Verbs are sometimes omitted in Japanese sentences. It is necessary to recover omitted verbs for purposes of language understanding, machine translation, and conversational processing. This paper describes a practical way to recover omitted verbs by using surface expressions and examples. We experimented the resolution of verb ellipses by using this information, and obtained a recall rate of 73%...

Samuel A. Silver, Dwomoa Adu, Sanjay Agarwal, K.L. Gupta, Andrew J.P. Lewington, Neesh Pannu, Arvind Bagga, Rajasekara Chakravarthi and Ravindra L. Mehta; for the Acute Dialysis Quality Initiative (ADQI) Consensus Group Division of Nephrology, Stanford University School of Medicine, Palo Alto, California, USA; Division of Nephrology, University of Toronto, Toronto, Ontario, Canada; School of Me...

This paper describes the Question Answering for Machine Reading (QA4MRE) task at the 2012 Cross Language Evaluation Forum. In the main task, systems answered multiple-choice questions on documents concerned with four different topics. There were also two pilot tasks, Processing Modality and Negation for Machine Reading, and Machine Reading on Biomedical Texts about Alzheimer's disease. This pap...

Many shallow natural language understanding tasks use dependency trees to extract relations between content words. However, strict surface-structure dependency trees tend to follow the linguistic structure of sentences too closely and frequently fail to provide direct relations between content words. To mitigate this problem, the original Stanford Dependencies representation also defines two de...

Machine reading aims at extracting formal knowledge representations from text to enable programs to execute some performance task, for example, diagnosis or answering complex queries stated in a formal representation language. Information extraction techniques are a natural starting point for machine reading, however, since they focus on explicit surface features at the phrase and sentence leve...

We outline several challenges and opportunities for building physically situated systems that can interact in open, dynamic, and relatively unconstrained environments. We review a platform and recent progress on developing computational methods for situated, multiparty, open-world dialog, and highlight the value of representations of the physical surroundings and of harnessing the broader situa...

Cell-cell adhesion is mediated by interaction of a number of protein complexes residing on the cell plasma membranes. Disruption of these complexes affects structural and functional integrity of tissues. It has been hypothesized that a membrane protein tetraspanin CD82, a known metastasis suppressor, may play a role in regulating cell adhesion. Two proteins of interest (PG and Dsg2) have been f...

This paper addresses the role of reference resolution within language understanding software. To process the range of referring expressions found in natural language, we argue that reference resolution must be defined so as to completely rewrite the semantic representation of the referring expression and its referent.

This paper describes a theory of the representation and use of linguistic knowledge in a natural language understanding system. The representation system draws much of its insight from the linguistic theory of Fillmore el al. (1988). This models knowledge of language as a large collection of grammatical constructions, each a description of a linguistic regularity. I describe a representation la...

Event extraction is a very important task for research textual information. This task can be applied to various types of written text, e.g. news messages, blogs, manuscripts, and user reviews for products or services. In this paper, we report results about an experiment in correlating Event-based lived experience patterns obtained from machine reading, and ranking derived from open rating systems.