We take a novel approach to zero pronoun resolution in Chinese: our model explicitly tracks the flow of focus in a discourse. Our approach, which generalizes to deictic references, is not reliant on the presence of overt noun phrase antecedents to resolve to, and allows us to address the large percentage of “non-anaphoric” pronouns filtered out in other approaches. We furthermore train our mode...

Existing probabilistic scanners and parsers impose hard constraints on the way lexical and syntactic ambiguities can be resolved. Furthermore, traditional grammar-based parsing tools are limited in the mechanisms they allow for taking context into account. In this paper, we propose a model-driven tool that allows for statistical language models with arbitrary probability estimators. Our work on...

While unsupervised anaphoric zero pronoun (AZP) resolvers have recently been shown to rival their supervised counterparts in performance, it is relatively difficult to scale them up to reach the next level of performance due to the large amount of feature engineering efforts involved and their ineffectiveness in exploiting lexical features. To address these weaknesses, we propose a supervised a...

We present an approach for answering questions that span multiple sentences and exhibit sophisticated cross-sentence anaphoric phenomena, evaluating on a rich source of such questions – the math portion of the Scholastic Aptitude Test (SAT). By using a tree transducer cascade as its basic architecture, our system (called EUCLID) propagates uncertainty from multiple sources (e.g. coreference res...

One of the first steps towards understanding natural multimodal language is aligning gesture and speech, so that the appropriate gestures ground referential pronouns in the speech. This paper presents a novel technique for gesture-speech alignment, inspired by saliencebased approaches to anaphoric pronoun resolution. We use a hybrid between data-driven and knowledge-based mtehods: the basic str...

Majority of present machine translation systems do not address the retaining of text coherency, they translate just isolated sentences. On the other hand, the authors of anaphora resolvers rarely integrate these tools into more complex scenarios, e.g. the task of machine translation. We propose the ways how machine translation systems can utilize the knowledge of anaphoric relations both in the...

Only a year ago, all state-of-the-art coreference resolvers were using an extensive amount of surface features. Recently, there was a paradigm shift towards using word embeddings and deep neural networks, where the use of surface features is very limited. In this paper, we show that a simple SVM model with surface features outperforms more complex neural models for detecting anaphoric mentions....

This article investigates how speakers and hearers who are referentially clear are designated anaphorically in Mandarin face-to-face conversation. Although anaphoric production involves both structural and functional factors, it is proposed that functional demands, which include social needs and pragmatic requirements, are the crucial determinants that decide the surface manifestations of anaph...

There are two major groups of analyses in the literature on English past tense; existential semantics with domain restriction, and pronominal (i.e. anaphoric) analysis. In this paper, I discuss a group data difficult for both these analyses: obligatory use some contexts without any salient antecedent, such as asking Who built church when pointing at (Kratzer 1998). The analysis predicts that te...