This pilot study investigates the effects of focus (broad, narrow and contrastive) on tonal patterns, f0 scaling and duration of accented syllables and rhythmic feet for a controlled dataset in Donegal Irish. Results show differences in pre-focal tonal patterns between broad focus and the other focus types. Narrow and contrastive focus renditions are implemented by largely the same phonetic mea...

This paper aims to provide a unified explanation for Contrastive Topic (CT) and Rise-Fall-Rise (RFR) construction by establishing a theory of ‘Semantic Contrast’. This will require us to depart from the conventional idea of putting Contrastive Topic under the category of Topic in the information structure and to have a new idea that the meaning of CT is derived from the interaction of Contrast ...

The referring expressions (REs) produced by a natural language generation (NLG) system can be misunderstood by the hearer, even when they are semantically correct. In an interactive setting, the NLG system can try to recognize such misunderstandings and correct them. We present an algorithm for generating corrective REs that use contrastive focus (“no, the BLUE button”) to emphasize the informa...

Many studies on developmental speech perception (e.g. Werker & Tees 1984, Kuhl et al. 1992) have documented changes in speech perception that occur during an infant’s first year of life. These changes are generally understood to reflect the phonemic structure of the native language (Best et al. 1988, Liberman et al. 1957). There is little research, however, on the phonological abstractness of t...

The information structure categories of Contrastive Topic and Contrastive Focus are examined to see their crucial roles in polarity and (conventional) implicature generation and implicature suspension and their respective correlatins with PA and SN conjunctions on one hand and descriptive (denotational) negation and metalinguistic negation on the other. The underlying notion of concessivity inv...

Replicated Softmax model, a well-known undirected topic model, is powerful in extracting semantic representations of documents. Traditional learning strategies such as Contrastive Divergence are very inefficient. This paper provides a novel estimator to speed up the learning based on Noise Contrastive Estimate, extended for documents of variant lengths and weighted inputs. Experiments on two be...

We look at the average frequency of contrastive connectives in the SPaRKy Restaurant Corpus with respect to realization ratings by human judges. We implement a discriminative n-gram ranker to model these ratings and analyze the resulting n-gram weights to determine if our ranker learns this distribution. Surprisingly, our ranker learns to avoid contrastive connectives. We look at possible expla...

This paper introduces Ranking Info Noise Contrastive Estimation (RINCE), a new member in the family of InfoNCE losses that preserves ranked ordering positive samples. In contrast to standard loss, which requires strict binary separation training pairs into similar and dissimilar samples, RINCE can exploit information about similarity ranking for learning corresponding embedding space. We show p...

Taxonomy plays an important role in many applications by organizing domain knowledge into a hierarchy of is-a relations between terms. Previous works on the taxonomic relation identification from text corpora lack in two aspects: 1) They do not consider the trustiness of individual source texts, which is important to filter out incorrect relations from unreliable sources. 2) They also do not co...

This study examines the acoustic correlates of stress in children’s productions of bisyllabic and trisyllabic words, differing in stress placement. Acoustic results of the data of two children aged 4;11 to 6;1 are reported as a part of a more comprehensive study on the acquisition of stress in German. In contrast to recent findings that infants show an early preference in perception for rhythmi...