background: cerebrovascular disease leading to stroke is the most common cause of aphasia. speakers with agrammatic non-fluent aphasia have difficulties in production of movement-derived sentences such as passive sentences, topicalized constituents, and wh-questions. to assess the production of complex sentences, some passive, topicalized and focused sentences were designed for patients with no...

We present a machine learning approach for classifying sentences as one-liner jokes or normal sentences. We use no deep analysis of the meaning to try to see if it is humorous, instead we rely on a combination of simple features to see if these are enough to detect humor. Features such as word overlap with other jokes, presence of words common in jokes, ambiguity and word overlap with common id...

A Swedish Hearing In Noise Test (HINT), consisting of everyday sentences to be used in an adaptive procedure to estimate the speech recognition thresholds in noise and quiet, has been developed. The material consists of 250 sentences, with a length of five to nine syllables, normalized for naturalness, difficulty and reliability. The sentences were recorded with a female speaker. From the sente...

This paper introduces a new type of unsupervised learning algorithm, based on the alignment of sentences and Harris’s (1951) notion of interchangeability. The algorithm is applied to an untagged, unstructured corpus of natural language sentences, resulting in a labelled, bracketed version of the corpus. Firstly, the algorithm aligns all sentences in the corpus in pairs, resulting in a partition...

In this article, the current implementation of the AlignmentBased Learning (ABL) framework (van Zaanen, 2002) will be described. ABL is an unsupervised grammar induction system that is based on Harris’s (1951) idea of substitutability. Instances of the framework can be applied to an untagged, unstructured corpus of natural language sentences, resulting in a labelled, bracketed version of that c...

This paper introduces a new type of unsupervised learning algorithm, based on the alignment of sentences and Harris’s (1951) notion of interchangeability. The algorithm is applied to an untagged, unstructured corpus of natural language sentences, resulting in a labelled, bracketed version of the corpus. Firstly, the algorithm aligns all sentences in the corpus in pairs, resulting in a partition...