This paper presents an exemplar-theoretic account of pitchaccent variability. Results from two experiments are reported. The first experiment examines variability / similarity across a range of pitch-accent contour types which vary in frequency of occurrence. The results report similar behaviour across the frequency bins and are indicative of pitch-accent immunity from frequency effects. The se...

Sentence Similarity [SS] computes a similarity score between two sentences. The SS task differs from document level semantics tasks in that it features the sparsity of words in a data unit, i.e. a sentence. Accordingly it is crucial to robustly model each word in a sentence to capture the complete semantic picture of the sentence. In this paper, we hypothesize that by better modeling lexical se...

This paper suggests refinements for the Distributional Similarity Hypothesis. Our proposed hypotheses relate the distributional behavior of pairs of words to lexical entailment – a tighter notion of semantic similarity that is required by many NLP applications. To automatically explore the validity of the defined hypotheses we developed an inclusion testing algorithm for characteristic features...

Two studies examined how lexical information contained in words affects people’s category representations. Some words are lexically suggestive regarding the taxonomic position of their referent (e.g., bumblebee, starfish). However, this information differs from language to language (e.g., in Dutch the equivalent words hold no taxonomic information: hommel, vlinder). Three language groups, Dutch...

This paper proposes a model of semantic labeling based on the edit distance. The dynamic programming approach stresses on a non-exact string matching technique that takes full advantage of the underlying grammatical structure of 65,000 parse trees in a Treebank. Both part-of-speech and lexical similarity serve to identify the possible semantic labels, without miring into a pure linguistic analy...

The role of segment similarity in early (i.e., partially learned) lexical entries was assessed using artificial lexicons in a referential context. During a learning phase participants heard 40 nonsense words, each accompanied by an unfamiliar picture. In testing, participants heard the direction ‘‘Click on the [X]’’, and chose which of four pictures was the target (X). Target lexical items (e.g...

Automated thesaurus construction by collecting relations between lexical items (synonyms, antonyms, etc) has a long tradition in natural language processing. This has been done by exploiting dictionary structures or distributional context regularities (coocurrence, syntactic associations, or translation equivalents), in order to define measures of lexical similarity or relatedness. Dyvik had pr...

The UOW submissions to the Semantic Textual Similarity task at SemEval-2012 use a supervised machine learning algorithm along with features based on lexical, syntactic and semantic similarity metrics to predict the semantic equivalence between a pair of sentences. The lexical metrics are based on wordoverlap. A shallow syntactic metric is based on the overlap of base-phrase labels. The semantic...

This paper introduces the state-of-the-art MT evaluation survey that contains both manual and automatic evaluation methods. The traditional human evaluation criteria mainly include the intelligibility, fidelity, fluency, adequacy, comprehension, and informativeness. We classify the automatic evaluation methods into two categories, including lexical similarity and linguistic features application...