File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/90/j90-2001_metho.xml
Size: 28,285 bytes
Last Modified: 2025-10-06 14:12:29
<?xml version="1.0" standalone="yes"?> <Paper uid="J90-2001"> <Title>WIDE-RANGE RESTRUCTURING OF REPRESENTATIONS IN MACHINE INTERMEDIATE TRANSLATION</Title> <Section position="3" start_page="0" end_page="0" type="metho"> <SectionTitle> 2 STYLISTIC GAPS BETWEEN LANGUAGES </SectionTitle> <Paragraph position="0"> In discussions on the stylistic gaps between English and Japanese, it is often said that English is a HAVE-type or DO-type language, whereas Japanese is a BE-type or BE-COME-type language. This contrast corresponds to the differences in the ways people recognize things and express their ideas about them (Nitta 1986), and hence is considered as a difference of viewpoint. Idioms and metaphors are heavily dependent upon each society and culture, and we sometimes have to reinterpret them to give an appropriate translation. Each language also has its own specific function word constructions, which are used to express specific meanings. These specific constructions cannot be directly translated into other languages.</Paragraph> <Paragraph position="1"> We categorize the major stylistic gaps as follows: (1) stylistic gaps in viewpoint, (2) stylistic gaps in idioms and metaphors, (3) stylistic gaps in specific constructions using function words, and (4) others. We will discuss these gaps in more detail in the case of English-to-Japanese translation by referring to examples extracted from the literature (Bekku 1979; Anzai 1983) and slightly modified for our purpose. In each example, the first sentence is the original English and the second one is an equivalent or a rough equivalent in Japanese-like English, which will help us recognize the stylistic gaps, though some of the rewritten English is not strictly acceptable.</Paragraph> <Section position="1" start_page="0" end_page="0" type="sub_section"> <SectionTitle> 2.1 STYLISTIC GAPS IN VIEWPOINT </SectionTitle> <Paragraph position="0"> The following are some examples of stylistic gaps due to differences of viewpoint.</Paragraph> <Paragraph position="1"> 1. Inanimate noun + transitive verb i) Inanimate noun + have (I-a) The room has two tables.</Paragraph> <Paragraph position="2"> (l-b) Two tables are in the room. ii) Others (2-a) This chapter contains the explanation. (2-b) The explanation is contained in this chapter. The meaning of (l-a) is that the room contains two tables. However, an inanimate subject for the verb have is not allowed in Japanese. Japanese usually expresses the same fact as in (l-b), without using an inanimate subject. (2-a) and (2-b) show a case in which the voice is changed to avoid an inanimate subject in a Japanese sentence. 2. Gerund (intransitive verb) + of + noun + transitive verb (3-a) The humming of insects reminded me of autumn. (3-b) Because insects were humming, it seemed to me it was autumn.</Paragraph> <Paragraph position="3"> T~:is case is similar to example (I-a) in that the subject of (3-a) is inanimate. An event or action, which may be the subject of an English sentence, is usually treated as a cause or reason in a Japanese sentence.</Paragraph> <Paragraph position="4"> &quot;/2 ,Computational Linguistics Volume 16, Number 2, June 1990 Taijiro Tsutsumi Intermediate Representations in Machine Translation 3. Inanimate noun + allow + noun + to-infinitive (4-a) The support allows you to write IPL procedures. (4-b) You can write IPL procedures by using the support. In this case, we can consider the subject as a tool or method, as explicitly rewritten in (4-b).</Paragraph> <Paragraph position="5"> 4. Have + adjective + noun (two-place predicate) (5-a) The routine has a relatively low usage rate. (5-b) The usage rate of the routine is relatively low. The adjective low in the noun phrase low usage rate in (5-a) is removed and used as predicative form in (5-b). Japanese often prefers predicative expressions like this. 5. Adjective + verbal noun + of + noun (6-a) He is a good speaker of English.</Paragraph> <Paragraph position="6"> (6-b) He speaks English well.</Paragraph> <Paragraph position="7"> The noun phrase a good speaker is rewritten to form a predicative phrase.</Paragraph> <Paragraph position="8"> 6. Special verb (do, make, perform, etc.) + adjective + verbal noun + of + noun (7-a) The DOS/VSE SCP is designed to make efficient use of a hardware system.</Paragraph> <Paragraph position="9"> (7-b) The DOS/VSE SCP is designed to use a hardware system efficiently.</Paragraph> <Paragraph position="10"> This is also a case in which Japanese prefers a predicative phrase.