A Joint Model of Orthography and Morphological Segmentation

Abstract

We present a model of morphological segmentation that jointly learns to segment and restore orthographic changes, e.g., funniest → fun-y-est. We term this form of analysis canonical segmentation and contrast it with the traditional surface segmentation, which segments a surface form into a sequence of substrings, e.g., funniest → funn-i-est. We derive an importance sampling algorithm for approximate inference in the model and report experimental results on English, German and Indonesian.

Neural Morphological Analysis: Encoding-Decoding Canonical Segments

“…Indonesian -or Bahasa Indonesia-is the official language of Indonesia. Cotterell et al (2016) report the best experimental results for Indonesian, followed by English and finally German. The high error rate for German might be caused by it being rich in orthografic changes.…”

“…To enable comparison to earlier work, we use a dataset that was prepared by Cotterell et al (2016) for canonical segmentation. 3…”

“…Finally, the data for Bahasa Indonesia was collected by using the output of the MORPHIND analyzer (Larasati et al, 2011), together with an open-source corpus of Indonesian. For each language we used the 10,000 forms that were selected at random by Cotterell et al (2016) from a uniform distribution over types to form the corpus. Following them, we perform our experiments on 5 splits of the data into 8000 training forms, 1000 development forms and 1000 test forms and report averages.…”

“…Baselines. Our first baseline is the joint transduction and segmentation model (JOINT) of Cotterell et al (2016). It is the current state of the art on the datasets we use and the task of canonical segmentation in general.…”

“…Canonical versions of morphological segmentation have been introduced multiple times in the literature (Kay, 1977;Naradowsky and Goldwater, 2009;Cotterell et al, 2016). Canonical segmentation has several representational advantages over surface segmentation, e.g., whether two words share a morpheme is no longer obfuscated by orthography.…”