Mention pair models that predict whether or not two mentions are coreferent have historically been very effective for coreference resolution, but do not make use of entity-level i...
We propose an event-driven model for headline generation. Given an input document, the system identifies a key event chain by extracting a set of structural events that describe ...
Contrasting meaning is a basic aspect of semantics. Recent word-embedding models based on distributional semantics hypothesis are known to be weak for modeling lexical contrast. W...
Framing is a sophisticated form of discourse in which the speaker tries to induce a cognitive bias through consistent linkage between a topic and a specific context (frame). We b...
Precisely evaluating the quality of a translation against human references is a challenging task due to the flexible word ordering of a sentence and the existence of a large numb...
Understanding open-domain text is one of the primary challenges in NLP. Machine comprehension evaluates the system’s ability to understand text through a series of question-answ...
Mrinmaya Sachan, Kumar Dubey, Eric P. Xing, Matthe...
Languages using Chinese characters are mostly processed at word level. Inspired by recent success of deep learning, we delve deeper to character and radical levels for Chinese lan...
Coverage maximization with bigram concepts is a state-of-the-art approach to unsupervised extractive summarization. It has been argued that such concepts are adequate and, in cont...
This paper considers the problem of embedding Knowledge Graphs (KGs) consisting of entities and relations into lowdimensional vector spaces. Most of the existing methods perform t...
In this paper, we apply the concept of pretraining to hidden-unit conditional random fields (HUCRFs) to enable learning on unlabeled data. We present a simple yet effective pre-t...