<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-0105">
  <Title>Semantic Analysis of Chinese Garden-Path Sentences</Title>
  <Section position="5" start_page="33" end_page="34" type="metho">
    <SectionTitle>
3 Sentence Degeneration model (SD)
</SectionTitle>
    <Paragraph position="0"> The Sentence Degeneration model, which is one model of the Hierarchical Network of Concepts theory (HNC), focuses on representing the subordinate clause in a sentence. The theory of the Hierarchical Network of Concepts (HNC theory), founded by Prof. Zengyang Huang of the Institute of Acoustics, Chinese Academy of Sciences, is a theoretical approach to Natural Language Processing (NLP). The objective of HNC is to establish natural language representation patterns based on the association veins of concepts, which can simulate the language perception process of the human brain and can be applied to computational Natural Language Understanding.</Paragraph>
    <Paragraph position="1"> Sentence Degeneration (SD) represents the semantic patterns of the subordinate clause in a sentence. There are three types of SD: prototype SD, key-element SD, and packed SD.</Paragraph>
    <Paragraph position="2"> In Prototype SD a subordinate clause wholly acts as one role of the other sentence without any alteration. For example,Zhong Guo Jia Ru Shi Jie Mao Yi Zu Zhi (China joined the WTO) is a complete sentence. However in sentence (3) this sentence acts as the subject ofCu Jin (accelerate). Unlike English, in Chinese there is no relative pronoun, such as that or which, to indicate that this is a subordinate clause. This phenomenon is named Prototype SD.</Paragraph>
    <Paragraph position="3"> (3)Zhong Guo Jia Ru Shi Jie Mao Yi Zu Zhi Hui Cu Jin Quan Qiu Jing Ji De Fa Zhan (That China joined the WTO will accelerate the development of global economics.).</Paragraph>
    <Paragraph position="4"> Key-element SD involves an NP which semantically is an attributive clause. For example, although in sentence (4)Jia Ru Shi Jie Mao Yi Zu Zhi De Zhong Guo is an NP, it can be transformed from the sentenceZhong Guo Jia Ru Shi Jie Mao Yi Zu Zhi by moving the subjectZhong Guo to the tail and adding the Chinese wordDe (of or 's) in front of it. We look at this NP as a specific attributive clause1 in Chinese, and look atZhong Guo as the core concept of this clause. Because the core concept of this clause is the subject, which is the key element, this phenomenon is called key-element SD. Besides the subject, the object and the verb of the sentence can be the core of key-element SD. For example, in sentence (5)Zhong Guo Dui Shi Jie Jing Ji De Ying Xiang is one key-element SD transformed from the sentenceZhong Guo Ying Xiang Shi Jie Jing Ji , and the verbYing Xiang is its core.</Paragraph>
    <Paragraph position="5">  uter is a prototype SD or key-element SD. For example, in sentence (6) and (7) both noun phrasesZhong Guo Jia Ru Shi Jie Mao Yi Zu Zhi De Xiao Xi and Zhong Guo Dui Shi Jie Jing Ji De Ying Xiang Cheng Du are Packed SD's. Moreover, the attributer ofXiao Xi isZhong Guo Jia Ru Shi Jie Mao Yi Zu Zhi which is a prototype SD, and the attributer ofCheng Du isZhong Guo Dui Shi Jie Jing Ji De Ying Xiang which is a key-element SD. The wordsXiao Xi andCheng Du are called packed words.</Paragraph>
    <Paragraph position="6"> (6)Zhong Guo Jia Ru Shi Jie Mao Yi Zu Zhi De Xiao Xi Ling Ren Ji Dong (The news that China joined WTO is exciting.) (7)Zhong Guo Dui Shi Jie Jing Ji De Ying Xiang Cheng Du Jiang Yue Lai Yue Da (The degree of influence that Chinese economics impacts on the world is deeper and deeper.) Let ElJ be the semantic structure of the subordinate clause, GBKi be the subject/object, and El be the verb of the clause. The semantic pattern of the clause can be given as ElJ=GBK1+El+GBK2+GBK3, where GBK2 and GBK3 can be absent and the position of GBKi can be changed. Suppose ElJ-GBKi stands for the action of subtracting the GBKi from ElJ, ElJ-El stands for subtracting the El. The seman- null tic patterns of SD can be given as follows: 1. ElJ. It means that ElJ is a prototype SD.</Paragraph>
    <Paragraph position="7"> 2. (ElJ-GBKi)+De +GBKi. It means that this key-element SD can be transformed from the clause ElJ by moving GBKi to the tail and adding the Chinese wordDe in front of GBKi.</Paragraph>
    <Paragraph position="8"> 3. (ElJ-El)+De +El. It means that this key-element SD can be transformed from the clause ElJ by moving El to the tail and adding the Chinese wordDe in front of El. Although this El looks like a noun because there is Chinese wordDe in front of it, it is regarded as a verb when restored back to the ElJ.</Paragraph>
