument are in an indirect dependency relation and achieve a new state of the art in the overall F_1 on a standard benchmark corpus.

We present a neural transition-based model that uses a simple set of edit actions (copy, delete, insert) for morphological transduction tasks such as inflection generation, lemmatization, and reinflection. In a large-scale evaluation on four datasets and dozens of languages, our approach consistently outperforms state-of-the-art systems on low and medium training-set sizes and is competitive in the high-resource setting. Learning to apply a generic copy action enables our approach to generalize quickly from a few data points. We successfully leverage minimum risk training to compensate for the weaknesses of MLE parameter learning and neutralize the negative effects of training a pipeline with a separate character aligner.

The use of machine learning for NLP generally requires resources for training. Tasks performed in a low-resource language usually rely on labeled data in another, typically resource-rich, language. However, there might not be enough labeled data even in a resource-rich language such as English. In such cases, one approach is to use a hand-crafted approach that utilizes only a small bilingual dictionary with minimal manual verification to create distantly supervised data. Another is to explore typical machine learning techniques, for example adversarial training of bilingual word representations. We find that in event-type detection task—the task to classify [parts of] documents into a fixed set of labels—they give about the same performance. We explore ways in which the two methods can be complementary and also see how to best utilize a limited budget for manual annotation to maximize performance gain.

Indigenous languages of the American continent are highly diverse. However, they have received little attention from the technological perspective. In this paper, we review the research, the digital resources and the available NLP systems that focus on these languages. We present the main challenges and research questions that arise when distant languages and low-resource scenarios are faced. We would like to encourage NLP research in linguistically rich and diverse areas like the Americas.

This paper describes an unsupervised model for morphological segmentation that exploits the notion of paradigms, which are sets of morphological categories (e.g., suffixes) that can be applied to a homogeneous set of words (e.g., nouns or verbs). Our algorithm identifies statistically reliable paradigms from the morphological segmentation result of a probabilistic model, and chooses reliable suffixes from them. The new suffixes can be fed back iteratively to improve the accuracy of the probabilistic model. Finally, the unreliable paradigms are subjected to pruning to eliminate unreliable morphological relations between words. The paradigm-based algorithm significantly improves segmentation accuracy. Our method achieves start-of-the-art results on experiments using the Morpho-Challenge data, including English, Turkish, and Finnish.

We propose a triad-based neural network system that generates affinity scores between entity mentions for coreference resolution. The system simultaneously accepts three mentions as input, taking mutual dependency and logical constraints of all three mentions into account, and thus makes more accurate predictions than the traditional pairwise approach. Depending on system choices, the affinity scores can be further used in clustering or mention ranking. Our experiments show that a standard hierarchical clustering using the scores produces state-of-art results with MUC and B 3 metrics on the English portion of CoNLL 2012 Shared Task. The model does not rely on many handcrafted features and is easy to train and use. The triads can also be easily extended to polyads of higher orders. To our knowledge, this is the first neural network system to model mutual dependency of more than two members at mention level.

This paper analyzes arguably the most challenging yet under-explored aspect of resolution tasks such as coreference resolution and entity linking, that is the resolution of plural mentions. Unlike singular mentions each of which represents one entity, plural mentions stand for multiple entities. To tackle this aspect, we take the character identification corpus from the SemEval 2018 shared task that consists of entity annotation for singular mentions, and expand it by adding annotation for plural mentions. We then introduce a novel coreference resolution algorithm that selectively creates clusters to handle both singular and plural mentions, and also a deep learning-based entity linking model that jointly handles both types of mentions through multi-task learning. Adjusted evaluation metrics are proposed for these tasks as well to handle the uniqueness of plural mentions. Our experiments show that the new coreference resolution and entity linking models significantly outperform traditional models designed only for singular mentions. To the best of our knowledge, this is the first time that plural mentions are thoroughly analyzed for these two resolution tasks.

Recent neural network methods for zero pronoun resolution explore multiple models for generating representation vectors for zero pronouns and their candidate antecedents. Typically, contextual information is utilized to encode the zero pronouns since they are simply gaps that contain no actual content. To better utilize contexts of the zero pronouns, we here introduce the self-attention mechanism for encoding zero pronouns. With the help of the multiple hops of attention, our model is able to focus on some informative parts of the associated texts and therefore produces an efficient way of encoding the zero pronouns. In addition, an attention-based recurrent neural network is proposed for encoding candidate antecedents by their contents. Experiment results are encouraging: our proposed attention-based model gains the best performance on the Chinese portion of the OntoNotes corpus, substantially surpasses existing Chinese zero pronoun resolution baseline systems.

Animacy is a necessary property for a referent to be an agent, and thus animacy detection is useful for a variety of natural language processing tasks, including word sense disambiguation, co-reference resolution, semantic role labeling, and others. Prior work treated animacy as a word-level property, and has developed statistical classifiers to classify words as either animate or inanimate. We discuss why this approach to the problem is ill-posed, and present a new approach based on classifying the animacy of co-reference chains. We show that simple voting approaches to inferring the animacy of a chain from its constituent words perform relatively poorly, and then present a hybrid system merging supervised machine learning (ML) and a small number of hand-built rules to compute the animacy of referring expressions and co-reference chains. This method achieves state of the art performance. The supervised ML component leverages features such as word embeddings over referring expressions, parts of speech, and grammatical and semantic roles. The rules take into consideration parts of speech and the hypernymy structure encoded in WordNet. The system achieves an F1 of 0.88 for classifying the animacy of referring expressions, which is comparable to state of the art results for classifying the animacy of words, and achieves an F1 of 0.75 for classifying the animacy of coreference chains themselves. We release our training and test dataset, which includes 142 texts (all narratives) comprising 156,154 words, 34,698 referring expressions, and 10,941 co-reference chains. We test the method on a subset of the OntoNotes dataset, showing using manual sampling that animacy classification is 90% +/- 2% accurate for coreference chains, and 92% +/- 1% for referring expressions. The data also contains 46 folktales, which present an interesting challenge because they often involve characters who are members of traditionally inanimate classes (e.g., stoves that walk, trees that talk). We show that our system is able to detect the animacy of these unusual referents with an F1 of 0.95.