Nelleke Oostdijk

The design of the Spoken Dutch Corpus

In June 1998 the Spoken Dutch Corpus project was started, a five-year project aimed at the compilation and annotation of a 10-million-word corpus of contemporary standard Dutch as spoken in the Netherlands and Flanders. This paper describes the corpus as it is currently under construction. It discusses more specifically the various considerations that have guided its design.

On temporal aspects of turn taking in conversational dialogues

Abstract In this short communication we show how shallow annotations in large speech corpora can be used to derive data about the temporal aspects of turn taking. Within the limitations of such a speech corpus, we show that the average durations of between-turn pauses made by speakers in a dyad are statistically related, and our data suggest the existence of gender effects in the temporal aspects of turn taking. Also, clear differences in turn taking behaviour between face-to-face and telephone dialogues can be detected using shallow analyses. We discuss the most important limitations imposed by the shallowness of the annotations in large corpora, and the possibility for enriching those annotations in a semi-automatic iterative manner.

Durational Aspects of Turn-Taking in Spontaneous Face-to-Face and Telephone Dialogues

On the basis of two-speaker spontaneous conversations, it is shown that the distributions of both pauses and speech-overlaps of telephone and face-to-face dialogues have different statistical properties. Pauses in a face-to-face dialogue last up to 4 times longer than pauses in telephone conversations in functionally comparable conditions. There is a high correlation (0.88 or larger) between the average pause duration for the two speakers across face-to-face dialogues and telephone dialogues. The data provided form a first quantitative analysis of the complex turn-taking mechanism evidenced in the dialogues available in the 9-million-word Spoken Dutch Corpus.

Evaluating discourse-based answer extraction for why -question answering

30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2007)

The Construction of a 500-Million-Word Reference Corpus of Contemporary Written Dutch

The construction of a large and richly annotated corpus of written Dutch was identified as one of the priorities of the STEVIN programme. Such a corpus, sampling texts from conventional and new media, is invaluable for scientific research and application development. The present chapter describes how in two consecutive STEVIN-funded projects, viz. D-Coi and SoNaR, the Dutch reference corpus was developed. The construction of the corpus has been guided by (inter)national standards and best practices. At the same time through the achievements and the experiences gained in the D-Coi and SoNaR projects, a contribution was made to their further advancement and dissemination.

What is not in the bag of words for why-qa?

While developing an approach to why-QA, we extended a passage retrieval system that uses off-the-shelf retrieval technology with a re-ranking step incorporating structural information. We get significantly higher scores in terms of MRR150 (from 0.25 to 0.34) and success10. The 23 improvement that we reach in terms of MRR is comparable to the improvement reached on different QA tasks by other researchers in the field, although our re-ranking approach is based on relatively lightweight overlap measures incorporating syntactic constituents, cue words, and document structure.

Finite Comment Clauses in Dutch: A Corpus-based approach

The present paper presents the results of a corpus-based study into the form and distribution of finite comment clauses in Dutch. More specifically, it was investigated where in the sentence such clauses can occur. For the analysis of the data, a topological descriptive model was used. While in the literature an extraction analysis has been suggested in order to account for finite comment clauses in English and German, our findings lead us to challenge this type of analysis and argue that a parenthetical analysis is to be preferred. 1 Thanks are due to Antal van den Bosch and Hans van Halteren for their help in tagging the corpus and to Toni Rietveld for his statistical advice.

N-Gram-Based recognition of threatening tweets

In this paper, we investigate to what degree it is possible to recognize threats in Dutch tweets. We attempt threat recognition on the basis of only the single tweet (without further context) and using only very simple recognition features, namely n-grams. We present two different methods of n-gram-based recognition, one based on manually constructed n-gram patterns and the other on machine learned patterns. Our evaluation is not restricted to precision and recall scores, but also looks into the difference in yield of the two methods, considering either combination or means that may help refine both methods individually.

Shallow parsing for recognizing threats in Dutch tweets

In this paper, we investigate the recognition of threats in Dutch tweets. As tweets often display irregular grammatical form and deviant orthography, analysis by standard means is problematic. Therefore, we have implemented a new shallow parsing mechanism which is driven by handcrafted rules. Experimental results are encouraging, with an F-measure of about 40% on a random sample of Dutch tweets. Moreover, the error analysis shows some clear avenues for further improvement.

Genre and domain in patent texts

In this paper we investigate the variation in language use within the very broad patent domain. We find that language use (represented by syntactic phrases) not only differs from one patent class to the next, but is also a characteristic that sets apart the four sections of a patent (viz. Title, Abstract, Description and Claims). This lends support to the claim that these sections can be viewed as different text genres. For the development of a syntactic parser that is trained on patent texts, we quantify the domain and genre differences in terms of the amounts of text needed to train domain-dependent versions of the parser. Our quantified and exemplified findings on the domain variation in patent data are of interest for the patent retrieval and analysis communities.