    <Paragraph position="9"> 4. a prototype SD or key-element SD+{De }+noun. It means the three patterns above  can serve as the attributer of the packed SD.</Paragraph>
    <Paragraph position="10"> Although the key-element SD and packed SD look like NP's in Chinese, they need to be transformed back into clauses during semantic analysis. It means that in patterns 2 and 3 the GBKi and El have to be restored into ElJ. This is why we named these phenomena Sentence Degeneration. Moreover, in patterns 2 and 3, the Chinese wordDe is necessary to indicate the transformation, and we call it a sign of SD.</Paragraph>
    <Paragraph position="11"> Therefore, if an NP or other structure includes a verb and the Chinese wordDe , it has to be analyzed as one type of SD. These semantic patterns of SD are useful for describing the interpretation of temporarily ambiguous verb structures, such as those in garden-path sentences.</Paragraph>
  </Section>
  <Section position="6" start_page="34" end_page="37" type="metho">
    <SectionTitle>
4 Semantic Model of Chinese Gar-
den-Path Sentence
</SectionTitle>
    <Paragraph position="0"> Based on the Sentence Degeneration model, there are two types of Chinese Garden-Path Sentences: SD type ambiguity garden-paths and NP allocated ambiguity garden-paths.</Paragraph>
    <Paragraph position="1"> A temporarily ambiguous verb structure in a sentence always has more than one semantic interpretation that can be represented as a type of SD. This phenomenon we call SD type ambiguity.</Paragraph>
    <Paragraph position="2"> If an SD type ambiguity includes a prototype SD, a garden-path arises. For example, an ambiguous structure likeYao Si Xi Ren De Gou has two different interpretations as A and B in sentence (1) and (2): A. It is a key-element SD in sentence (1), whereGou (dog) is the subject ofYao Si (kill), and Xi Ren (hunter) is the object ofYao Si (kill).</Paragraph>
    <Paragraph position="3"> B. It is a prototype SD in sentence (2), where Gou (dog) is the object ofYao Si (kill), andXi Ren (hunter) is the attributer ofGou (dog).</Paragraph>
    <Paragraph position="4"> Obviously,Yao Si Xi Ren De Gou has SD type ambiguity, and one type of SD is prototype SD.</Paragraph>
    <Paragraph position="5"> Therefore, sentence (1) and sentence (2) are garden-path sentences.</Paragraph>
    <Paragraph position="6"> An NP allocated ambiguity garden-path is a sentence in which one NP can be both the object of v1 and the subject of v2. Given the structure NP1+v1+NP2+v2+NP3, if NP1+v1+NP2 is a clause, NP2+v2+NP3 is a clause, too; there is an ambiguity about whether NP2 serves as either the object of the first clause or the subject of the second clause. Unlike the garden-path that arises from an SD type ambiguity, NP allocated ambiguity garden-paths confuse the main verb of the sentence. For example, Sentence (8) has two different interpretations as A and B. The difference in the two interpretations is the role of the solution. So, sentence (8) is a garden-path sentence with an NP allocated ambiguity.</Paragraph>
    <Paragraph position="7"> (8)Zhe Ge Xue Sheng Wang Ji Da An Zai Shu De Bei Hou (The student forgot the solution was in the back of the book.) A. the solution is the subject of was, the main verb is forgot; the solution was in the back of the book, which is a prototype SD, is the object of  forgot.</Paragraph>
    <Paragraph position="8"> B. the solution is the object of forgot, the main verb is was, the student forgot the solution, which is a prototype SD, is the subject of was.</Paragraph>
    <Paragraph position="9"> We can see that it is necessary for both types of garden-path that NP1+v1+NP2 be a clause. If there is an NP allocated ambiguity garden-path, NP1+v1+NP2 is a clause together with NP2+v2+NP3 as a clause. If there is an SD type ambiguity garden-path, NP1+v1+NP2 has to be a prototype SD together with one of other two types of SD (Key-element SD or packed SD).</Paragraph>
    <Paragraph position="10"> Thus, this clause, NP1+v1+NP2, is called a garden-path detecting signal.</Paragraph>
    <Paragraph position="11"> Therefore, in our model the garden-path is represented as one of two types of ambiguity: the SD type ambiguity and NP allocated ambiguity.</Paragraph>
    <Paragraph position="12"> Garden-path processing involves detecting and analyzing these two types of ambiguities.</Paragraph>
