File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/intro/99/w99-0205_intro.xml
Size: 10,795 bytes
Last Modified: 2025-10-06 14:06:55
<?xml version="1.0" standalone="yes"?> <Paper uid="W99-0205"> <Title>Resolution of Indirect Anaphora in Japanese Sentences Using Examples &quot;X no Y (Y of X)&quot;</Title> <Section position="3" start_page="0" end_page="33" type="intro"> <SectionTitle> 1 Introduction </SectionTitle> <Paragraph position="0"> A noun phrase can indirectly refer to an entity that has already been mentioned. For example, &quot;I went into an old house last night. The roof was leaking badly and ...&quot; indicates that &quot;The roof' is associated with &quot;an old house,&quot; which has already been mentioned. This kind of reference (indirect anaphora) has not been thoroughly studied in natural language processing, but is important for coherence resolution, language understanding, and machine translation. We propose a method that will resolve the indirect anaphora in Japanese nouns by using the relationship between two nouns.</Paragraph> <Paragraph position="1"> When we analyze indirect anaphora, we need a case frame dictionary for nouns that contains information about the relationship between two nouns.</Paragraph> <Paragraph position="2"> For instance, in the above example, the knowledge that &quot;roof&quot; is a part of a &quot;house&quot; is required to analyze the indirect anaphora. But no such noun case frame dictionary exists at present. We considered using the example-based method to solve this problem. In this case, the knowledge that &quot;roof&quot; is a part of &quot;house&quot; is analogous to &quot;house of roofi&quot; Therefore, we use examples of the form &quot;X of Y&quot; instead. In the above example, we use linguistic data such as &quot;the roof of a house.&quot; In the case of verbal nouns, we do not use &quot;X of Y&quot; but a verb case frame dictionary. This is because a noun case frame is similar to a verb case frame and a verb case frame dictionary does exist.</Paragraph> <Paragraph position="3"> The next section describes a method for resolving indirect anaphora.</Paragraph> <Paragraph position="4"> 2 How to Resolve Indirect Anaphora Anaphors and antecedents in indirect anaphora have a certain relationship. For example, &quot;yane (roof)&quot; and &quot;hurui ie (old house)&quot; are in an indirect anaphoric relationship which is a part-of relationship. null sakuban aru hurui ie-ni itta.</Paragraph> <Paragraph position="5"> (last night) (a certain) (old) (house) (go) (I went into an old house last night.) yane-wa hidoi amamoride ...</Paragraph> <Paragraph position="6"> (roof) (badly) (be leaking) (.The roof was leaking badly and ... ) (1) When we analyze indirect anaphora, we need a dictionary containing information about relationships between anaphors and their antecedents.</Paragraph> <Paragraph position="7"> We show examples of the relationships between anaphors and antecedents in Table 1. The form of Table 1 is similar to the form of a verb case frame dictionary. We would call a dictionary containing the relationships between two nouns a noun case frame dictionary but no noun case frame dictionary has yet been created. Therefore, we substitute it with examples of &quot;X no Y&quot; (Y of X) and with a verb case frame dictionary. &quot;X no Y&quot; is a Japanese expression. It means &quot;Y of X,&quot; &quot;Y in X,&quot; &quot;Y for X,&quot; etc.</Paragraph> <Paragraph position="9"> \[ex. hikouki (air plain), hune (ship)\] seito (student), kate (he) atai (value), de-ta (data) We resolve the indirect anaphora&quot; using the follow- null ing steps: 1. We detect some elements which could be analyzed by indirect anaphora resolution using &quot;X no Y&quot; and a verb case frame dictionary. When a noun was a verbal noun, we use a verb case frame dictionary. Otherwise, we use examples of &quot;X no V.&quot; For example, in the following example sentences kaiseki (analysis) is a verbal noun, and we use a case frame of a verb kaiseki-surn (analyze) for the indirect anaphora resolution of kaiseki (analysis). The case frame is shown in Table 2. In this table there are two case components, the ga-case (subject) and the wo-case (object). These two case components are elements which will be analyzed in indirect anaphora resolution. denkishingou-no riyouni-ni yotte (electronic detectors) (use) (by) (By using electronic detectors. ) Butsurigakusha-wa tairyou-no deeta-wo (physicist) (a large amount) (data) shuushuudekiru-youni-natta.</Paragraph> <Paragraph position="10"> (collect) (physicists had been able to collect large amounts of data. ) (2) sokode subayai kaiseki-no houhou-ga hitsuyouni-natta. (then) (quick) (analysis) (method) (require) (Then, they required a method of quick analysis.) 2. We take possible antecedents from topics or loci in the previous sentences. We assign them a certain weight based on the plausibility that they are antecedents. The topics/foci and their weights are defined in Table 3 and Table 4. For example, in the case of &quot;I went into an old house last night. The roof was leaking badly and ..., .... an old house&quot; becomes a candidate of the desired antecedent. In the case of &quot;analysis&quot; in example sentence 2, &quot;electronic detectors,&quot; &quot;physicists,&quot; and &quot;large amounts of data&quot; become candidates of the two desired antecedents of &quot;analysis.