<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-4190">
  <Title>CAN COMPUTERS HANDLE ADVERBS?*</Title>
  <Section position="5" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2. SEMANTIC CLASSIFICATION OF
ADVERBS AND SELECTIONAL
RESTRICTIONS.
</SectionTitle>
    <Paragraph position="0"> With minor variations, Jacobson \[1964\] and Quirk et al. \[1985, p438-74\] classify adverbs semantically as: adverbs of time, manner, degree, location, direction, transition and hedges. Adverbs of time, for example, answer questions such as &amp;quot;When?,&amp;quot; &amp;quot;How often?,&amp;quot; &amp;quot;How long?.&amp;quot; Some examples of adverbs in this class are &amp;quot;before,&amp;quot; &amp;quot;during,&amp;quot; &amp;quot;now,&amp;quot; &amp;quot;forever,&amp;quot; &amp;quot;seldom,&amp;quot; etc. Adverbs of manner answer questions like &amp;quot;How?&amp;quot; and &amp;quot;In what manner (way)?&amp;quot; Examples are &amp;quot;quickly,&amp;quot; AcrEs DE COLING..92, NANTES, 23-28 AO~r 1992 1 i 9 2 PROC. OF COLING-92, NANTES, AUC/I. 23-28. 1992 &amp;quot;like,&amp;quot; &amp;quot;together,&amp;quot; and &amp;quot;without.&amp;quot; Hedges indicate fuzzy restrictions such as &amp;quot;essentially,&amp;quot; &amp;quot;sort of,&amp;quot; and &amp;quot;virtually&amp;quot; \[Lakoff, 1972\]. We have classified adverbs by systematically analyzing CED definitions.</Paragraph>
    <Paragraph position="1"> More details on this process can be found in Conlon et al., \[1990\] and Pin-Ngern \[1990\].</Paragraph>
    <Paragraph position="2"> These semantic classes are stored in our adverbial lexicon as in Table 1.</Paragraph>
    <Paragraph position="4"> about 1 2 l DEGREE, TIME actually 1 1 1 MOOD between 1 2 2 PLACE, DIRECTION down 1 2 7 POSITION evidently 1 1 1 MOOD  The first line indicates that in CED, the adverb &amp;quot;about&amp;quot; with homograph number 1, sense number 2, and subsense number 1 belongs to the flggr~ and time class. (To facilitate exposition, the tables here and below are not normalized.) Huang \[1975\] provides a similar classification of adverbs based on semantic usage with verbs. These classes of adverbs include: State of ~ ~. Adverbs in this group indicate a participant's state of mind. Examples are ~ and ~ in the following sentences: He rf_aLf.Ra~ stepped into the room. Mary was F_JllLegl2 taken advantage of... vA.d.x.cz~. These adverbs express an evaluation of the actor's participation in the event such as &amp;quot;clumsily&amp;quot; in &amp;quot;He clumsily stepped on the snail.&amp;quot; of \]~5.UR. These describe aspects of the result of an event such as the adverb &amp;quot;correctly&amp;quot; in the sentence &amp;quot;He spelled the words correctly.&amp;quot; Huang's classifications can also be incorporated into Table 1.</Paragraph>
    <Paragraph position="5"> These adverb classifications can be extremely useful to NIP systems, in particular, in the statement of selectional restrictions (or preferences). Huang describes a number of selectional restrictions between adverbs and other parts of speech. Some examples are: Adverbs of manner or direction can modify verbs of motion.</Paragraph>
    <Paragraph position="6"> Adverbs of result are proper to accomplishment and achievement verbs.</Paragraph>
    <Paragraph position="7"> Time and locative adverbs usually occur in action sentences and specify the temporal and spatial circumstances of the events.</Paragraph>
    <Paragraph position="8"> Degree adverbs express the degree or extent of a certain quality or state and presuppose an analysis of grading properties in the semantics of adjectives in particular.</Paragraph>
    <Paragraph position="9"> Conjunctive adverbs are used in almost the same way as conjunctions.</Paragraph>
    <Paragraph position="10"> This type of information should help text generation systems to select appropriate types of adverb to suit nouns, verbs, adjective, and adverbs which have already been chosen. It may also be useful for resolution of ambiguity in natural language understanding applications (see Radford \[1988, p372\] for an example of a sentence in which selectional restrictions resolve ambiguity). Information about selectional restriction are stored as in</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
of Manner
</SectionTitle>
      <Paragraph position="0"> From the above examples, &amp;quot;clumsily&amp;quot; and &amp;quot;slowly&amp;quot; can modify dynamic verbs and action sentences.</Paragraph>
    </Section>
  </Section>
  <Section position="6" start_page="0" end_page="0" type="metho">
    <SectionTitle>
3. FUNCTIONAL CLASSIFICATION
AND THE SYNTACTIC BEHAVIOR OF
ADVERBS