    <Paragraph position="13">  5 Algorithm for processing Chinese Garden-Path Sentences A Chinese Garden-Path Sentence is processed in four steps: (1) Initially, v1 is analyzed as the main verb. (2) When v2 is encountered, if there is a clause before v2, this is a garden-path detecting signal. It is necessary to detect and analyze the garden-path in this sentence.</Paragraph>
    <Paragraph position="14"> (3) Detect if v1 and v2 can give rise to a garden-path (see section 5.1).</Paragraph>
    <Paragraph position="15"> (4) Determine the main verb of the sentence and the semantic interpretation of the gar- null den-path sentence (see section 5.2).</Paragraph>
    <Section position="1" start_page="35" end_page="36" type="sub_section">
      <SectionTitle>
5.1 Garden-path detection
</SectionTitle>
      <Paragraph position="0"> Given an input string S, suppose its grammatical structure is NP1+v1+NP2+v2+NP3, where NP1 and NP3 can be absent. Therefore, a garden-path detecting signal means that NP1+v1+NP2 is a clause.</Paragraph>
      <Paragraph position="1"> The garden-path can be detected in two steps as follows: Step 1: test if there is SD type ambiguity in NP1+v1+NP2.</Paragraph>
      <Paragraph position="2"> We can look at the clause NP1+v1+NP2 as a prototype SD without any change. If this prototype SD can be analyzed as another type of SD, such as key-element or packed SD, an SD type ambiguity is found, and the input S is a garden-path sentence. Otherwise, if there is no SD type ambiguity, the input S is a non garden-path sentence.</Paragraph>
      <Paragraph position="3"> As mentioned above, sentence (1) has an ambiguity between a prototype and a key-element SD, and it is a garden-path sentence. Consider another sentence (9), with grammatical structure NP1+v1+NP2+v2. Because the Chinese word De (of) in NP2 is a sign of SD, the structure can be rewritten as NP1+v1+NP21+De +NP22+v2.</Paragraph>
      <Paragraph position="4"> (9)Xiao Wang Yan Jiu Lu Xun De Wen Zhang Fa Biao Liao (The paper which Mr. wang research on Luxun is published.) The structure NP1+v1+NP21+De +NP22 can be analyzed in two different ways as follows. Obviously there is an ambiguity between prototype SD and packed SD, and sentence (9) is a garden-path sentence.</Paragraph>
      <Paragraph position="5"> A. It is a prototype SD, whereWen Zhang (paper) is the object ofYan Jiu (research), andWen Zhang (paper) was written byLu Xun (Luxun).</Paragraph>
      <Paragraph position="6"> B. It is a packed SD, whereLu Xun (Luxun) is the object ofYan Jiu (research), andWen Zhang (paper) was written byXiao Wang (Mr. wang).</Paragraph>
      <Paragraph position="7"> Although the structure v1+NP2+v2 in sentence (1) and the structure NP1+v1+NP2+v2 in sentence (9) can give rise to garden-paths, not all the instances of these two structures are like this. For example, in sentence group (10)Nian Qing Ren (younger) andDao (knife) disfavor being objects ofRe Ai (love) andXue (peel), soRe Ai Zu Guo De Nian Qing Ren is only analyzed as a key-element SD, and Xiao Wang Xue Ping Guo De Dao is only analyzed as a packed SD. There is no garden-path detecting signal, so these sentences are non garden-path sentences.</Paragraph>
      <Paragraph position="8"> (10)Re Ai Zu Guo De Nian Qing Ren Hui Guo Liao (The younger who love his country go back.) Xiao Wang Xue Ping Guo De Dao Bu Jian Liao (The knife with which Mr. wang peeled the apple is lost.) Furthermore, in sentence group (11), v1+NP2 is a clause, so there is a garden-path detecting signal. However,Pi (fruit skin) disfavors being the subject ofXue (peel), andMen (door) is not a packed word, soXue Ping Guo De Pi andXiao Wang Tui Kai Fang Jian De Men are only analyzed as prototype SD.</Paragraph>
      <Paragraph position="9"> There is no SD type ambiguity, so these sentences are non garden-path sentences.</Paragraph>
      <Paragraph position="10">  (11)Xue Ping Guo De Pi Yao Xiao Xin (Peeling the apple need to be careful.) Xiao Wang Tui Kai Fang Jian De Men Zou Liao (Mr. wang opened the door and went away.) Step 2: test if NP2+v2+NP3 is a clause.</Paragraph>
      <Paragraph position="11">  If NP2+v2+NP3 is not a clause, definitely there is no NP allocated ambiguity, and the sentence is not a garden-path sentence. For example,  in sentence (12)Yi La Ke Qi Yin Yu Neng Yuan Wei Ji (Iraq is due to the crisis of energy) is not a clause, so sentence (12) is a non garden-path sentence.</Paragraph>
