We use cookies to distinguish you from other users and to provide you with a better experience on our websites. Close this message to accept cookies or find out how to manage your cookie settings.
To save content items to your account,
please confirm that you agree to abide by our usage policies.
If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account.
Find out more about saving content to .
To save content items to your Kindle, first ensure no-reply@cambridge.org
is added to your Approved Personal Document E-mail List under your Personal Document Settings
on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part
of your Kindle email address below.
Find out more about saving to your Kindle.
Note you can select to save to either the @free.kindle.com or @kindle.com variations.
‘@free.kindle.com’ emails are free but can only be saved to your device when it is connected to wi-fi.
‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.
The last six months have seen a number of interesting announcements and products in the commercial language technology arena. Here are some that caught my eye, and which you might find interesting too.
In this paper we discuss a persistent problem arising from polysemy: namely the difficulty of finding consistent criteria for making fine-grained sense distinctions, either manually or automatically. We investigate sources of human annotator disagreements stemming from the tagging for the English Verb Lexical Sample Task in the SENSEVAL-2 exercise in automatic Word Sense Disambiguation. We also examine errors made by a high-performing maximum entropy Word Sense Disambiguation system we developed. Both sets of errors are at least partially reconciled by a more coarse-grained view of the senses, and we present the groupings we use for quantitative coarse-grained evaluation as well as the process by which they were created. We compare the system's performance with our human annotator performance in light of both fine-grained and coarse-grained sense distinctions and show that well-defined sense groups can be of value in improving word sense disambiguation by both humans and machines.
We address the problem of improving the efficiency of natural language text input under degraded conditions (for instance, on mobile computing devices or by disabled users), by taking advantage of the informational redundancy in natural language. Previous approaches to this problem have been based on the idea of prediction of the text, but these require the user to take overt action to verify or select the system's predictions. We propose taking advantage of the duality between prediction and compression. We allow the user to enter text in compressed form, in particular, using a simple stipulated abbreviation method that reduces characters by 26.4%, yet is simple enough that it can be learned easily and generated relatively fluently. We decode the abbreviated text using a statistical generative model of abbreviation, with a residual word error rate of 3.3%. The chief component of this model is an n-gram language model. Because the system's operation is completely independent from the user's, the overhead from cognitive task switching and attending to the system's actions online is eliminated, opening up the possibility that the compression-based method can achieve text input efficiency improvements where the prediction-based methods have not. We report the results of a user study evaluating this method.
We address the problem of extracting bilingual chunk pairs from parallel text to create training sets for statistical machine translation. We formulate the problem in terms of a stochastic generative process over text translation pairs, and derive two different alignment procedures based on the underlying alignment model. The first procedure is a now-standard dynamic programming alignment model which we use to generate an initial coarse alignment of the parallel text. The second procedure is a divisive clustering parallel text alignment procedure which we use to refine the first-pass alignments. This latter procedure is novel in that it permits the segmentation of the parallel text into sub-sentence units which are allowed to be reordered to improve the chunk alignment. The quality of chunk pairs are measured by the performance of machine translation systems trained from them. We show practical benefits of divisive clustering as well as how system performance can be improved by exploiting portions of the parallel text that otherwise would have to be discarded. We also show that chunk alignment as a first step in word alignment can significantly reduce word alignment error rate.
We present the source authoring facilities of a natural language generation system that produces personalised descriptions of objects in multiple natural languages starting from language-independent symbolic information in ontologies and databases as well as pieces of canned text. The system has been tested in applications ranging from museum exhibitions to presentations of computer equipment for sale. We discuss the architecture of the overall system, the resources that the authors manipulate, the functionality of the authoring facilities, the system's personalisation mechanisms, and how they relate to source authoring. A usability evaluation of the authoring facilities is also presented, followed by more recent work on reusing information extracted from existing databases and documents, and supporting the OWL ontology specification language.
We compare the word sense disambiguation systems submitted for the English-all-words task in SENSEVAL-2. We give several performance measures for the systems, and analyze correlations between system performance and word features. A decision tree learning algorithm is employed to discover the situations in which systems perform particularly well, and the resulting decision tree is examined. We investigate using a decision tree based on the SENSEVAL systems to (i) filter out senses unlikely to be correct, and to (ii) combine WSD systems. Some combinations created in this way outperform the best SENSEVAL system.