</Paragraph> <Paragraph position="11"> 7. Special determiner (no, few, little, etc.) + noun (8-a) I have no French books.</Paragraph> <Paragraph position="12"> (8-b) I do not have any French books.</Paragraph> <Paragraph position="13"> This is a case in which a special determiner should be removed from the noun phrase and rewritten as an adverb. If we translate these English sentences literally into Japanese, we will have low readability for the Japanese sentences.</Paragraph> </Section> <Section position="2" start_page="0" end_page="0" type="sub_section"> <SectionTitle> 2.2 STYLISTIC GAPS IN IDIOMS AND METAPHORS </SectionTitle> <Paragraph position="0"> Idioms and metaphors should be distinguished from other phrases in a text, because they have implicit and fixed meanings. The following are some examples: (9-a) A car drinks gasoline.</Paragraph> <Paragraph position="1"> (9-b) A car requires a lot of gasoline.</Paragraph> <Paragraph position="2"> (10-a) Cigarettes are time bombs.</Paragraph> <Paragraph position="3"> (10-b) Cigarettes gradually harm us.</Paragraph> <Paragraph position="4"> (1 l-a) He burned his bridges.</Paragraph> <Paragraph position="5"> (1 I-b) He destroyed his alternative options. In case (9-a), we will face difficulty in semantic processing if we try to translate the sentence directly. The reason is that the verb drink usually requires an animate subject whereas the noun car is, in most cases, classified as an inanimate thing.</Paragraph> <Paragraph position="6"> We can translate example (10-a) literally if we want to preserve the humor conveyed by the original sentence. However, this is not often possible because of cultural differences. Example (1 l-a) is a typical case of something that we cannot translate literally into Japanese.</Paragraph> </Section> </Section> <Section position="4" start_page="0" end_page="0" type="metho"> <SectionTitle> 2.3 STYLISTIC GAPS IN SPECIAL FUNCTION WORD CONSTRUCTIONS </SectionTitle> <Paragraph position="0"> The following are some examples of stylistic gaps due to special English constructions using function words.</Paragraph> <Paragraph position="1"> (12-a) It is required that you specify the assignment. (12-b) That you specify the assignment is required. (13-a) The system operation is so impaired that the IPL procedure has to be repeated.</Paragraph> <Paragraph position="2"> (13-bl) Because the system operation is impaired very much, the IPL procedure has to be repeated.</Paragraph> <Paragraph position="3"> (13-b2) The system operation is impaired to the extent that the IPL procedure has to be repeated.</Paragraph> <Paragraph position="4"> (14-a) The box is too heavy for a child to carry. (14-bl) Because the box is very heavy, a child cannot carry it.</Paragraph> <Paragraph position="5"> (14-b2) The box is very heavy to the extent that a child cannot carry it.</Paragraph> <Paragraph position="6"> There is no direct way to translate the examples given above, because the grammatical functions conveyed by the special constructions using function words are often expressed in a very different way in a target language.</Paragraph> <Section position="1" start_page="0" end_page="0" type="sub_section"> <SectionTitle> 2.4 OTHERS </SectionTitle> <Paragraph position="0"> In addition to the stylistic gaps described above, we often see other stylistic gaps based on the meaning of a word. For example, the verb bridge in English should be translated by &quot;hashi (a noun meaning a bridge) wo (a case particle meaning an object) kakeru (a verb meaning 'install')&quot; in Japanese. One English verb corresponds to a noun, a case particle, and a verb in this case. A set of consecutive words may have a fixed meaning: for example, a number of can be considered as many in most cases. Differences in tense, aspect, and modality are also related to stylist gaps between languages, although we do not discuss these in detail here.</Paragraph> <Paragraph position="1"> So far, we have discussed four types of stylistic gaps.</Paragraph> <Paragraph position="2"> Generally, there are larger stylistic gaps between languages belonging to different groups than between languages in the same group. It is clear that if we can deal adequately with these stylistic gaps, we can further improve translation quality.</Paragraph> </Section> </Section> <Section position="5" start_page="0" end_page="0" type="metho"> <SectionTitle> 3 How TO DEAL WITH STYLISTIC GAPS </SectionTitle> <Paragraph position="0"> This section discusses a framework for dealing with the stylistic gaps we noted in the previous section.