      <Paragraph position="12"> (12)Mei Guo Da Ji Yi La Ke Qi Yin Yu Neng Yuan Wei Ji (That USA attacked Iraq is due to the crisis of energy) If NP2+v2+NP3 is a clause, there are two interpretations for v1 and v2.</Paragraph>
      <Paragraph position="13"> First, v1 and v2 are serial verbs, and the sentence can be divided into two separate sentences; one is NP1+v1+NP2, the other is NP2+v2+NP3 and the subject of v2 is NP2. For example, sentence (13) can be divided into sentences (14) and (15). This phenomenon can be interpreted as sentence (15) sharingDa Hui (conference) with sentence (14), which is not NP allocated ambiguity, so the sentence (13) is a non garden-path sentence.</Paragraph>
      <Paragraph position="14"> (13)Wen Jian Jiang Ti Jiao Gei Da Hui Tao Lun (The file will be given to the conference to discuss.) (14)Wen Jian Jiang Ti Jiao Gei Da Hui (The file will be given to the conference.) (15)Da Hui Tao Lun Zhe Ge Wen Jian (The conference will discuss the file.) Second, one of v1 and v2 is the main verb of the sentence, and NP2 has to be in NP1+v1+NP2 or NP2+v2+NP3, and cannot be shared. For example, in sentence (8), the solution cannot be shared by forgot and was. Absolutely this is an NP allocated ambiguity, and the sentence is a garden-path sentence.</Paragraph>
      <Paragraph position="15"> The difference between a serial verb interpretation and an NP allocated ambiguity interpretation is the semantic information of the two verbs. Suppose VS(pro) is the set of all verbs whose subject can be a prototype SD, VO(pro) is the set of all verbs whose object can be a prototype SD. Verbs about mental acts, emotions or other human feelings, such as forget, worry, cry, belong to the VS(pro). Verbs about propositions, causes and results, such as be, result in, be due to, belong to both VO(pro) and VS(pro).</Paragraph>
      <Paragraph position="16"> If NP2+v2+NP3 is a clause, and if v1 is not one of VO(pro) and v2 is not one of VS(pro), the sentence is a non garden-path sentence and these two verbs are serial verbs. Otherwise, the sentence is a garden-path sentence.</Paragraph>
    </Section>
    <Section position="2" start_page="36" end_page="37" type="sub_section">
      <SectionTitle>
5.2 Garden-path analysis
</SectionTitle>
      <Paragraph position="0"> A garden-path is always affected by the selection of the main verb of a sentence. In the garden-path caused by SD ambiguity, v1 is regarded as the main verb initially, however, in the end, v2 is the real main verb. In the garden-path caused by NP allocated ambiguity, both v1 and v2 can be the main verb. So, the garden-path analysis includes two steps: the first step is determining the main verb of the sentence; the second step is disambiguating the SD type or the NP allocated ambiguity, and determining the semantic structure of the sentence.</Paragraph>
      <Paragraph position="1"> Given a garden-path sentence with grammatical structure NP1+v1+NP2+v2+NP3, the analysis process is as follows: First, if an SD type ambiguity is detected, it means NP1+v1+NP2 can be a prototype SD and key-element or packed SD, and v2 always is the main verb of the sentence. The ambiguity can be processed as in Figure 1. For example, In sentences (1) and (2),Shi (is) is one of VS(pro) and Tao Pao (run away) is not, soYao Si Xi Ren De Gou is processed as a key-element SD in sentence (1) and a prototype SD in sentence (2).</Paragraph>
      <Paragraph position="2"> Second, if an NP allocated ambiguity is detected, it means that both NP1+v1+NP2 and NP2+v2+NP3 can be clauses. The main verb can be determined in Figure 2. The NP allocated ambiguity can be processed as in Figure 3.</Paragraph>
      <Paragraph position="3"> (16)Zhang Xian Sheng Kan Jian Li Xiao Jie Zheng Zai Tiao Wu (Mr. Zhang saw Miss. Li dancing.) The result of garden-path analysis is a semantic structure for the sentence. In Figures 1 and 3, a flag of prototype SD, key-element SD and packed SD, which indicates the semantic interpretation, is added to the grammatical structure of the sentence. Therefore, the main verb, which is always outside the flag, and the semantic structure of the sentence are both represented.</Paragraph>
      <Paragraph position="4">  indicating that the content in it is prototype SD, &lt; &gt; is the flag of key-element SD, and { } is the flag of packed SD.</Paragraph>
      <Paragraph position="5">  indicating that the content in it is prototype SD.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>