<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-0819">
  <Title>Semantic Parsing Based on FrameNet</Title>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
PART OF SPEECH OF HEAD WORD (hPos) [?] The part of speech tag of
</SectionTitle>
    <Paragraph position="0"> the head word.</Paragraph>
  </Section>
  <Section position="5" start_page="0" end_page="0" type="metho">
    <SectionTitle>
PART OF SPEECH OF CONTENT WORD (cPos) [?]The part of speech
</SectionTitle>
    <Paragraph position="0"> tag of the content word.</Paragraph>
  </Section>
  <Section position="6" start_page="0" end_page="0" type="metho">
    <SectionTitle>
NAMED ENTITY CLASS OF CONTENT WORD (cNE) [?] The class of
</SectionTitle>
    <Paragraph position="0"> In FrameNet, sentences are annotated with the name of the sub-corpus. There are 12,456 possible names of sub-corpus. For the 40 frames evaluated in Senseval-3, there were 1442 names associated with the example sentences in the training data and 2723 names in the test data. Three of the most frequent sub-corpus names are: &amp;quot;V-trans-other&amp;quot; (frequency=613), &amp;quot;N-all&amp;quot; (frequency=562) and &amp;quot;V-trans-simple&amp;quot;(frequency=560). The name of the sub-corpus indicates the relations between the target word and some of its FEs. For example, the &amp;quot;V-trans-other&amp;quot; name indicated that the target word is a transitive verb, and thus its FEs are likely to have other roles than object or indirect object. A sentence annotated with this sub-corpus name is: &amp;quot;Night's coming, you can see the black shadow on [Self mover the stones] that [TARGET rush] [Pathpast] and [Pathbetween your feet.&amp;quot;]. For this sentence both FEs with the role of Path are neither objects or indirect objects of the transitive verb.</Paragraph>
    <Paragraph position="1"> Feature SUPPORT VERBS considers the usage of support expressions in FrameNet. We have found that whenever adjectives are target words, their semantic interpretation depends on their co-occurrence with verbs like &amp;quot;take&amp;quot;, &amp;quot;become&amp;quot; or &amp;quot;is&amp;quot;. Support verbs are defined as those verbs that combine with a state-noun, event-noun or state-adjective to create a verbal predicate, allowing arguments of the verb to serve as FEs of the frame evoked by the noun or the adjective.</Paragraph>
    <Paragraph position="2"> The CORENESS feature takes advantage of a more recent implementation concept of core FEs (vs. non-core FEs) in FrameNet. More specifically, the FrameNet developers classify frame elements in terms of how central they are to a particular frame, distinguishing three levels: core, peripheral and extra-thematic.</Paragraph>
    <Paragraph position="3"> The features were used to produce two types of examples: positive and negative examples. For each FE of a frame, aside from the positive examples rendered by the annotations, we considered as negative examples all the annotations of the other FEs for the same frame. The positive and the negative examples were used for training the multi-class classifiers.</Paragraph>
    <Paragraph position="4"> SUPPORT_VERBS that are recognized for adjective or noun target words target word. The values of this feature are either (1) The POS of the head of the VP containing the target word or (2) NULL if the target word does not belong to a VP  or ADJECTIVE LIST_CONSTITUENT (FEs): This feature represents a list of the syntactic Grammatical Function: This feature indicates whether the FE is: [?] an External Argument (Ext) [?] an Object (Obj) [?] a Complement (Comp) [?] a Modifier (Mod) [?] Head noun modified by attributive adjective (Head) [?] Genitive determiner (Gen) [?] Appositive (Appos)  LIST_Grammatical_Function: This feature represents a list of the grammatical functions of the FEs recognized in the sentence. in each sentence.</Paragraph>
    <Paragraph position="5"> FRAME_NAME: This feature indicates the name of the semantic frame for which FEs are labeled COVERAGE: This feature indicates whether there is a syntactic structure in the parse tree that perfectly covers the FE a conceptually necessary participant of a frame. For example, in the are: (1) core; (2) peripheral and (3) extrathemathic. FEs that mark notions such as Time, Place, Manner and Degree are peripheral. Extrathematic FEs situate an event against a backdrop of another event, by evoking a larger frame for which the target event fills a role. SUB_CORPUS: In FrameNet, sentences are annotated with the name of the subcorpus they belong to. For example, for a verb target word, to a FE included in a relative clause headed by a wh[?]word.  (2) a hyponym of sense 1 of PERSON in WordNet (1) a personal pronoun or  HUMAN: This feature indicates whether the syntactic phrase is either TARGET[?]TYPE: the lexical class of the target word, e.g. VERB, NOUN consituents covering each FE of the frame recognized in a sentence. For the example illustrated in Figure 1, the list is: [NP, NP, PP] NUMBER_FEs: This feature indicates how many FEs were recognized have the role of predicate for the FEs. For example, if the target word is &amp;quot;clever&amp;quot; in the sentence &amp;quot;Smith is very clever, but he's no Einstein&amp;quot;, the the FE &amp;quot;Smith&amp;quot; is an argument of the support verb &amp;quot;is&amp;quot;' rather than of the CORENESS: This feature indicates whether the FE instantiates REVENGE frame, Punishment is a core element. The values V[?]swh represents a subcorpus in which the target word is a predicate  Our multi-class classification allows each FE to be initially labeled with more than one role when several classifiers decide so. For example, for the AT-TACHING frame, an FE may be labeled both as Goal and as Item if the classifiers for the Goal and Item select it as a possible role. To choose the final label, we select the classification which was assigned the largest score by the SVMs.</Paragraph>
  </Section>
  <Section position="7" start_page="0" end_page="0" type="metho">
    <SectionTitle>
PARSE TREE PATH WITH UNIQUE DELIMITER [?] This feature removes
</SectionTitle>
    <Paragraph position="0"> the direction in the path, e.g. VBN[?]VP[?]ADVP PARTIAL PATH [?] This feature uses only the path from the constituent to the lowest common ancestor of the predicate and the constituent</Paragraph>
  </Section>
  <Section position="8" start_page="0" end_page="0" type="metho">
    <SectionTitle>
3 Boundary Detection
</SectionTitle>
    <Paragraph position="0"> The boundary detection of each FE was required in the Restricted Case of the Senseval-3 evaluation. To classify a word as belonging to an FE or not, we used all the entire Feature Set 1 and 2. From the Feature Set 3 we have used only four features: the Support- Verbs feature; the Target-Type feature, the Frame-Name feature and the Sub Corpus feature. For this task we have also used Feature Set 4, which were first introduced in (Pradhan et al., 2004). The Feature Set 4 is illustrated in Figure 5. After the boundary detection was performed, the semantic roles of each FE were assigned using the role classifier trained for the</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
Restricted Case
</SectionTitle>
      <Paragraph position="0"/>
    </Section>
  </Section>
  <Section position="9" start_page="0" end_page="0" type="metho">
    <SectionTitle>
4 Heuristics
</SectionTitle>
    <Paragraph position="0"> Frequently, syntactic constituents do not cover exactly FEs. For the Unrestricted Case we implemented a very simple heuristic: when there is no parse-tree node that exactly covers the target role r but a subset of adjacent nodes perfectly match r, we merge them in a new NPmerge node. For the Restricted Case, a heuristic for adjectival and nominal target words w adjoins consecutive nouns that are in the same noun phrase as w.</Paragraph>
  </Section>
class="xml-element"></Paper>