&quot; In Table 3 and Table 4 such candidates are given certain weights which indicate preference.</Paragraph> <Paragraph position="11"> 3. We determine the antecedent by combining the weight of topics and foci mentioned in step 2, the weight of semantic similarity in &quot;X no Y&quot; or in a verb case frame dictionary, and the weight of the distance between an anaphor and its possible antecedent.</Paragraph> <Paragraph position="12"> For example, when we want to clarify the antecedent of vane (roof) in example sentence 1, we gather examples of &quot;Noun X no vane (roof)&quot; (roof of Noun X), and select a possi- null ble noun which is semantically similar to Noun X as its antecedent. In example sentence 2, when we want to have an antecedent of kaiseki (analysis) we select as its antecedent a possible noun which satisfies the semantic constraint in the case frame of kuichigau (differ) in Table 2 or is semantically similar to examples of components in the case frame. In the ga-case (subject), of three candidates, &quot;electronic detectors,&quot; &quot;physicists,&quot; and &quot;large amounts of data,&quot; only &quot;physicists&quot; satisfies the semantic constraint, human, in the case frame of the verb kaiseki-suru in Table 2. So &quot;physicists&quot; is selected as the desired antecedent of the ga-case. In the wo-case (object), two phrases, &quot;electronic detectors&quot; and &quot;large amounts of data&quot; satisfy the semantic constraints, abstract and product. By using the examples &quot;value&quot; and &quot;data&quot; in the case frame, the phrase &quot;large amounts of data,&quot; which is semantically similar to &quot;data&quot; in the examples of the case frame, is selected as the desired antecedent of the wo-case.</Paragraph> <Paragraph position="13"> We think that errors made by the substitution of a verb case frame for a noun case frame are rare, but many errors occur when we substitute &quot;X no Y&quot; for a noun case frame. This is because &quot;X no Y&quot; (Y of X) has many semantic relationships, in particular a feature relationship (ex. &quot;a man of ability&quot;), which cannot be an indirect anaphoric relationship. To reduce the errors, we use the following procedures. 1. We do not use an example of the form &quot;Noun X no Noun Y=&quot; (Y of X), when noun X is an adjective noun \[ex. HONTOU (reality)\], a numeral, or a temporal noun. For example, we do not use honton (reality) no (of) hannin (criminal) (a real criminal).</Paragraph> <Paragraph position="14"> 2. We do not use an example of the form &quot;Noun X no Noun Y&quot; (Y of X), when noun Y is a noun that cannot be an anaphor of an indirect anaphora. For example, we do not use &quot;Noun X no tsurn (crane),&quot; or &quot;Noun X no ningen (human being).&quot; We cannot completely avoid errors by introducing the above procedure, but we can reduce them to a certain extent.</Paragraph> <Paragraph position="15"> Nouns such as ichibu (part), tonari (neighbor) and betsu (other) need further consideration. When such a noun is a case component of a verb, we use information on the semantic constraints of the verb. We use a verb case frame dictionary as shown in Table 5.</Paragraph> <Paragraph position="16"> takusan-no kuruma-ga kouen-ni tomatte,ita.</Paragraph> <Paragraph position="17"> (many) (car) (in the park) (there were) (There were many cars in the park.) ichibu-wa kith-hi mukatta \[A part (of them)\] (to the north) (went) (A part of them went to the north.) (3) In this example, since ichibu (part) is a ga-case (subject) of a verb mukau(go), we consult the ga-case (subject) of the case frame of mukau (go). Some noun phrases which can also be used in the case component are written in the ga-case (subject) of the case frame. In this case, kate (he) and hune (ship) are written as examples of things which can be used in the case component. This indicates that the antecedent is semantically similar to kare (he) and hune (ship). Since takusan no kuruma (many cars) is semantically similar to hune (ship) in the meaning of vehicles, it is judged to be the proper antecedent.</Paragraph> <Paragraph position="18"> When such a noun as tonari (neighbor or next) modifies a noun X as tonari no X, we consider the antecedent to be a noun which is similar to noun X ga-case (subject) concrete kare (he), hune (ship) n/-case (object) place kouen (park), minato (port) in meaning.</Paragraph> <Paragraph position="19"> ojiisan-wa ooyorokobi-wo-shite ie-ni kaerimashita. (the old man) (in great joy) (house) (returned) \[The old man returned home (house) in great joy,\] okotta koto-wo hitobito-ni hanashimashita (happened to him) (all things) (everybody) (told) (4) (and told everybody all that had happened to him.) tonari-no ie-ni ojiisan-ga mouhitori sunde-orimashita. (next) (house) (old man) (another) (llve) (There lived in the next house another old man.) For example, when tonari (neighbor or next) modifies ie (house), we judge that the antecedent of tonari (neighbor or next) is ie (house) in the first sentence.</Paragraph> </Section> class="xml-element"></Paper>