<?xml version="1.0" standalone="yes"?>
<Paper uid="J91-1002">
  <Title>Word Sentence Lexical Chain</Title>
  <Section position="3" start_page="38" end_page="41" type="concl">
    <SectionTitle>
5. Conclusions
</SectionTitle>
    <Paragraph position="0"> The motivation behind this work was that lexical cohesion in text should correspond in some way to the structure of the text. Since lexical cohesion is a result of a unit of text being, in some recognizable semantic way, about a single topic, and text structure  Computational Linguistics Volume 17, Number 1 analysis involves finding the units of text that are about the same topic, one should have something to say about the other. This was found to be true. The lexical chains computed by the algorithm given in Section 3.2.3 correspond closely to the intentional structure produced from the structural analysis method of Grosz and Sidner (1986). This is important, since Grosz and Sidner give no method for computing the intentions or linguistic segments that make up the structure that they propose.</Paragraph>
    <Paragraph position="1"> Hence the concept of lexical cohesion, defined originally by Halliday and Hasan (1976) and expanded in this work, has a definite use in an automated text understanding system. Lexical chains are shown to be almost entirely computable with the relations defined in Section 3.2.2. The computer implementation of this type of thesaurus access would be a straightforward task involving traditional database techniques. The program to implement the algorithm given in Section 3.2.3 would also be straightforward. However, automated testing could help fine-tune the parameters, and would help to indicate any unfortunate chain linkages. Although straightforward from an engineering point of view, the automation would require a significant effort. A machine-readable thesaurus with automated index searching and lookup is required.</Paragraph>
    <Paragraph position="2"> The texts we have analyzed, here and elsewhere (Morris 1988) are general-interest articles taken from magazines. They were chosen specifically to illustrate that lexical cohesion, and hence this tool, is not domain-specific.</Paragraph>
    <Section position="1" start_page="39" end_page="40" type="sub_section">
      <SectionTitle>
5.1 Improvements on Earlier Research
</SectionTitle>
      <Paragraph position="0"> The methods used in this work improve on those from Halliday and Hasan (1976).</Paragraph>
      <Paragraph position="1"> Halliday and Hasan related words back to the first word to which they are tied, rather than forming explicit lexical chains that include the relationships to intermediate words in the chain. They had no notions of transitivity, distance between words in a chain, or chain returns. Their intent was not a computational means of finding lexical chains, and they did not suggest a thesaurus for this purpose.</Paragraph>
      <Paragraph position="2"> Ventola (1987) analyzed lexical cohesion and text structure within the framework of systemic linguistics and the specific domain of service encounters such as the exchange of words between a client at a post office and a postal worker. Ventola's chain-building rule was that each lexical item is &amp;quot;taken back once to the nearest preceding lexically cohesive item regardless of distance&amp;quot; (p. 131). In our work the related words in a chain are seen as indicating structural units of text, and hence distance between words is relevant. Ventola did not have the concept of chain returns, and transitivity was allowed up to any level. Her research was specific to the domain used. She does not discuss a computational method of determining the lexical chains.</Paragraph>
      <Paragraph position="3"> Hahn (1985) developed a text parsing system that considers lexical cohesion.</Paragraph>
      <Paragraph position="4"> Nouns in the text are mapped directly to the underlying model of the domain, which was implemented as a frame-structured knowledge base. Hahn viewed lexical cohesion as a local phenomenon between words in a sentence and the preceding one. There was also an extended recognizer that worked for cohesion contained within paragraph boundaries. Recognizing lexical cohesion was a matter of searching for ways of relating frames and slots in the database that are activated by words in the text. Heavy reliance is put on the &amp;quot;formally clear cut model of the underlying domain&amp;quot; (Hahn 1985, p. 3). However, general-interest articles such as we analyzed do not have domains that can be a priori formally represented as frames with slot values in such a manner that lexical cohesion will correspond directly to them. Our work uses lexical cohesion as it naturally occurs in domain-independent text as an indicator of unity, rather than fitting a domain model to the lexical cohesion. Hahn does not use the concept of chain returns or transitivity.</Paragraph>
