LoPar: Design and Implementation

By Helmut Schmid. 2000

88 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Software Engineering

Citations in the corpus

The Edinburgh/JHU Phrase-based Machine Translation Systems for WMT 2015 (2015, methodology): “…was exploited in addition to word surface forms: Och clusters (50 classes), morphological tags, part-of-speech tags, and word stems on the German side (Schmid, 2000), as well as Och clusters (50 classes), part-of-speech tags (Ratnaparkhi, 1996), and word stems (Porter, 1980) on the English side.”
Learning Concept Hierarchies from Text Corpora using Formal Concept Analysis (2005, methodology): “First, the corpus is part-of-speech (POS) tagged 1 using TreeTagger (Schmid, 1994) and parsed using LoPar 2 (Schmid, 2000), thus yielding a parse tree for each sentence.”
Treebank Annotation Schemes and Parser Evaluation for German (2007, methodology): “A comparison of unlexicalised PCFG parsing (K¤ubler, 2005) trained and evaluated on the German NEGRA (Skut et al., 1997) and the T¤uBa-D/Z (Telljohann et al., 2004) treebanks using LoPar (Schmid, 2000) shows a difference in parsing results of about 16%, using the PARSEVAL metric (Black et al., 1991)”
English SLT and MT system description for the IWSLT 2013 evaluation (2013, methodology): “We used LoPar [42] to obtain morphological analysis and POS annotation of German and MXPOST [43], a maximum entropy model for English POS tags.”
Edinburgh’s Statistical Machine Translation Systems for WMT16 (2016, background): “…several translation factors in addition to word surface forms, in particular: Och clusters (with 50 classes) and part-of-speech tags (Ratnaparkhi, 1996) on the English side, as well as Och clusters (50 classes), morphological tags, and part-of-speech tags on the German side (Schmid, 2000).”
Understanding and Improving Morphological Learning in the Neural Machine Translation Decoder (2017, methodology): “We used the following tools recommended on the Moses website 1 to annotate the data: LoPar (Schmid, 2000) for German, Tree-tagger (Schmid, 1994) for Czech and MXPOST (Ratnaparkhi, 1998) for English.”
Investigating the Usefulness of Generalized Word Representations in SMT (2014, methodology): “We used LoPar (Schmid, 2000) to obtain morphological analysis and POS annotation of German and MXPOST (Ratnaparkhi, 1998), a maximum entropy model for English POS tags.”
Using subcategorization knowledge to improve case prediction for translation to German (2013, methodology): “…was dependency-parsed with Bohnet (2010), and subcategorization information was extracted as described in Scheible et al. (2013); the newspaper data (HGC - Huge German Corpus) was parsed with Schmid (2000), and subcategorization information was extracted as described in Schulte im Walde (2002b).”
On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, background): “corpora: MADAMIRA [272] for Arabic POS and morphological tags, Tree-Tagger [296] for Czech and French POS tags, LoPar [297] for German POS and morphological tags, and MXPOST [283] for English POS tags.”