Statistical parsers trained on labeled data suffer from sparsity, both grammatical and lexical. For parsers based on strongly lexicalized grammar formalisms (such as CCG, which has complex lexical categories but simple combinatory rules), the problem of sparsity can be isolated to the lexicon. In this paper, we show that semi-supervised Viterbi-EM can be used to extend the lexicon of a generati...

Speech recognizers are typically trained with data from a standard dialect and do not generalize to non-standard dialects. Mismatch mainly occurs in the acoustic realization of words, which is represented by acoustic models and pronunciation lexicon. Standard techniques for addressing this mismatch are generative in nature and include acoustic model adaptation and expansion of lexicon with pron...

In this paper, we outline a model of semantics that integrates aspects of discourse-sensitive logics with the compositional mechanisms available from lexically-driven semantic interpretation. Specifically, we concentrate on developing a composition logic required to properly model complex types within the Generative Lexicon (henceforth GL), for which we employ SDRT principles. As we are present...

Human language relies on a finite lexicon to express a potentially infinite set of ideas. A key result of this tension is that words acquire novel senses over time. However, the cognitive processes that underlie the historical emergence of new word senses are poorly understood. Here, we present a computational framework that formalizes competing views of how new senses of a word might emerge by...

Corpus-based Valency Lexicon of Czech Nouns is a starting project picking up the threads of our previous work on nominal valency. It builds upon solid theoretical foundations of the theory of valency developed within the Functional Generative Description. In this paper, we describe the ways of treating valency of nouns in a modern corpus-based lexicon, available as machine readable data in a fo...

The analysis of nominal compound constructions has proven to be a recalcitrant problem for linguistic semantics and poses serious challenges for natural language processing systems. We argue for a compositional treatment of compound constructions which limits the need for listing of compounds in the lexicon. We argue that the development of a practical model of compound interpretation crucially...

In virtually every state-of-the-art large vocabulary continuous speech recognition (LVCSR) system, grapheme-to-phoneme (G2P) conversion is applied to generalize beyond a fixed set of words given by a background lexicon. The overall performance of the G2P system has a strong effect on the recognition quality. Typically, generative models based on joint-n-grams are used, although some discriminat...

We present a probabilistic model of phonotactics, the set of well-formed phoneme sequences in a language. Unlike most computational models of phonotactics (Hayes and Wilson, 2008; Goldsmith and Riggle, 2012), we take a fully generative approach, modeling a process where forms are built up out of subparts by phonologically-informed structure building operations. We learn an inventory of subparts...