</Paragraph> <Section position="1" start_page="0" end_page="0" type="sub_section"> <SectionTitle> 3.1 THE COMPOSlTIONALITY PRINCIPLE IN </SectionTitle> <Paragraph position="0"/> </Section> </Section> <Section position="6" start_page="0" end_page="0" type="metho"> <SectionTitle> MACHINE TRANSLATION </SectionTitle> <Paragraph position="0"> Most machine translation systems (Slocum 1985) aiming at practical use employ the transfer method, which divides Computational Linguistics Volume 16, Number 2, June 1990 73 Taijiro Tsutsumi Intermediate Representations in Machine Translation the whole process into three phases: analysis of the source language, transfer between intermediate representations, and generation of the target language. The basic concept underlying current machine translation technology is the compositionality principle (Nagao 1986). The original idea of the principle is that the meaning of a sentence can be assembled from the meaning of each of its constituents and, moreover, that the assembling process can be implemented by assembling the forms or syntax that convey the meanings. Montague grammar is one of the theoretical bases of the principle, and some work applying Montague grammar to machine translation has been reported (Landsbergen 1982; Nishida and Doshita 1983). If the compositionality principle is applied to machine translation, we expect that it will be possible to translate a whole sentence by translating each word individually and then appropriately composing all the translated words.</Paragraph> <Paragraph position="1"> For example, let us consider the following two sentences, which have the same meaning.</Paragraph> <Paragraph position="2"> S: I drink water. (English) JS: watashi ha mizu wo nomu. (Japanese) (I) (water) (drink) Let us assume that the above sentences have the syntactic structures shown in Figure 1 (a) and (b), based on the grammars shown in (c) and (d), respectively. Note that the parentheses in the right-hand side of the last rule in (d) denote a condition that must be met in applying the rule.</Paragraph> <Paragraph position="3"> These structures are also considered to be the intermediate structures (i.e. the source structure and target structure) in the transfer phase of machine translation.</Paragraph> <Paragraph position="4"> The ideal machine translation based on the compositionality principle ensures that structure (a) is successfully transferred to structure (b) by applying the transfer rules, as shown in Figure 2.</Paragraph> <Paragraph position="5"> In Figure 2, the transfer rules are symbolized for convenience. The left-hand sides of the rules consist of matching patterns that correspond to the grammar of the English sentence, and the right-hand sides consist of target patterns that correspond to the grammar of the target Japanese sentence.</Paragraph> <Paragraph position="6"> The steps of the transfer process using these transfer rules are shown in Figure 3. This transfer process is done entirely in a bottom-up and left-to-right manner by using the transfer rules, and is based on the compositionality principle. The process is simple, easy to control, and easy to implement efficiently.</Paragraph> <Paragraph position="7"> Let us consider the stylistic gaps mentioned in the previous section. To bridge such gaps, we need to replace some words with new words and perform restructuring widely. It is important to recognize that the words involved in the rephtcement are class words (i.e. noun, adjective, verb, and adverb) rather than function words (i.e. preposition, auxiliary verb, conjunction, relative pronoun, particle, etc.), as shown in the examples of types 2.1 and 2.2. For example, in cases (6-a) and (6-b), good is replaced by well and speaker is replaced by speaks. In cases (10-a) and (10-b), are time bombs is replaced by gradually harm us. On the other hand, most words involved in the replacement are function words in the examples of type 2.3. For example, in cases (13-a) and (13-bl), so and that are replaced by because and very much.</Paragraph> <Paragraph position="8"> The above-mentioned framework based on the compositionality principle cannot provide appropriate treatment for stylistic gaps of types 2.1 and 2.2, because wide-range structure handling, as well as the replacement of some class words, is necessary instead of the local and bottom-up structure handling that includes some treatment of function words. For type 2.3, the above framework does not suit the treatment of the gaps if the transfer is done at the analysis-tree level and some function words exist in the source structure for the transfer. It is not difficult to handle gaps of type 2.4 except for those caused by tense, aspect, and modality, because they can be bridged only by local treatment of constituents instead of wide-range restructuring. For example, if a system finds the consecutive words a number of in a sentence, the system can exceptionally treat it as one word meaning many in the previous framework. It is normally translated by replacing it with a target-language equivalent.