Morpho-syntactic Lexicon Generation Using Graph-based Semi-supervised Learning

Morpho-syntactic Lexicon Generation Using Graph-based Semi-supervised Learning Manaal Faruqui Carnegie Mellon University mfaruqui@cs.cmu.edu Ryan McDonald Google Inc. ryanmcd@google.com Radu Soricut Google Inc. rsoricut@google.com Abstract Morpho-syntactic lexicons provide informa- tion about the morphological and syntactic roles of words in a language. Such lexicons are not available for all languages and even when available, their coverage can be limited. We present a graph-based semi-supervised learning method that uses the morphologi- cal, syntactic and semantic relations between words to automatically construct wide cover- age lexicons from small seed sets. Our method is language-independent, and we show that we can expand a 1000 word seed lexicon to more than 100 times its size with high quality for 11 languages. In addition, the automatically created lexicons provide features that improve performance in two downstream tasks: mor- phological tagging and dependency parsing. 1 Introduction Morpho-syntactic lexicons contain information about the morphological attributes and syntactic roles of words in a given language. A typical lexicon contains all possible attributes that can be displayed by a word. Table 1 shows some entries in a sample English morpho-syntactic lexicon. As these lexicons contain rich linguistic information, they are useful as features in downstream NLP tasks like machine translation (Nießen and Ney, 2004; Minkov et al., 2007; Green and DeNero, 2012), part of speech tag- ging (Schmid, 1994; Denis and Sagot, 2009; Moore, 2015), dependency parsing (Goldberg et al., 2009), language modeling (Arisoy et al., 2010) and mor- phological tagging (M¨uller and Schuetze, 2015) in- ter alia. There are three major factors that limit the use of such lexicons in real world applications: (1) played POS:VERB, VFORM:FIN, . . .TENSE:PAST, playing POS:VERB, VFORM:GER, . . .TENSE:PRES, awesome POS:ADJ, DEGREE:POS Table 1: A sample English morpho-syntactic lexicon. They are often constructed manually and are expen- sive to obtain (Kokkinakis et al., 2000; Dukes and Habash, 2010); (2) They are currently available for only a few languages; and (3) Size of available lexi- cons is generally small. In this paper, we present a method that takes as in- put a small seed lexicon, containing a few thousand annotated words, and outputs an automatically con- structed lexicon which contains morpho-syntactic attributes (henceforth referred to as attributes) for a large number of words of a given language. We model the problem of morpho-syntactic lexicon gen- eration as a graph-based semi-supervised learning problem (Zhu, 2005; Bengio et al., 2006; Subra- manya and Talukdar, 2014). We construct a graph where nodes represent word types and the goal is to label them with attributes. The seed lexicon pro- vides attributes for a subset of these nodes. Nodes are connected to each other through edges that de- note features shared between them or surface mor- phological transformation between them. Our entire framework of lexicon generation, in- cluding the label propagation algorithm and the fea- ture extraction module is language independent. We only use word-level morphological, semantic and syntactic relations between words that can be in- duced from unannotated corpora in an unsuper- 1 Transactions of the Association for …

Content truncated to 500 words