Articles

We present a noun phrase coreference sys- tem that extends the work of Soon et al. (2001) and, to our knowledge, pro- duces the best results to date on the MUC- 6 and MUC-7 coreference resolution data sets — F-measures of 70.4 and 63.4, re- spectively. Improvements arise from two …...

We consider the problem of parsing non-recursive context-free grammars, i.e., context-free grammars that generate finite languages. In natural language process- ing, this problem arises in several areas of application, including natural language generation, speech recognition and ma- chine translation. We present two tabu- lar algorithms for parsing of non-recursive context-free …...

The incremental algorithm introduced in (Dale and Reiter, 1995) for producing dis- tinguishing descriptions does not always generate a minimal description. In this paper, I show that when generalised to sets of individuals and disjunctive proper- ties, this approach might generate unnec- essarily long and ambiguous and/or epis- temically redundant …...

Previous approaches to pronominalization have largely been theoretical rather than applied in nature. Frequently, such meth- ods are based on Centering Theory, which deals with the resolution of anaphoric pro- nouns. But it is not clear that complex the- oretical mechanisms, while having satis- fying explanatory power, are necessary for …...

Real (i.e., working) machine translation may be presented both as the result of inevitable approximations over an ideal, theoretically motivated model based on the principle of semantic compositionality and as the re- sult of a set of necessary refinements over a very rudimentary word-for-word substitu- tional system. This paper explores …...

The paper describes the use of an assessed independent study project on machine translation evaluation as part of a final-year undergraduate course on machine assisted translation. The advantages and potential drawbacks of the use of such a component are outlined. The usefulness of studying MT evaluation is underlined, as it …...

This paper introduces the concept of controlled translation as the new working environment for the professional translator, and advances the idea that a new teaching scenario should emerge to cater for the needs of this controlled environment. In this context, we present how such scenario can be tailor-made to answer …...

An exploratory study has been initiated to determine the uptake of machine translation (MT) among UK freelance translators, to assess their perceptions and experience of it, and to identify their perceived MT training needs. preliminary analysis of findings suggestsA that, although the uptake of MT has, to date, been rather …...

The paper presents an approach to ellipsis resolution in a framework of scope under- specification (Underspecified Discourse Representation Theory). It is argued that the approach improves on previous pro- posals to integrate ellipsis resolution and scope underspecification (Crouch, 1995; Egg et al., 2001) in that application pro- cesses like anaphora …...

In Optimality-Theoretic Syntax, optimiza- tion with unrestricted expressive power on the side of the OT constraints is unde- cidable. This paper provides a proof for the decidability of optimization based on constraints expressed with reference to lo- cal subtrees (which is in the spirit of OT theory). The proof builds …...

In this paper we explore the power of surface text patterns for open-domain question answering systems. In order to obtain an optimal set of patterns, we have developed a method for learning such patterns automatically. A tagged corpus is built from the Internet in bootstrapping process by providing a few …...

We show that it is possible to learn the contexts for linguistic operations which map a semantic representation to a surface syntactic tree in sentence realization with high accuracy. We cast the problem of learning the contexts for the linguistic operations as classification tasks, and apply straightforward machine learning techniques, …...

Natural-Language Generation from flat semantics is an NP-complete problem. This makes it necessary to develop al- gorithms that run with reasonable effi- ciency in practice despite the high worst- case complexity. We show how to con- vert TAG generation problems into de- pendency parsing problems, which is use- ful because …...

We describe a speedup for training conditional maxi- mumentropymodels. Thealgorithmisasimplevari- ation on Generalized Iterative Scaling, but converges roughly an order of magnitude faster, depending on the number of constraints, and the way speed is mea- sured. Rather than attempting to train all model pa- rameters simultaneously, the algorithm trains them …...

This paper ties up some loose ends in finite-state Optimality Theory. First, it discusses how to perform comprehension un- der Optimality Theory grammars consisting of finite-state con- straints. Comprehension has not been much studied in OT; we show that unlike production, it does not always yield a regular set, making …...

This article reports on three cases of teaching translation or English as a foreign language using pre-editing tasks with a machine translation system. Trainee translators or English learners were asked to input a Chinese or English paragraph into an MT system, observe the irregularities in the output, and subsequently edit …...

This paper discusses the issue of suitability of software used for the teaching of Machine Translation. It considers requirements to such software, and describes a set of tools that have initially been created as developer environment of an APTrans MT system but can easily be included in the learning environment …...

This paper addresses the advantages of practical academic teaching of machine translation by implementations of „toy" systems. This is the result of experience from several semesters with different types of courses and different categories of students. In addition to describing two possible architectures for such educational toy systems, we will …...

This paper reports the results of research into the current state of affairs with respect to teaching MT/CAT tools in Greece. Although a variety of methods is employed, this research essentially takes the form of a survey. According to the data provided by respondents, the current status of MT/CAT tools, …...

The different factors that affect the level of teaching of machine translation, both as a formal courseware and in an informal manner to students doing developmental and research projects can be identified as the background of the student, the state of machine translation research in the country, the language pattern …...