Abstract not found

Abstract. In the last ten years there has been a significant amount of research in Machine Translation within a “new ” paradigm of empirical approaches, often labelled collectively as “Example-based” approaches. The first manifestation of this approach caused some surprise and hostility among observers more used to different ways of working, but the techniques were quickly adopted and adapted by many researchers, often creating hybrid systems. This paper reviews the various research efforts within this paradigm reported to date, and attempts a categorisation of different manifestations of the general approach.

An es.,;ential problem of exa, mple-based transla- tion is how to utilize more than one translation example for translating one source sentence.

Abstract not found

EBMT (Example-Based Machine Translation) is proposed. EBMT retrieves similar examples (pairs of source phrases, sentences, or texts and their translations) from a tahase of examples, adapting the examples to franslate a new input. EBMT has the following features: (1) It is easily upgraded simply by inputting appropriate examples to the database; (2) It assigns a reliability factor to the translation result; (3) It is accelerated effectively by both indexing axi parallel computing; (4) It is robust because of best-match reasoning; (5) It well utilizes translator expertise. A prototype system has been implemented to deal with a difficult Iranslation problem fee conventional Rule-Based Machine Translation (RBMT), i.e., translating Japanese noun phrases of the form 'lq a no N2" into English. The system has achieved about a 78% success rate on average. This paper explains the basic idea of EBMT, illustrates the experiment in detail, explains the broad applicability of EBMT to several difficult translation problems fee RBMT discusses the advantages of integrating EBMT with RBMT.

This paper proposes a two-phase example-based machine translation methodology which develops translation templates from examples and then translates using template matching. This method improves translation quality and facilitates customization of machine translation systems. This paper focuses on the automatic learning of translation templates. A translation template is a bilingual pair of sentences in which corresponding units (words and phrases) are coupled and replaced with variables. Correspondence between units is determined by using a bilingual dictionary and by analyzing the syntactic structure of the sentences. Syntactic ambiguity and ambiguity in correspondence between units are simultaneously resolved. All of the translation templates generated from a bilingual corpus are grouped by their source language part, and then further refined to resolve conflicls among templates whose source language parts are the same but whose target language parts are different. By using the proposed method, not only transfer rules but also knowledge for lexical selection is effectively extracted from a bilingual corpus.

Translingual information retrieval (TIR) consists of providing a query in one language and searching document collections in one or more di erent languages. This paper introduces new TIR methods and reports on comparative TIR experiments with these new methods and with previously reported ones in a realistic setting. Methods fall into two categories: query translation based, and statistical-IR approaches establishing translingual associations. The results show that using bilingual corpora for automated extraction of term equivalences in context outperforms other methods. Translingual versions of the Generalized Vector Space Model (GVSM) and Latent Semantic Indexing (LSI) perform relatively well, as does translingual pseudo relevance feedback (PRF). All showed relatively small performance loss between monolingual and translingual versions. Query translation based on a general machinereadable bilingual dictionary { heretofore the most popular method { did not match the performance of other, more sophisticated methods. Also, the previous very high LSI results in the literature were discon rmed by more realistic relevance-based evaluations. 1

Example-Based Machine Translation (EBMT) using partial exact matching against a database of translation examples has proven quite successful, but requires a large amount of pre-translated text in order to achieve broad coverage of unrestricted text. By adding linguistically tagged entries to the example base and permitting recursive matches that replace the matched text with the associated tag, substantial reductions in the required amount of pre-translated text can be achieved. A modest investment of time -- on the order of two person-weeks -- adding linguistic knowledge reduces the required example text by a factor of six or more, while retaining comparable translation quality. This reduction makes EBMT more attractive for so-called "low-density" languages for which little data is available.

An Example-Based Machine Translation system is supplied with a sentence-aligned bilingual corpus, but no other knowledge sources. Using the knowledge implicit in the corpus, it generates a bilingual word-for-word dictionary for alignment during translation. With such an automatically-generated dictionary, the system covers (with equivalent quality) more of its input on unseen texts than the same system does when provided with a manually-created general-purpose dictionary and other knowledge sources.

Translingual information retrieval (TLIR) consists of providing a query in one language and searching document collections in one or more different languages. This paper introduces new TLIR methods and reports on comparative TLIR experiments with these new methods and with previously reported ones in a realistic setting. Methods fall into two categories: query translation and statistical-IR approaches establishing translingual associations. The results show that using bilingual corpora for automated extraction of term equivalences in context outperforms dictionary-based methods. Translingual versions of the Generalized Vector Space Model (GVSM) and Latent Semantic Indexing (LSI) also perform well, as does translingual pseudo relevance feedback (PRF) and Example-Based Term-in-context Translation (EBT). All showed relatively small performance loss between monolingual and translingual versions, ranging between 87% to 101% of monolingual IR performance. Query translation based on a general...