In this paper we focus on a specific search-related query expansion topic, namely search on Danish compounds and expansion to some of their synonymous phrases. Compounds constitute a specific issue in search, in particular in languages where they are written in one word, as is the case for Danish and the other Scandinavian languages. For such languages, expansion of the query compound into separate lemmas is a way of finding the often frequent alternative synonymous phrases in which the content of a compound can also be expressed. However, it is crucial to note that the number of irrelevant hits is generally very high when using this expansion strategy. The aim of this paper is therefore to examine how we can obtain better search results on split compounds, partly by looking at the internal structure of the original compound, partly by analyzing the context in which the split compound occurs. In this context, we pursue two hypotheses: (1) that some categories of compounds are more likely to have synonymous ‘split’ counterparts than others; and (2) that search results where both the search words (obtained by splitting the compound) occur in the same noun phrase, are more likely to contain a synonymous phrase to the original compound query. The search results from 410 enhanced compound queries are used as a test bed for our experiments. On these search results, we perform a shallow linguistic analysis and introduce a new, linguistically based threshold for retrieved hits. The results obtained by using this strategy demonstrate that compound splitting combined with a shallow linguistic analysis focusing on the argument structure of the compound head as well as on the recognition of NPs, can improve search by substantially bringing down the number of irrelevant hits.
Science and natural philosophy largely abandoned ideas about parallel worlds of mind and matter in the years following Descartes and his dualistic philosophy. By the twentieth century, most of science exhibited an unhesitant materialistic metaphysics. The present investigation occasions an opportunity to reexamine ideas about materialism.
What is materialism?
The standard conception of materialism is the thesis that all events in the world consist of ordinary physical matter, energy, and other physical properties, denying the existence or causal influence of other things. It does not deny the possibility of using nonphysical properties to characterize physical things; civilization's use of numbers to quantify physical dimensions would suffer greatly were this so. But it does deny that these nonphysical characterizations play any physical role.
One should note that materialism exhibits an open-ended character. When philosophers first bruited materialism, it referred to everything being the tangible, visible stuff of the world. Eventually this conception required enlargement to include the invisible, intangible stuff—energy, electromagnetic fields, spin, neutrinos—that later physics developed as physical entities or properties, even though some of these are far removed from the direct experience characteristic of the original conceptions of physical materials.
Mechanics has enjoyed some four centuries of sustained development without producing results in psychology or economics. The mental sciences have enjoyed a couple centuries of sustained development without requiring mechanical intervention. To use the standard economic argument, if there was a connection worth pursuing, would not one have already been made?
In fact, people have made numerous attempts at connecting mechanics and mind. Although those attempts at establishing such connections have failed, there are identifiable changes in scientific circumstances that explain why a mechanical approach to psychology and economics should prove more fruitful now.
To see the reasons for the lack of successful connections in the past, this chapter examines some of the difficulties prevailing at earlier times and how they have undercut historical attempts at connecting physics and psychology. Readers wishing to proceed to mechanics proper can skip ahead to Chapter 4 or Chapter 5 without loss of understanding.
Impediments to understanding
Why have the mental sciences lagged the physical so markedly? The answer could involve social factors, such as the stimulus to physical discovery made by war and trade, but one might expect that discoveries about the mind might benefit these activities to some extent as well, as was assumed by Joseph Göbbels and is known by advertising agencies today.
Mining data logged by intelligent tutoring systems has the potential to discover information of value to students, teachers, authors, developers, researchers, and the tutors themselves – information that could make education dramatically more efficient, effective, and responsive to individual needs. We factor this discovery process into tactics to modify tutors, map heterogeneous event streams into tabular data sets, and mine them. This model and the tactics identified mark out a roadmap for the emerging area of tutorial data mining, and may provide a useful vocabulary and framework for characterizing past, current, and future work in this area. We illustrate this framework using experiments that tested interventions by an automated reading tutor to help children decode words and comprehend stories.
As was noted earlier, the traditional conception of what we call mechanical computation or computation by machine relies on a purely kinematical conception of mechanics. It entirely omits any notion of force and focuses attention only on abstract states and motion between them. In this it follows a trend in mechanical formalism that moved away from considering forces and spatial motions to considering mainly Hamiltonian motion through abstract spaces, with no mention of either the central notion of force or the key notion of mass (cf. Hermann 1990, Sussman & Wisdom 2001).
This disconnect between mechanical computation and mechanics comes closest to being bridged in the related field of information theory, in which some authors have viewed information content as a type of mass measure (Manthey & Moret 1983) and have produced formal relations between information content and thermostatic theories of entropy (Chaitin 1975). These ropes tossed across the gap lack tether to the notion of force and still leave the crossing perilous.
Let us now reconsider the notion of computation from the mechanical point of view, to treat “mechanizability”—viewed in terms of machines—as mechanizability—viewed in terms of mechanics. We seek to understand the notion of effectiveness as involving not just abstract kinematics but also those fundamental concepts that distinguish mechanics from geometry, especially the concepts of rate of motion limited by limits on force and bounds on the rate of work.
Discussions in previous chapters have touched on these ideas already.