Using cross-modal form priming, we compared the use of stress and lexicality in the segmentation of spoken English by native English speakers (L1) and by native Hungarian speakers of second-language English (L2). For both language groups, lexicality was found to be an effective segmentation cue. That is, spoken disyllabic word fragments were stronger primes in a subsequent visual word recogniti...

This paper presents a joint model for morphological and dependency analysis based on automatically acquired lexical knowledge. This model takes advantage of rich lexical knowledge to simultaneously resolve word segmentation, POS, and dependency ambiguities. In our experiments on Japanese, we show the effectiveness of our joint model over conventional pipeline models.

Morphological segmentation data for the METU-Sabancı Turkish Treebank is provided in this paper. The generalized lexical forms of the morphemes which the treebank previously lacked are added to the treebank. This data maybe used to train POS-taggers that use stemmer outputs to map these lexical forms to morphological tags.

Human listeners use lexical stress for word segmentation and disambiguation. We look into using lexical stress for speech recognition by examining a Dutch-language corpus. We propose that different spectral features are needed for different phonemes and that, besides vowels, consonants should be taken into account.

This research examined acoustic-phonetic cues to word boundary location in French consonant clusters, and assessed their use in on-line lexical segmentation. Two word-spotting experiments manipulated the alignment between word targets and syllable boundaries. A perceptual cost of such misalignment was observed for obstruent-liquid clusters but not for /s/ + obstruent clusters. For the former cl...

This work concerns automatic topic segmentation of email conversations. We present a corpus of email threads manually annotated with topics, and evaluate annotator reliability. To our knowledge, this is the first such email corpus. We show how the existing topic segmentation models (i.e., Lexical Chain Segmenter (LCSeg) and Latent Dirichlet Allocation (LDA)) which are solely based on lexical in...

Text segmentation is a fundamental problem in natural language processing, which has application in information retrieval, question answering, and text summarization. Almost previous works on unsupervised text segmentation are based on the assumption of lexical cohesion, which is indicated by relations between words in the two units of text. However, they only take into account the reiteration,...

The possible-word constraint (PWC; Norris, McQueen, Cutler, & Butterfield, 1997) has been proposed as a language-universal segmentation principle: Lexical candidates are disfavoured if the resulting segmentation of continuous speech leads to vowelless residues in the input-for example, single consonants. Three word-spotting experiments investigated segmentation in Slovak, a language with single...

We describe our experiments for the Similar Segments in Social Speech Task at MediaEval 2013 Benchmark. We mainly focus on segmentation of the recordings into shorter passages on which we apply standard retrieval techniques. We experiment with machine-learning-based segmentation employing textual (word n-grams, tag n-grams, letter cases, lexical cohesion, etc.) and prosodic features (silence) a...