</Paragraph> <Section position="1" start_page="0" end_page="0" type="sub_section"> <SectionTitle> 3.2 TWO-STEP TRANSFER METHOD </SectionTitle> <Paragraph position="0"> To deal with stylistic gaps effectively in a system based on the transfer method, we propose the incorporation of a specific sub-component for wide-range restructuring of the intermediate structures in the transfer component, as shown in Figure 4. This gives an example of a system configuration for English-to-Japanese machine translation. The basic transfer consists of lexical transfer and reordering of words.</Paragraph> <Paragraph position="1"> The wide-range restructuring should be done after analysis of the input sentence and before the basic transfer. We take advantage of syntactic clues given in the intermediate representation for effective restructuring after analysis of the input. The wide-range restructuring, which changes the global structure as well as some class words of the sentence, should be performed not after but before the basic transfer, for the following reasons.</Paragraph> <Paragraph position="2"> 1. The restructuring makes the basic transfer easier and it also reduces the transfer rules, because it often contributes to standardization or limitation of English sentence styles, as discussed in more detail in Section 3.3 2. The restructuring is not affected by transfer errors, which often occur because of the complexity of the transfer process.</Paragraph> <Paragraph position="3"> By means of this restructuring sub-component, the intermediate representation of the input sentence is transformed or reinterpreted from a source-dependent expression into a target-dependent one. We can define augmented CFGs for analysis and generation in this framework. If we design the</Paragraph> <Paragraph position="5"> rule appropriately and control for the wide-range restructuring sub-component, the output structures of both the sub-component and the basic transfer sub-component can be defined by using augmented CFGs that deal with conditions for rule applications. In other words, the basic transfer sub-component can specialize in transfer from one augmented CFG system to another, as illustrated in Figure 2.</Paragraph> <Paragraph position="6"> Because wide-range restructuring, which does not suit the compositionality principle, can be performed entirely in the restructuring sub-component, and because the basic transfer can be simplified and specialized in local and bottom-up treatments of structures based on the augmented CFG formalism, as mentioned above, all the processes of machine translation except wide-range restructuring can be based on the augmented CFG formalism or the compositionality principle. This approach makes the whole system simple, easy to control, and efficient.</Paragraph> <Paragraph position="7"> If a machine translation system uses analysis-tree structures as intermediate structures (Lehmann et al. 1981; Nitta et al. 1982), wide-range restructuring can be introduced appropriately at the surface level. If the system performs deep analysis of the input sentence and creates a semantic representation such as a frame-like structure or a semantic network as an intermediate representation, wide-range restructuring may be required at the deep level. This is true whenever we handle stylistic gaps of types 2.1 and 2.2. However, gaps of type 2.3 can be handled by analysis, and no wide-range restructuring is required from the system that performs deep analysis of the input sentence.</Paragraph> </Section> <Section position="2" start_page="0" end_page="0" type="sub_section"> <SectionTitle> 3.3 ADVANTAGE OF THE TWO-STEP TRANSFER </SectionTitle> <Paragraph position="0"/> </Section> </Section> <Section position="7" start_page="0" end_page="0" type="metho"> <SectionTitle> METHOD OVER THE SINGLE-STEP TRANSFER METHOD </SectionTitle> <Paragraph position="0"> Let us discuss the advantage of this approach over the conventional single-step transfer method from the standpoint of maintainability.</Paragraph> <Paragraph position="1"> Technical documents contain many variants of sentence patterns. The examples in Section 2 are regarded as variants from the viewpoint of English-to-Japanese translation. As a matter of fact, several different English sentences in an English technical document can often be translated by the same Japanese sentence. In other words, a wide variety of expression in English can be reduced to some extent in Japanese, because the most important concern in technical documents is that each sentence should convey technical information correctly. Therefore, we may standardize or control styles of English sentences for the sake of English-to-Japanese translation.