Combined Distributional and Logical Semantics

Transactions of the Association for Computational Linguistics, 1 (2013) 179–192. Action Editor: Johan Bos. Submitted 1/2013; Revised 3/2013; Published 5/2013. c⃝2013 Association for Computational Linguistics. Combined Distributional and Logical Semantics Mike Lewis School of Informatics University of Edinburgh Edinburgh, EH8 9AB, UK mike.lewis@ed.ac.uk Mark Steedman School of Informatics University of Edinburgh Edinburgh, EH8 9AB, UK steedman@inf.ed.ac.uk Abstract We introduce a new approach to semantics which combines the benefits of distributional and formal logical semantics. Distributional models have been successful in modelling the meanings of content words, but logical se- mantics is necessary to adequately represent many function words. We follow formal se- mantics in mapping language to logical rep- resentations, but differ in that the relational constants used are induced by offline distri- butional clustering at the level of predicate- argument structure. Our clustering algorithm is highly scalable, allowing us to run on cor- pora the size of Gigaword. Different senses of a word are disambiguated based on their in- duced types. We outperform a variety of ex- isting approaches on a wide-coverage question answering task, and demonstrate the ability to make complex multi-sentence inferences in- volving quantifiers on the FraCaS suite. 1 Introduction Mapping natural language to meaning representa- tions is a central challenge of NLP. There has been much recent progress in unsupervised distributional semantics, in which the meaning of a word is in- duced based on its usage in large corpora. This ap- proach is useful for a range of key applications in- cluding question answering and relation extraction (Lin and Pantel, 2001; Poon and Domingos, 2009; Yao et al., 2011). Because such a semantics can be automically induced, it escapes the limitation of de- pending on relations from hand-built training data, knowledge bases or ontologies, which have proved of limited use in capturing the huge variety of mean- ings that can be expressed in language. However, distributional semantics has largely de- veloped in isolation from the formal semantics liter- ature. Whilst distributional semantics has been ef- fective in modelling the meanings of content words such as nouns and verbs, it is less clear that it can be applied to the meanings of function words. Semantic operators, such as determiners, negation, conjunc- tions, modals, tense, mood, aspect, and plurals are ubiquitous in natural language, and are crucial for high performance on many practical applications— but current distributional models struggle to capture even simple examples. Conversely, computational models of formal semantics have shown low recall on practical applications, stemming from their re- liance on ontologies such as WordNet (Miller, 1995) to model the meanings of content words (Bobrow et al., 2007; Bos and Markert, 2005). For example, consider what is needed to answer a question like Did Google buy YouTube? from the following sentences: 1. Google purchased YouTube 2. Google’s acquisition of YouTube 3. Google acquired every company 4. YouTube may be sold to Google 5. Google will buy YouTube or Microsoft 6. Google didn’t takeover YouTube All of these require knowledge of lexical seman- tics (e.g. that …

Content truncated to 500 words