Ted Briscoe

The Second Release of the RASP System

We describe the new release of the RASP (robust accurate statistical parsing) system, designed for syntactic annotation of free text. The new version includes a revised and more semantically-motivated output representation, an enhanced grammar and part-of-speech tagger lexicon, and a more flexible and semi-supervised training method for the structural parse ranking model. We evaluate the released version on the WSJ using a relational evaluation scheme, and describe how the new release allows users to enhance performance using (in-domain) lexical information.

Evaluating the Accuracy of an Unlexicalized Statistical Parser on the PARC DepBank

We evaluate the accuracy of an unlexicalized statistical parser, trained on 4K treebanked sentences from balanced data and tested on the PARC DepBank. We demonstrate that a parser which is competitive in accuracy (without sacrificing processing speed) can be quickly tuned without reliance on large in-domain manually-constructed treebanks. This makes it more practical to use statistical parsers in applications that need access to aspects of predicate-argument structure. The comparison of systems using DepBank is not straightforward, so we extend and validate DepBank and highlight a number of representation and scoring issues for relational evaluation schemes.

High precision extraction of grammatical relations

A parsing system returning analyses in the form of sets of grammatical relations can obtain high precision if it hypothesises a particular grammatical relation only when it is certain that the relation is correct. We operationalise this technique -in a statistical parser using a manually-developed wide-coverage grammar of English - by only returning relations that form part of all analyses licensed by the grammar. We observe an increase in precision from 75% to over 90% (at the cost of a reduction in recall) on a test corpus of naturally-occurring text.

Lexical Issues in Natural Language Processing

In this paper, I will briefly describe the role of the lexicon in natural language processing (NLP) applications and will go on to discuss a number of issues in lexical research and in the design and construction of lexicons for practical NLP applications. I will survey relevant research in Europe, America and Japan; however, in a paper of this length it is not possible to consider every instance of a particular approach, so neither the text nor references should be taken to be exhaustive.

Biomedical Event Extraction without Training Data

We describe our system for the BioNLP 2009 event detection task. It is designed to be as domain-independent and unsupervised as possible. Nevertheless, the precisions achieved for single theme event classes range from 75% to 92%, while maintaining reasonable recall. The overall F-scores achieved were 36.44% and 30.80% on the development and the test sets respectively.

Looking for Hyponyms in Vector Space

The task of detecting and generating hyponyms is at the core of semantic understanding of language, and has numerous practical applications. We investigate how neural network embeddings perform on this task, compared to dependency-based vector space models, and evaluate a range of similarity measures on hyponym generation. A new asymmetric similarity measure and a combination approach are described, both of which significantly improve precision. We release three new datasets of lexical vector representations trained on the BNC and our evaluation dataset for hyponym generation.

Efficient Extraction of Grammatical Relations

We present a novel approach for applying the Inside-Outside Algorithm to a packed parse forest produced by a unification-based parser. The approach allows a node in the forest to be assigned multiple inside and outside probabilities, enabling a set of weighted GRs to be computed directly from the forest. The approach improves on previous work which either loses efficiency by unpacking the parse forest before extracting weighted GRs, or places extra constraints on which nodes can be packed, leading to less compact forests. Our experiments demonstrate substantial increases in parser accuracy and throughput for weighted GR output.

Co-evolution of language and of the language acquisition device

A new account of parameter setting during grammatical acquisition is presented in terms of Generalized Categorial Grammar embedded in a default inheritance hierarchy, providing a natural partial ordering on the setting of parameters. Experiments show that several experimentally effective learners can be defined in this framework. Evolutionary simulations suggest that a learner with default initial settings for parameters will emerge, provided that learning is memory limited and the environment of linguistic adaptation contains an appropriate language.

LEXICAL ACCESS IN CONNECTED SPEECH RECOGNITION

This paper addresses two issues concerning lexical access in connected speech recognition: 1) the nature of the pre-lexical representation used to initiate lexical lookup 2) the points at which lexical look-up is triggered off this representation. The results of an experiment are reported which was designed to evaluate a number of access strategies proposed in the literature in conjunction with several plausible pre-lexical representations of the speech input. The experiment also extends previous work by utilising a dictionary database containing a realistic rather than illustrative English vocabulary.

LINGUISTIC ADAPTATIONS FOR RESOLVING AMBIGUITY

We motivate a model of human parsing and ambiguity resolution on the basis of psycholinguistic and typological data. Analysis of spoken and written corpora suggests that ambiguity is a factor in the choice of relativization strategy for English and supports the model’s predictions. Within an evolutionary account of language, we predict that languages will adapt over time so that prosodic and syntactic systems are organised to minimize processing cost according to this model.