<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-0840">
  <Title>Senseval 3 Logic Forms: A System and Possible Improvements</Title>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2 Automatic Generation of Logic Forms
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
2.1 Parse Tree Construction
</SectionTitle>
      <Paragraph position="0"> Logic Forms are derived from the output of a syntactic parser. The first step is the identification of word collocations (based on those identified by WordNet (Miller, 1995)). The parser then proceeds to identify (i) parts of speech of individual words, and (ii) syntactic structure of the text, based on grammar rules. It also differentiates active verb constructs from passive ones.</Paragraph>
      <Paragraph position="1"> The output is a parse tree. We also include in the parse tree (i) word senses, based on WordNet, and (ii) named-entity tags (Surdeanu and Harabagiu, 2002). Named-entity tags are tags associated with a word or group of words, indicating that they belong to a particular category, for instance, currency, time, date, place, human, etc.</Paragraph>
      <Paragraph position="2"> The word senses from the parse tree are simply included in the Logic Form as is (for subsequent use in applications), while the named-entity tags are additionally used in the generation of Logic Forms.</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
2.2 Logic Form Generation
</SectionTitle>
      <Paragraph position="0"> First we identify independent arguments (those arguments which are generated anew for certain predicates). These include arguments for nouns,</Paragraph>
    </Section>
    <Section position="3" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
Association for Computational Linguistics
</SectionTitle>
      <Paragraph position="0"> for the Semantic Analysis of Text, Barcelona, Spain, July 2004 SENSEVAL-3: Third International Workshop on the Evaluation of Systems verbs (action/eventuality only), and compound nouns and coordinating conjunctions (for both of these, only the result argument (or the first one)).</Paragraph>
      <Paragraph position="1"> Independent arguments are also generated for certain adjectival phrases and/or determiners in the rare cases when they do not qualify a noun phrase, but stand all by themselves. The independent arguments, once generated, are propagated up the parse tree (as predicates form the leaves of the parse tree). In this way, heads of phrases are marked.</Paragraph>
      <Paragraph position="2"> Next comes the identification of dependent arguments (those which are derived from other independent and/or dependent arguments). These may include arguments for modifiers (adjectives, adverbs), secondary verb slots (all except the first) and secondary coordinating conjunction slots (all except the resulting argument), or linking words (prepositions, subordinating conjunctions, etc). The derivation of these arguments follows from a slot-filling approach and is based on the interpretation of the parse tree structure and the associated transformation rule (Moldovan and Rus, 2001). This is a rule that says how a particular parse tree structure must be handled, for instance, 'S -&gt; NP VP' says that the subject of the main/action verb of VP is the head of phrase of NP.</Paragraph>
    </Section>
  </Section>
  <Section position="5" start_page="0" end_page="0" type="metho">
    <SectionTitle>
3 Dealing with Ambiguous Structures
</SectionTitle>
    <Paragraph position="0"> Named-entity tags are helpful when parsing certain ambiguous structures. Take, for instance, the following two sentences: (i) They gave the visiting team a heavy loss.</Paragraph>
    <Paragraph position="1"> (ii) They played football every evening.</Paragraph>
    <Paragraph position="2"> The grammar rule for the verb phrase in both sentences is 'VP -&gt; VB NP NP'.</Paragraph>
    <Paragraph position="3"> Whereas, in sentence (i), the first NP is the indirect object and the second one the direct, exactly the converse is true for sentence (ii). Upon closer examination, it is found that 'every evening' being an indicator of time, does not qualify for the position of the direct object.</Paragraph>
    <Paragraph position="4"> The named-entity recognition system marks all such indicators of time/date. This enables us to disqualify these noun phrases as candidates for the position of the direct object of a verb.</Paragraph>
    <Paragraph position="5"> The aforementioned is just one kind of ambiguity that we have addressed. Another kind of ambiguity that we encountered (but have not implemented a solution for yet) is the reduction of certain words to base forms. Consider, for instance, null (i) John found the key. ('find' in VBN form) (ii) The King promised to found a similar institution. ('found' in VB form) A possible solution we considered was looking at part-of-speech tags (VBN vs. VB) to resolve ambiguity, but have not pursued this further in the (current) absence of a database that maintains a mapping from inflected word and part-of-speech pairs to the corresponding base forms. Another approach considered was choosing the base form whose frequency of occurrence in the Brown corpus, as reflected in WordNet, was highest.</Paragraph>
  </Section>
  <Section position="6" start_page="0" end_page="0" type="metho">
    <SectionTitle>
4 Changes/Improvements for Senseval 3
</SectionTitle>
    <Paragraph position="0"> Since no complete specification was given for the proper formation of logic forms for many special cases, we chose to model our Senseval 3 Logic Form system on the provided examples. The LF system was updated to model the Senseval 3 behavior in the following ways.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
4.1 Adverbs Modifying Adjectives
</SectionTitle>
      <Paragraph position="0"> These adverbs are assigned the same argument as the adjective they modify (Mohammed, 2003).</Paragraph>
      <Paragraph position="1"> For instance, &amp;quot;the extremely fast athlete&amp;quot; is represented as &amp;quot;extremely:r_ (x1) fast:a_ (x1) athlete:n_ (x1)&amp;quot;.</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
4.2 Variable Slots for Verbs
</SectionTitle>
      <Paragraph position="0"> The verbs are now given a variable number of arguments (minimum two: the action/eventuality and the subject). They get arguments for all verb objects, including prepositional attachments.</Paragraph>
      <Paragraph position="1"> Previously, we had a fixed slot allocation mechanism for verbs, specifying always the action, the subject, and the direct object. These slots were filled with dummy arguments in the absence of proper arguments.</Paragraph>
      <Paragraph position="2"> Example: S: John gave Mary the book on Saturday.</Paragraph>
      <Paragraph position="4"/>
    </Section>
    <Section position="3" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
4.3 Subordinating Conjunctions
</SectionTitle>
      <Paragraph position="0"> These conjunctions are given two arguments. The second argument is the main/action verb of the subordinate clause. The first argument is assigned as follows: (i) if the clause attaches to a sentence (or a verb phrase), then the main/action verb of this sentence (or verb phrase), (ii) if the clause attaches to a noun phrase, then the head of the noun phrase. Additional details are presented in Mohammed (2003).</Paragraph>
      <Paragraph position="1">  parse trees. This makes the generation of accurate parse trees extremely important. We have analyzed the performance of automatically generated Logic Forms based on both the machine-generated (hence necessarily somewhat erroneous) parse trees and parse trees generated by human annotators.</Paragraph>
      <Paragraph position="2"> The following results are based on the set of 300 test sentences provided for the Logic Forms Identification task at Senseval 3. The number of sentences with all predicates correctly identified has increased from 155 to 191, an improvement of 23.2%. The number of sentences with all correct arguments and all correct predicates (in other words, 100% correct Logic Forms) has increased from 65 to 98, a 50.7% improvement over Logic Forms derived from machine-generated parse trees. The results are presented in Table 1. Note that the row captioned &amp;quot;Predicates&amp;quot; indicates the number of sentences for which all predicates were correctly identified, while the row captioned &amp;quot;Entire LF&amp;quot; indicates those for which all predicates as well as all associated arguments were correctly identified.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>