</SectionTitle>
    <Paragraph position="0"> Jacobson \[1964\] groups adverbs into four major functional classes: modifying adverbs (&amp;quot;L.I/C/...~ he is ~ careful&amp;quot;), complementary adverbs (&amp;quot;Please come ~'), referential adverbs (&amp;quot; This section, in particular, is important&amp;quot;), and conjunctive adverbs (&amp;quot;He will not leave unless she asks him to&amp;quot;).</Paragraph>
    <Paragraph position="1"> Adverbs that function as modifiers, in turn, can modify verbs (&amp;quot;He spelledr,~_rLeC~&amp;quot;), adjectives ('They are ~ tall&amp;quot;), other adverbs (&amp;quot;He works ~ well&amp;quot;), or even clauses and the whole sentences (&amp;quot;ForCunatC/ly he was not drunk&amp;quot;).</Paragraph>
    <Paragraph position="2"> These functional classes help to organize knowledge representation schemes involving adverbs, and are also essential for understanding the syntactic properties of adverbs. Jackendoff, for example, classifies adverbs as subject-oriented, speaker-oriented (sentence), and manner adverbs, and represents the meaning structures of these adverbs in essentially prolog form as follows:  Huang uses similar prolog-like formulas to represent the semantic structure of adverbs.</Paragraph>
    <Paragraph position="3"> This same functional classification also allows Jackendoff to derive positions of adverbs by using parse trees. According to Jackendoff, sentence adverbs must be attached to an Snode, while manner adverbs are attached to VP nodes. Thus the sentence adverb &amp;quot;evidently&amp;quot; can appear in positions such as the following:  A similar parse tree could be constructed for &amp;quot;John walked in the store, evidently.&amp;quot; On the other hand, the sentence *'John walked evidently in the store,&amp;quot; is impossible because the parse tree does not allow &amp;quot;evidently&amp;quot; to be attached to the S node (see figure 4.)</Paragraph>
    <Paragraph position="5"> Adverb Based on Modification Class Additional information about adverbial positions in sentences has been collected by Jacobson \[1964\]. This information should supplement the information in Table 3, and should also be helpful for information retrieval and NLP applications. This information is organized as in Table 4.</Paragraph>
    <Paragraph position="6"> ADV-JACOBSON(~_,H/G#,SENS~, SUBSENSE#,POSITION) after 1 2 1 E4 constantly 1 1 1 M1, M3, M4, El, E5 exactly 1 1 2 M3, M4 otherwise 1 2 1 M3, El, E4, E5  Thus, &amp;quot;constantly&amp;quot; is found in &amp;quot;middle&amp;quot; and &amp;quot;end&amp;quot; positions. More details about each position can be found in Jacobson \[1964\].</Paragraph>
  </Section>
  <Section position="7" start_page="0" end_page="0" type="metho">
    <SectionTitle>
4. APPLICATIONS
</SectionTitle>
    <Paragraph position="0"> A sophisticated adverbial lexicon should help NLP systems to handle adverbs appropriately.</Paragraph>
    <Paragraph position="1"> NLP systems will be able to use information in the adverbial lexicon in parsing, language understanding, and text generation systems.</Paragraph>
    <Paragraph position="2"> Suppose, for example, that a parser has to parse a sentence of the form: &amp;quot;John \[Adv\] walked to the store.&amp;quot; The parser can determine how to treat the adverb by looking in the lexicon to see whether the adverb is a sentence or a verb phrase adverb. For example, if &amp;quot;quickly&amp;quot; is the adverb in the sentence, it is a manner adverb, so it should be attached to the verb or verb phrase node. On the other hand, if the adverb is &amp;quot;evidently&amp;quot; then it is a mood adverb (speaker oriented sentence modifier), and so, should be attached to the S node.</Paragraph>
  </Section>
  <Section position="8" start_page="0" end_page="0" type="metho">
    <SectionTitle>
ACRES DE COLING-92, NANll~S, 23-28 AO~' 1992 1 1 9 5 t'ROC. O1: COLING-92, NANTES, AUG. 23-28, 1992
</SectionTitle>
    <Paragraph position="0"> Once the sentence has been successfully parsed, the language understanding system can then create prolog-like formulas of the form indicated in Figure 1. Similarly, the text generation system should be designed to take prolog-like formulas such as those in Figure 1 and successfully translate them into natural language. The functional class then places restrictions on the position of the adverbs, as in Figures 2, 3, and 4.</Paragraph>
    <Paragraph position="1"> Finally, selectional restrictions can be used to reduce lexical ambiguity in language understanding systems, and assist in word choice in text generation (see Section 2).</Paragraph>
  </Section>
class="xml-element"></Paper>