</Paragraph> <Paragraph position="2"> The two-step transfer method including wide-range restructuring is an appropriate way to take advantage of this phenomenon. If we encounter a new variant of a sentence pattern in English, we only have to write an English restructuring rule in the case of the two-step transfer method. On the other hand, a whole transfer rule, which is usually harder to write, is needed in the single-transfer method. If we want to modify a target Japanese sentence that corresponds to some English sentences, we only have to Computational Linguistics Volume 16, Number 2, June 1990 75 Taijiro Tsutsumi Intermediate Representations in Machine Translation modify the corresponding basic transfer rule, instead of modifying all the transfer rules for these English sentences.</Paragraph> <Paragraph position="3"> Consequently, it is easier to maintain the transfer rules if the system is based on the two-step transfer method, especially in translating technical documents.</Paragraph> </Section> <Section position="8" start_page="0" end_page="0" type="metho"> <SectionTitle> 4 IMPLEMENTATION OF THE WIDE-RANGE RESTRUCTURING FUNCTION </SectionTitle> <Paragraph position="0"> A prototype English-to-Japanese machine translation system, SHALT (Tsutsumi 1986), is based on the two-step transfer method described in Section 3.2. So far we have developed about 500 wide-range restructuring rules to cope with the stylistic gaps exemplified in Section 2, and we have confirmed the effectiveness of the restructuring through test translation of a few IBM computer manuals.</Paragraph> <Paragraph position="1"> In this section, we discuss the details of the rules for the wide-range restructuring and their applications in SHALT, as an example. SHALT is implemented in LISP, and the English and Japanese intermediate representations are syntactic-analysis tree structures.</Paragraph> </Section> <Section position="9" start_page="0" end_page="0" type="metho"> <SectionTitle> 4.1 WIDE-RANGE RESTRUCTURING RULES AND THEIR APPLICATIONS </SectionTitle> <Paragraph position="0"> A wide-range restructuring rule consists of a pair of a matching pattern and a target pattern. If an input English tree structure matches a matching pattern, then a target Japanese-like English tree structure is generated according to specifications in a target pattern. A matching pattern is defined as follows. Note that * allows repetition of specifications. null of a structure), which has already been set by MATCH-ING-ELEMENTs in an earlier matching process, is a target for checking. A sequence of MATCHING-ELE-MENTs checks a sequence of daughter tree structures. If specified MATCHING-CONDITIONs match a structure, a specified MATCHING-VARIABLE is set to the structure. If a MATCHING-ELEMENT is a mere MATCH-ING-VARIABLE, any structure or nil can be set for the variable. MATCHING-CONDITION specifies a LISP function and its arguments. LISP functions check parts of speech, terminal symbols, or other information of a structure. All specifications in a matching pattern form AND conditions, except arguments of LISP functions, which form OR conditions.</Paragraph> <Paragraph position="1"> A target pattern specifies the required output structure by using MATCHING-VARIABLEs where structures are already set and by adding new structures.</Paragraph> <Paragraph position="2"> Figure 5 shows an example of a wide-range restructuring rule and its application. Figure 5 (a) shows the output of English analysis, which is the input for wide-range restructuring. Figure 5 (b) shows a wide-range restructuring rule and (c) gives the output of the restructuring.</Paragraph> <Paragraph position="3"> The left-hand side of the restructuring rule is a matching pattern, and the right-hand side of the rule is a target pattern in Figure 5 (b). Numbers preceded by *, such as * 1, * 2, and *3, denote MATCHING-VARIABLEs. There are four specifications of (STRUCTURE- (MATCHING-ELEMENT*)) in the matching pattern, such as (0- (*1</Paragraph> <Paragraph position="5"> symbol of the tree should be &quot;it.&quot; (P ADJ) denotes that the part of speech of the root node should be ADJ (i.e., adjective). T and P are the LISP function names to perform these specific checks.