      <Paragraph position="5"> Sedelow and Sedelow (1986, 1987) have done a significant amount of research  Morris and Hirst Lexical Cohesion on the thesaurus as a knowledge source for use in a natural language understanding system. They have been interested in the application of clustering patterns in the thesaurus. Their student Bryan (1973) proposed a graph-theoretic model of the thesaurus. A boolean matrix is created with words on one axis and categories on the other. A cell is marked as true if a word associated with a cell intersects with the category associated with a cell. Paths or chains in this model are formed by traveling along rows or columns to other true cells. Semantic &amp;quot;neighborhoods&amp;quot; are grown, consisting of the set of chains emanating from an entry. It was found that without some concept of chain strength, the semantic relatedness of these neighborhoods decays, partly due to homographs. Strong links are defined in terms of the degree of overlap between categories and words. A strong link exists where at least two categories contain more than one word in common, or at least two words contain more than one category in common. The use of strong links was found to enable the growth of strong semantic chains with homograph disambiguation.</Paragraph>
      <Paragraph position="6"> This concept is different from that used in our work. Here, by virtue of words co-occurring in a text and then also containing at least one category in common or being in the same category, they are considered lexically related and no further strength is needed. We use the thesaurus as a validator of lexical relations that are possible due to the semantic relations among words in a text.</Paragraph>
    </Section>
    <Section position="2" start_page="40" end_page="41" type="sub_section">
      <SectionTitle>
5.2 Further Research
</SectionTitle>
      <Paragraph position="0"> It has already been mentioned that the concept of chain strength needs much further work. The intuition is that the stronger a chain, the more likely it is to have a corresponding structural component.</Paragraph>
      <Paragraph position="1"> The integration of this tool with other text understanding tools is an area that will require a lot of work. Lexical chains do not always correspond exactly to intentional structure, and when they do not, other textual information is needed to obtain the correct correspondences. In the example given, there were cases where a lexical chain did correspond to an intention, but the sentences spanned by the lexical chain and the intention differed by more than two. In these cases, verification of the possible correspondence must be accomplished through the use of other textual information such as semantics or pragmatics. Cue words would be interesting to address, since such information seems to be more computationally accessible than underlying intentions.</Paragraph>
      <Paragraph position="2"> It would be useful to automate this tool and run a large corpus of text through it. We suspect that the chain-forming parameter settings (regarding transitivity and distances between words) will be shown to vary slightly according to author's style and the type of text. As it is impossible to do a complete and error-free lexical analysis of large text examples in a limited time-frame, automation is desirable. It could help shed some light on possible unfortunate chain linkages. Do they become problematic, and if so, when does this tend to happen? Research into limiting unfortunate linkages and detecting when the method is likely to produce incorrect results should be done (cf. Charniak 1986).</Paragraph>
      <Paragraph position="3"> Analysis using different theories of text structure was not done, but could prove insightful. The independence of different people's intuitive chains and structure assignments was also not addressed by this paper.</Paragraph>
      <Paragraph position="4"> A practical limitation of this work is that it depends on a thesaurus as its knowledge base. A thesaurus is as good as the work that went into creating it, and also depends on the perceptions, experience, and knowledge of its creators. Since language is not static, a thesaurus would have to be continually updated to remain current. Furthermore, no one thesaurus exists that meets all needs. Roget's Thesaurus, for example, is a general thesaurus that does not contain lexical relations specific to the geography  Computational Linguistics Volume 17, Number 1 of Africa or quantum mechanics. Therefore, further work needs to be done on identifying other sources of word knowledge, such as domain-specific thesauri, dictionaries, and statistical word usage information, that should be integrated with this work. As an anonymous referee pointed out to us, Volks and Volkswagen were not included in the chain containing driving and car. These words were not in a general thesaurus, and were also missed by the authors! Section 1 mentioned that lexical chains would be also useful in providing a context for word sense disambiguation and in narrowing to specific word meanings. As an example of a chain providing useful information for word sense disambiguation, consider words I to 15 of chain 2.1 of the example: {afflicted, darkness, panicky, mournful, exciting, deadly, hating, aversion, cruel, relentless, weird, eerie, cold, barren, sterile .... }. In the context of all of these words, it is clear that barren and sterile do not refer to an inability to reproduce, but to a cruel coldness. The use of lexical chains for ambiguity resolution is a promising area for further research.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>