Chris Brew

Stochastic HPSG

In this paper we provide a probabilistic interpretation for typed feature structures very similar to those used by Pollard and Sag. We begin with a version of the interpretation which lacks a treatment of re-entrant feature structures, then provide an extended interpretation which allows them. We sketch algorithms allowing the numerical parameters of our probabilistic interpretations of HPSG to be estimated from corpora.

Using SGML as a Basis for Data-Intensive NLP

This paper describes the LT NSL system (McKelvie et al, 1996), an architecture for writing corpus processing tools. This system is then compared with two other systems which address similar issues, the GATE system (Cunningham et al, 1995) and the IMS Corpus Workbench (Christ, 1994). In particular we address the advantages and disadvantages of an SGML approach compared with a non-SGML database approach.

Using SGML as a Basis for Data-Intensive Natural Language Processing

This paper describes the LT NSL system (McKelvie et al., 1996), an architecture for writing corpus processing tools. This system is then compared with two other systems which address similar issues, the GATE system (Cunningham et al., 1995) and the IMS Corpus Workbench (Christ, 1994). In particular we address the advantages and disadvantages of an SGML approach compared with a non-sgml database approach.

PRIORITY UNION AND GENERALIZATION IN DISCOURSE GRAMMARS

We describe an implementation in Carpenters typed feature formalism, ALE, of a discourse grammar of the kind proposed by Scha, Polanyi, et al. We examine their method for resolving parallelism-dependent anaphora and show that there is a coherent feature-structural rendition of this type of grammar which uses the operations of priority union and generalization. We describe an augmentation of the ALE system to encompass these operations and we show that an appropriate choice of definition for priority union gives the desired multiple output for examples of VP-ellipsis which exhibit a strict/sloppy ambiguity.

Natural Language Question Answering and Analytics for Diverse and Interlinked Datasets

Previous systems for natural language questions over complex linked datasets require the user to enter a complete and well-formed question, and present the answers as raw lists of entities. Using a feature-based grammar with a full formal semantics, we have developed a system that is able to support rich autosuggest, and to deliver dynamically generated analytics for each result that it returns.

Classifying ReachOut posts with a radial basis function SVM

The ReachOut clinical psychology shared task challenge addresses the problem of providing an automatic triage for posts to a support forum for people with a history of mental health issues. Posts are classified into green, amber, red and crisis. The non-green categories correspond to increasing levels of urgency for some form of intervention. The Thomson Reuters submissions arose from an idea about self-training and ensemble learning. The available labeled training set is small (947 examples) and the class distribution unbalanced. It was therefore hoped to develop a method that would make use of the larger dataset of unlabeled posts provided by the organisers. This did not work, but the performance of a radial basis function SVM intended as a baseline was relatively good. Therefore, the report focuses on the latter, aiming to understand the reasons for its performance.

Automatic evaluation of computer generated text: a progress report on the TextEval project

We present results of experiments designed to assess the usefulness of a new technique for the evaluation of translation quality, comparing human rankings with automatic measures. The basis of our approach is the use of a standard set and the adoption of a statistical view of translation quality. This approach has the ability to provide evaluations which avoid dependence on any particular theory of translation, which are therefore potentially more objective than previous techniques. The work presented here was supported by the Science and Engineering and the Social and Economic Research Councils of Great Britain, and would not have been possible without the gracious assistance of Ian Mason of Heriot Watt University, Edinburgh.

Partial descriptions and systemic grammar

This paper examines the properties of featurebased partial descriptions built on top of Hallidays systemic networks. We show that the crucial operation of consistency checking for such descriptions is NP-complete, and therefore probably intractable, but proceed to develop algorithms which can sometimes alleviate the unpleasant consequences of this intractability.

Building and Querying an Enterprise Knowledge Graph

Information providers are faced with a critical challenge to process, retrieve and present information to their users in order to satisfy their complex information needs, because data has been increasing in an unprecedented manner, coming from diverse sources, and covering a variety of domains in heterogeneous formats. In this paper, we present Thomson Reuters’ effort in developing a family of services for building and querying an enterprise knowledge graph in order to address this challenge. We first acquire data from various sources via different approaches. Furthermore, we mine useful information from the data by adopting a variety of techniques, including Named Entity Recognition and Relation Extraction; such mined information is further integrated with existing structured data (e.g., via Entity Linking techniques) in order to obtain relatively comprehensive descriptions of the entities. By modeling the data as an RDF graph model, we enable easy data management and the embedding of rich semantics in our data. Finally, in order to facilitate the querying of this mined and integrated data, i.e., the knowledge graph, we propose TR Discover, a natural language interface that allows users to ask questions of our knowledge graph in their own words; such natural language questions are then translated into executable queries for answer retrieval. We evaluate our services, i.e., named entity recognition, relation extraction, entity linking and natural language interface, on real-world datasets, and demonstrate and discuss their practicability and limitations.