</Paragraph> <Paragraph position="6"> The target pattern in Figure 5 (b) specifies that the</Paragraph> <Paragraph position="8"> important for the user to specify the file that the user specify the file B J- important (c) Output of the Wide-Range Restructuring. *9, and *7 should be used and that some new tree structure should be added to form the output tree structure. We can directly specify the output tree structure by using parentheses &quot;(&quot;and&quot;),&quot; and node names, such as VP and COMPL. LISP functions can also be specified to generate new elements. LISP function names are distinguished by a preceding &quot;!,&quot; as in !SN. (!SN NP) results in a new node name, NPXXX (XXX is a unique number in a LISP environment) for identification. (!APP-TERM &quot;B J-&quot; *9) denotes that a new symbol concatenating &quot;B J-&quot; and the value of *9 should be created. &quot;B J-important&quot; in Figure 5 (c) means that &quot;important&quot; in this case should be treated as a predicative adjective.</Paragraph> <Paragraph position="9"> These specifications for the wide-range restructuring rules were found to be user-friendly in our experience of developing a practically sized rule set.</Paragraph> <Paragraph position="10"> The wide-range restructuring rules are categorized into about 20 groups according to their functions. This categorization is more detailed than the one described in Section 2. These groups and rules in each group are arranged sequentially so that more specific and local rules can come earlier when they are checked. Checking and application of these rules are done along an input tree in top-down and left-to-right manner. If one of the rules in a group has successfully been applied to an input tree, then the rest of the rules in the same group are no longer checked, and the process goes to the next rule group. After all the groups have been checked and applied to the input tree, the process goes to the next daughter tree of the input tree. When the process goes to a new tree, the system checks the category name of its root node and thus avoids useless checking of the tree.</Paragraph> <Paragraph position="11"> Because all the rules are used in a fixed sequence, they can be easily maintained.</Paragraph> <Paragraph position="12"> Figure 6 shows the output of the basic transfer that follows the process of the wide-range restructuring. As we compare the output of the wide-range restructuring, which is the input of the basic transfer, in Figure 5 (c) with the tree structure in Figure 6, we can see how the basic transfer is done. For example, sub-trees COMPL, NP3, VERB2, NP2, VP, and VERB3 in Figure 5 (c) are transferred to sub-trees JANOUN, JNPPART3, JVP2, JNPPART2, JNC, and JVP3 in Figure 6, respectively. This example shows that the basic transfer is more straightforward and localized than the wide-range restructuring.</Paragraph> </Section> <Section position="10" start_page="0" end_page="0" type="metho"> <SectionTitle> JS </SectionTitle> <Paragraph position="0"> r ............ L ..................... 1 JNPPART JVP3 r ...... +- ......................... 1 ~C JPART f ...... L ......................... 1 ~S JAN0~ r ......... t ...... Y .............. 1 I ~PPART3 JNPPART2 JVP2 J r---+-l .... r---+-l .... I I JNOUH JPART JNOUN JPART I I I I I I I I yuza 8a fairu wo shiteisuru koto ha Jyuyou</Paragraph> </Section> <Section position="11" start_page="0" end_page="0" type="metho"> <SectionTitle> 4.2 FURTHER DISCUSSIONS ON IMPLEMENTATION </SectionTitle> <Paragraph position="0"> Let us discuss example (5-a) in Section 2. The wide-range restructuring rule is as follows. If the main verb is have and the head noun (rate) of the object is a two-place predicate and there is an adjective (low) that modifies the head noun, then restructure it as shown in (5-b). If the head noun of the object is classified as &quot;ATTRIBUTE,&quot; the restructuring is obligatory. Otherwise, translation without this restructuring is not very good, but acceptable.</Paragraph> <Paragraph position="1"> The restructuring rule for case (l-a) in Section 2 is slightly complicated because we need richer information, such as (room contains table), so as to restructure (l-a) into the form 'NP1 be in NP2.' If the input is The table has four legs, it will be restructured differently into the form Four legs exist for the table because of the above constraint. This is not standard English, but it is very similar in form to Japanese.</Paragraph> <Paragraph position="2"> We have not yet implemented a way of using semantic information, such as (room contains table), as constraint, because the desired restructuring can be done on the basis of syntactic restrictions in the field of IBM computer manuals. However, the approach proposed in this paper can be augmented to handle semantic information without any crucial problems, if we prepare a knowledge base.</Paragraph> </Section> class="xml-element"></Paper>