Joint Morphological and Syntactic Disambiguation

Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 208–217, Prague, June 2007. c⃝2007 Association for Computational Linguistics Joint Morphological and Syntactic Disambiguation∗ Shay B. Cohen and Noah A. Smith Language Technologies Institute School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 USA {scohen,nasmith}@cs.cmu.edu Abstract In morphologically rich languages, should morphological and syntactic disambiguation be treated sequentially or as a sin- gle problem? We describe several efficient, probabilistically- interpretable ways to apply joint inference to morphological and syntactic disambiguation using lattice parsing. Joint infer- ence is shown to compare favorably to pipeline parsing methods across a variety of component models. State-of-the-art perfor- mance on Hebrew Treebank parsing is demonstrated using the new method. The benefits of joint inference are modest with the current component models, but appear to increase as com- ponents themselves improve. 1 Introduction As the field of statistical NLP expands to handle more languages and domains, models appropriate for standard benchmark tasks do not always work well in new situations. Take, for example, pars- ing the Wall Street Journal Penn Treebank, a long- standing task for which highly accurate context-free models stabilized by the year 2000 (Collins, 1999; Charniak, 2000). On this task, the Collins model achieves 90% F1-accuracy. Extended for new lan- guages by Bikel (2004), it achieves only 75% on Arabic and 72% on Hebrew.1 It should come as no surprise that Semitic parsing lags behind English. The Collins model was care- fully designed and tuned for WSJ English. Many of the features in the model depend on English syntax or Penn Treebank annotation conventions. Inherent in its crafting is the assumption that a million words of training text are available. Finally, for English, it need not handle morphological ambiguity. Indeed, the figures cited above for Arabic and Hebrew are achieved using gold-standard morpho- logical disambiguation and part-of-speech tagging. ∗ The authors acknowledge helpful feedback from the anonymous reviewers, Sharon Goldwater, Rebecca Hwa, Alon Lavie, and Shuly Wintner. 1Compared to the Penn Treebank, the Arabic Treebank (Maamouri et al., 2004) has 60% as many word tokens, and the Hebrew Treebank (Sima’an et al., 2001) has 6%. Given only surface words, Arabic performance drops by 1.5 F1 points. The Hebrew Treebank (un- like Arabic) is built over morphemes, a convention we view as sensible, though it complicates parsing. This paper considers parsing for morphologically rich languages, with Hebrew as a test case. Mor- phology and syntax are two levels of linguistic de- scription that interact. This interaction, we argue, can affect disambiguation, so we explore here the matter of joint disambiguation. This involves the comparison of a pipeline (where morphology is in- ferred first and syntactic parsing follows) with joint inference. We present a generalization of the two, and show new ways to do joint inference for this task that does not involve a computational blow-up. The paper is organized as follows. §2 describes the state of the art in NLP for Hebrew and some …

Content truncated to 500 words