Lexical Knowledge Acquisition from Bilingual Corpora

I)br practical research in natnral language processing, it is indisl)ensM)le to develop a large scale semantic dictionary for computers. It is cspeciany important to improve thc tcclmiqucs tbr compiling semantic dictionaries ti'orn natural language texts such as those in existing human dictionaries or in large corpora, llowever, there are at least two ditlicultics in analyzing existing texts: tbe l)roblem of syntactic ambiguities and the probtcm of polysemy. Our approaclL to solve these difficulties is to make use of translation exampies in two distinct languages that have (lnite different syntactic structures and word meanings. The roe.son we took this at)preach is that in many cases both syn: tactic aLrd semantic ambignitics arc resolved by comparing analyzed resnlts from botb languages. In this paper, we propose a method Ibr resolving the syntactic ambiguities of translation cxaml>lcs of bilingual corpora and a method for acquiring lexical knowledge, such as ease frames of verbs and attribute sets el noons. 1 I n t r o d u c t i o n It has become widely accel)ted that developing a large scale semantic dictionary is indispensable to future natural language research. ILL recent years, several research activities for compiling selnantic dictionaries tot natural language processing have been uudcrtaken One of the approaches in this research is attempts to compile dictionaries by band. Japan Electronic Dictionary Research Institute (El)R.) is now compiling conceptual dictionaries[5] by hand with the help of software tools. [nformation-4echnology Promotion Agency (IPA), Japan, has also compiled IPA Lexicon of the Japanese Language for computers (II'AL)[4]. IPAL has 861 entries for basic Jalranese verbs. Cyc project at tempts to assend)le a massive knowledge base covering human common-sense knowledge[7]. IIowever, this approach sailors from *The authol~ would like to t}mak the editorial staff of Kodazm|m for permission tO use the data of Jalmnese-12)nglidt dictionaa'y, arm also thank l)r. Shouichi YOKOYAMA, I,',TL, and Prof. l[ozumi TANAKA and Dr. '['akenobu TOKUNA(;A, Tokyo hmtitute of Teclmology, for providing us the data of Jal)ane~e-l~nglish dictionary. This work is partly supported by the Grants from Ministry of Education, #032,15103. probh'.Ins socb as a huge alnount of manila[ labor, difficulties in extending tile dictionaries, unstable remilts, and so forth. Anothcr approach is to compile dictionaries using some teclxmques of lexical knowledge acquisition. One ~nch approach is to extract hierarclfical relations or it thesanrtm of conceptual items froln hunLall dictionaries in an automatic way. q)surrnnaru et el. studied to construct a t}LeSaLLrlIs of nominal concepts from noun detinitions[t3], qbmiara et al. also extracted snperordinatc-subordmatc relation between verbs from the defining sentences in IPAL[12]. l i e sidcs these rcseasches, there are other several research activitics tbr lexical knowledge acquisition, which syntactically anMyze the sentences m large corpora and at tcmpt to extract lcxical knowledge from statistical data [3] [1]. Most of the works undertake shallow analysis of texts and they extract only superticial lexical information. For the development of tile techniques of knowledge acquisition from natural language texts, it is very important to improve the httter approach of cornpiling semantic dictionaries by comimter l)rograuL~. Ilowever, there are at least two basic difficulties in this at)preach 1. Tire i~robh~m (ff sy n t ac t i c a m b i g u i t i e s When analyzing a sentence., syntactic ambiguities often remain. So i~ is not easy to obtain correct parsed results automatically. 2. The, probh~rrr of polyue,my it often happens that one word has several meanings and corre.sponrls to ,~cveral concepts. So it is not easy to associate one sm'fa~e word with olle correct conceptHal item. Our approach to solve these diiliculties is to make use of translatitm cxarnples in two distinct languages that have quite different syntactic structures and word mf~anings (such as English and Japanese), and to c(nnt~are analyzed results from each language, h| many (:asc~, the two languagcs }Lave different types of syntactic ambiguities, anti comparison of syntactic structures of both bmguagcs helps to resolve the ambiguities. Also, a pair of bilingually equivalent snrface words helps to a~'4ociate tile words with conceptual Ac~s DECOLING-92, NANTIiS, 23-28 AOIJT 1992 5 8 1 l'~oc. OF COL]NG-92. NANTES. AUG. 23-28, 1992 words helps to associate the words with conceptual items, because the intersection of conceptual items that each surface word has could be considered as one conceptual i tem[ll] [2]. ["or example, in tire case of the translation example given in Example 1, both syntactic and semantic ambiguities are resolved.