File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/92/a92-1028_metho.xml
Size: 13,249 bytes
Last Modified: 2025-10-06 14:12:56
<?xml version="1.0" standalone="yes"?> <Paper uid="A92-1028"> <Title>Zero Pronoun Resolution in a Machine Translation System by using Japanese to English Verbal Semantic Attributes.</Title> <Section position="4" start_page="203" end_page="204" type="metho"> <SectionTitle> 4 Classification of Verbal Semantic Attributes </SectionTitle> <Paragraph position="0"> As mentioned in the preceding chapter, the resolution of certain types of zero pronouns that could not be dealt with by conventional methods, may now be resolved by using semantic information. Therefore, in this chapter, the verbal semantic attributes will be categorized for the purpose of resolving zero pronouns using only linguistic knowledge (i.e. not world knowledge), The referent of zero pronouns will be determined by the relationship between attributes.</Paragraph> <Paragraph position="1"> Japanese verbs will be categorized using the following 2 viewpoints.</Paragraph> <Paragraph position="2"> The conceptual system of verbs as categorized by these standards is shown in Figure 1.</Paragraph> <Paragraph position="3"> Next, we consider the relationship between verbs, by examining the information regarding the relationships within sentences containing zero pronouns and assess whether this information will be furnished anew to sentences containing the referent. The verbal semantic attribute (VSA) between verbs governing the referent and the verb governing the zero pronoun can be summarized in the form shown in to make an assumption of verbal relationship and to determine the referential elements of zero pronouns based on the relationship of the two factors of verbal semantic attributes.</Paragraph> <Paragraph position="4"> As mention,ed in Chapter 3, the first sentence of the lead paragraph in a newspaper article often consists of a discourse structure that presents an outline of the contents of the entire article. Here, we shall refer to a unit sentence of this type as a &quot;topicalized unit sentence&quot;, and based on its semantic attributes, the referents of zero pronouns in sentences that follow will be selected.</Paragraph> <Paragraph position="5"> By relying on the categorization of verbal semantic attributes, and observing the rules for determining the referential elements of zero pronouns as described by its attribute value, we find that it is possible to describe multi-purpose anaphora resolution analysis rules which do not rely on the target domain of the analysis. Thus because, the information that is required for analysis is contained within the scope of linguistic knowledge, anaphora resolution el zero pronouns using this method can be applied to machine translation.</Paragraph> </Section> <Section position="5" start_page="204" end_page="205" type="metho"> <SectionTitle> 5 Format of Anaphorai Resolution </SectionTitle> <Paragraph position="0"/> <Section position="1" start_page="204" end_page="204" type="sub_section"> <SectionTitle> 5.1 Algorithm </SectionTitle> <Paragraph position="0"> The structure of the system for resolution of zero pronouns using verbal semantic attributes is shown in Figure 2. The Japanese sentence to be analyzed has already undergone morphological analysis, syntactic/semantic analysis, and the results are input to context analysis. In context analysis, anaphora resolution of zero pronouns is conducted as follows.</Paragraph> <Paragraph position="1"> (Step 1) --Detection of zero pronouns.</Paragraph> <Paragraph position="2"> If they exist, examine whether there are referents within the same sentence.</Paragraph> <Paragraph position="3"> If they exist, and resolution is concluded, proceed constraints where anaphoral elements determine the syntactic structure depending on the type of postpositional particle and of conjunctions. A portion of the rules for determining anaphoral elements depending on the type of conjunctions is shown in Table3. &quot;to'(when) The second method is when, within the same sentence, anaphoral elements cannot be determined based on conjunctions (for example, when three or more types of unit sentences exist within the same sentence), anaphoral resolution is then conducted using VSA.</Paragraph> <Paragraph position="4"> (Step 2)--When they do not exist within the same sentence,referent candidates are selected from among the case elements of topicalized unit sentences that are retained within the contextual information stage sector, The standard for selection will be based on the relationship between VSA of verbs governed by zero pronouns and VSA of topicalized unit sentences and on the rules for designating verbs given in Table 2. When constraints by verbs are satisfied, anaphoral relationships become valid and proceed to Step 4. (Step 3)--When the referent cannot be detected, handle as &quot;processing impossible&quot;.</Paragraph> <Paragraph position="5"> Based on the semantic restrictions imposed on the zero pronoun by the verbs, conjecture anaphoral elements.</Paragraph> <Paragraph position="6"> (Step 4)--From the knowledge base for sentence structure control, use the rules for extraction of topicalized unit sentences determined by relying on the sentence structure of target field of analysis 1 to select the topicalized unit sentence and have the context information retaining sector retain the sentence.</Paragraph> <Paragraph position="7"> Proceed to the next sentence.</Paragraph> <Paragraph position="8"> sub sent.<-->main sent. &quot;ha&quot;(FOP/SUBJ), &quot;ga&quot;(SUBJ) &quot;wo&quot;(OSJ) Table 3 Constraints to Zero Pronouns and their referent with Connecting Words * The arrows go from the sentence which include referents to the sentence including the zero pronouns capable of correspondence.</Paragraph> <Paragraph position="9"> ** In the ease of &quot;tsutsu&quot; and &quot;nagara&quot;, the &quot;we&quot; case will become the target of referents only when its connection is &quot;CONTRARY-AFFIRMATIVE&quot;(This type of connection is translated as &quot;although&quot; in our system)</Paragraph> </Section> <Section position="2" start_page="204" end_page="205" type="sub_section"> <SectionTitle> 5.2 Examples </SectionTitle> <Paragraph position="0"> Using the example sentence (6) and using the technique mentioned here, an example of zero pronoun resolution is given in (7).