Abstract
Syntax-based distributional models of lexical semantics provide a flexible and linguistically adequate representation of co-occurrence information. However, their construction requires large, accurately parsed corpora, which are unavailable for most languages. In this paper, we develop a number of methods to overcome this obstacle. We describe (a) a crosslingual approach that constructs a syntax-based model for a new language requiring only an English resource and a translation lexicon; and (b) multilingual approaches that combine crosslingual with monolingual information, subject to availability. We evaluate on two lexical semantic benchmarks in German and Croatian. We find that the models exhibit complementary profiles: crosslingual models yield higher accuracies while monolingual models provide better coverage. In addition, we show that simple multilingual models can successfully combine their strengths.
Highlights
Building on the Distributional Hypothesis (Harris, 1954; Miller and Charles, 1991), which states that words occurring in similar contexts are similar in meaning, distributional semantic models (DSMs) represent a word’s meaning via its occurrence in context in large corpora
Since the nature of the translation is not indicated in the translation lexicon, we exploit typical redundancies in the source Distributional Memory (DM), which often contains “quasi-synonymous” edges that express the same relation with different words, e.g., book obj read and novel obj read
Does not require parallel or comparable corpora. That translation lexicons such as the ones we use can be extracted from comparable corpora (Rapp, 1999; Vulicand Moens, 2012, and many others), though few papers are concerned with the translation at the level of semantic relations, as we are
Summary
Building on the Distributional Hypothesis (Harris, 1954; Miller and Charles, 1991), which states that words occurring in similar contexts are similar in meaning, distributional semantic models (DSMs) represent a word’s meaning via its occurrence in context in large corpora. A notable subclass of DSMs are syntax-based models (Lin, 1998; Baroni and Lenci, 2010) which use (lexicalized) syntactic relations as dimensions. They are able to model more fine-grained distinctions than word spaces and have been found to be useful for tasks such as selectional preference learning (Erk et al, 2010), verb class induction (Schulte im Walde, 2006), analogical reasoning (Turney, 2006), and alternation discovery (Joanis et al, 2006). The paper concludes with related work (Section 8) and a general discussion (Section 9)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Transactions of the Association for Computational Linguistics
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
