We describe our entry to SemEval 2016 Task 10: Detecting Minimal Semantic Units and their Meanings. Our approach uses a discriminative first-order sequence model similar to Schneider and Smith (2015). The chief novelty in our approach is a factorization of the labels into multiword expression and supersense labels, and restricting first-order dependencies within these two parts. Our submitted m...

David Tannenbaum,a Craig R. Fox,b Gülden Ülkümen c aDavid Eccles School of Business, University of Utah, Salt Lake City, Utah 84112; bAnderson School of Management, University of California, Los Angeles, Los Angeles, California 90024; cMarshall School of Business, University of Southern California, Los Angeles, California 90089 Contact: [email protected] (DT); [email protected]...

This paper focuses on the task of inserting punctuation symbols into transcribed conversational speech texts, without relying on prosodic cues. We investigate limitations associated with previous methods, and propose a novel approach based on dynamic conditional random fields. Different from previous work, our proposed approach is designed to jointly perform both sentence boundary and sentence ...

We describe a probabilistic approach to content selection for meeting summarization. We use skipchain Conditional Random Fields (CRF) to model non-local pragmatic dependencies between paired utterances such as QUESTION-ANSWER that typically appear together in summaries, and show that these models outperform linear-chain CRFs and Bayesian models in the task. We also discuss different approaches ...

In this paper, we propose an automatic sentence classification model that can map sentences of a given biomedical abstract into set of pre-defined categories which are used for Evidence Based Medicine (EBM). In our model we explored the use of various lexical, structural and sequential features and worked with Conditional Random Fields (CRF) for classification. Results obtained with our propose...

Urban land cover is one of the fastest global growing land cover types which permanently alters land surface properties and atmospheric interactions, often initiating an urban heat island effect. Urbanisation comprises a number of land cover changes within metropolitan regions. However, these complexities have been somewhat neglected in temperature analysis studies of the urban heat island effe...

We consider the task of generating transliterated word forms. To allow for a wide range of interacting features, we use a conditional random field (CRF) sequence labeling model. We then present two innovations: a training objective that optimizes toward any of a set of possible correct labels (since more than one transliteration is often possible for a particular input), and a k-best reranking ...

Determining the semantic intent of web queries not only involves identifying their semantic class, which is a primary focus of previous works, but also understanding their semantic structure. In this work, we formally define the semantic structure of noun phrase queries as comprised of intent heads and intent modifiers. We present methods that automatically identify these constituents as well a...