</Paragraph> <Paragraph position="1"> article becomes the topicalized unit sentence. When the first sentence consists of a number of unit sentences, set an order of priority for the topicalized unit sentence depending on the type of conjunction used. Specifically, in the case of compound sentences, rules such as the main sentence taking precedence will be applied</Paragraph> </Section> </Section> <Section position="6" start_page="205" end_page="206" type="metho"> <SectionTitle> (SUBJ &quot;NTT&quot;)(OBJ &quot;new model switchboard&quot;)) </SectionTitle> <Paragraph position="0"> The results of analyzing the first sentence are used to extract the topicalized unit sentence. In example (7), the first sentence is structured from the unit sentence and the result of analysis is stored in the context information storage sector as the topicalized unit sentence. Next, from the analysis results of the second sentence, it can be understood that the subjects of &quot;tousaisuru (is outfitted with or equipped with)&quot; and &quot;yoteida (is planning to)&quot; have been converted to zero pronouns. Since there are no referents within the same sentence, the case element within the topicalized unit sentence becomes the referent candidate. The VSA of &quot;tousaisuru&quot; and &quot;yoteida&quot; are respectively, &quot;POSS&quot;, &quot;THINK-ACT&quot;, and the VSA of topicalized unit sentence verb are &quot;POSS-TRANS2&quot; and &quot;START&quot;. Thus, according to the rules given in Table 2, &quot;Detailed explanation&quot; and &quot;Policy decision&quot; are established as the verbal semantic relationships and the object and subject of the topicalized unit sentence respectively, and become the referents.</Paragraph> <Paragraph position="1"> 6 Implementation in a Machine Translation</Paragraph> <Section position="1" start_page="205" end_page="206" type="sub_section"> <SectionTitle> System </SectionTitle> <Paragraph position="0"> The following is an outline of the processing undertaken by the Japanese to English machine translation system, ALT-J/E (See Figure 3). First, a morphological analysis of the input Japanese sentence is conducted, followed by a dependency analysis of elements in the sentence. Unit sentences 2 are extracted based on results of the relationships between verbs, and from these a simple unit sentence 3 is extracted. Subjective expression information such as 2a unit sentence is a part of the sentence in which the tree structure is centered around one predicate in the sentence; there are occasions when embedded sentences are included in a unit sentence.</Paragraph> <Paragraph position="1"> 3a simple unit sentence is one where a unit sentence has been parsed to the level where it has only one predicate..</Paragraph> <Paragraph position="2"> (Ex.(in English) &quot;This is the only paper that contains the news&quot; <- unit sentence &quot;This is the only paper&quot;, &quot;the only paper contains the news&quot; <- simple unit sentences ) modality, tense and aspect is extracted from the simple unit sentence to yield the objective simple unit sentence. This objective simple unit sentence, as shown in Figure 4, is collated with two types of pattern dictionaries having predicates as index words (the idiomatic expression transfer dictionary and the semantic valentz pattern transfer dictionary). When there is no appropriate pattern, a general pattern transfer rule is applied. This determines the syntactic and semantic structure pattern that is used in Japanese to English conversion. In the cases of (3) and (4) in Chapter 2, (1) Morphological analysis: Separation of words, determination of words part of speech (2) Dependency analysis: -Determination of relations between sentence elements (3) J-J conversion: -Conversion of expressions within Japanese (4) Simple sentence extraction: -Determining the scope of influence of all predicates from dependency analysis results (5) Simple sentence analysis: (5.1) Predicate analysis: -Extraction of modality and other elements and conversion to an ordinary sentence (5.2) Gerund phrase analysis: -Determination of semantic structure of gerund phrases and compound words (6) Embedded sentence analysis: -Determination of the semantic structure of embedded sentences (7) Ordinary sentence conversion to English: -Conversion of objective expression by means of pattern dictionary (8) Connection analysis: -Determination of relations between declinable words (9) Optimal result selection: -The best(semantically and syntactically most plausible) interpretation is selected (10) Zero anaphora resolution: -Resolution of zero anaphora by use of contextual information (11) Resolved element conversion: -Determination of the conversion method for resolved zero anaphora (12) Unit sentence generation: (12.1) Basic structure generation: -Determination of the structure of the entire English sentence (12.2) Adverbial phrase generation: -Determination of adverbial phrase translation from modality, tense, verb and other elements 02.3) Noun phrase generation: -Conversion of phrase and compound word structures and embedding of embedded sentences (13) Connecting structure generation: -connection of the unit sentences according to connection attributes and the presence or absence of a subject (14) Modality tense structure generation: (1) bird ...... hen (2) food ... chicken</Paragraph> <Paragraph position="4"> they are not identified during processing as cases of zero pronouns. If numerous interpretations remain at this point, a single and final interpretation is decided on, based on the results of interpretation of the pattern at the objective simple unit sentence level. Also, as seen in (1) and (7) of Chapter 2, when there is a wide difference between the structures in Japanese and English, converting the Japanese structure resulting from analysis to a structure as close as possible to the English expression can make it possible to avoid referential analysis; only the zero pronouns that are used in the English translation need to be treated. If, after the foregoing analysis, zero pronouns still remain, anaphora resolution using the context is conducted as shown in Chapter 5. At this stage, the sentence pattern used in generating the unit sentence is established and all that remains is to use this to generate the backbone expression in English, adding other relevant information such as modality, tense and conjunction. In doing so, care should be taken to avoid the situation where extracting zero pronouns after correspondence analysis results in verbose English. In this case elliptical pronouns and definite articles should be used.</Paragraph> </Section> </Section> class="xml-element"></Paper>