Any-language frame-semantic parsing

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 2062–2066, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. Any-language frame-semantic parsing Anders Johannsen, Héctor Martínez Alonso, Anders Søgaard Center for Language Technology University of Copenhagen, Denmark Njalsgade 140, DK-2300 Copenhagen S {ajohannsen,alonso,soegaard}@hum.ku.dk Abstract We present a multilingual corpus of Wikipedia and Twitter texts annotated with FRAMENET 1.5 semantic frames in nine different languages, as well as a novel technique for weakly supervised cross-lingual frame-semantic parsing. Our approach only assumes the existence of linked, comparable source and target lan- guage corpora (e.g., Wikipedia) and a bilingual dictionary (e.g., Wiktionary or BABELNET). Our approach uses a truly interlingual representation, enabling us to use the same model across all nine lan- guages. We present average error reduc- tions over running a state-of-the-art parser on word-to-word translations of 46% for target identification, 37% for frame identi- fication, and 14% for argument identifica- tion. 1 Introduction Frame-semantic parsing is the task of automati- cally finding semantically salient targets in text, disambiguating the targets by assigning a sense (frame) to them, identifying their arguments, and labeling these arguments with appropriate roles. The FRAMENET 1.5 lexicon1 provides a fixed repository of semantic frames and roles, which we use in the experiments below. Several learning and parsing algorithms have been developed for frame-semantic analysis (Jo- hansson and Nugues, 2007; Das et al., 2014; Täck- ström et al., 2015), and frame semantics has been successfully applied to question-answering (Shen and Lapata, 2007), information extraction (Sur- deanu et al., 2003) and knowledge extraction (Sø- gaard et al., 2015b). 1https://framenet.icsi.berkeley.edu/ In contrast to Propbank-style semantic-role la- beling (Titov and Klementiev, 2012), only very limited frame-semantic resources exist for lan- guages other than English. We therefore fo- cus on multilingual or cross-language frame- semantic parsing, leveraging resources for English and other major languages to build any-language parsers. We stress that we learn frame-semantic parsing models that can be applied to any lan- guage, rather than cross-lingual transfer models for specific target languages. Our approach re- lies on inter-lingual word embeddings (Søgaard et al., 2015a), which are built from topic-aligned documents. Word embeddings have previously been used for monolingual frame-semantic pars- ing by Hermann et al. (2014). Contributions This paper makes the following three contributions. We present a new multi- lingual frame-annotated corpus covering five top- ics, two domains (Wikipedia and Twitter), and nine languages. We implement a simplified ver- sion of the frame-semantic parser introduced in Das et al. (2014). Finally, we show how to modify this parser to learn any-language frame-semantic parsing models using inter-lingual word embed- dings (Søgaard et al., 2015a). 2 Data annotation Figure 1 depicts a FRAMENET 1.5 frame-semantic analysis of a German sentence from Wikipedia. The annotator marked two words, Idee and kam, as targets. In frame-semantic parsing, target iden- tification is the task of deciding which words (i.e. targets) trigger FRAMENET frames. Frame iden- tification is the problem of disambiguating targets by labeling them with frames, e.g., COGITATION or COMING_UP_WITH. …

Content truncated to 500 words