<?xml version="1.0" standalone="yes"?>
<Paper uid="N04-3006">
  <Title>Open Text Semantic Parsing Using FrameNet and WordNet</Title>
  <Section position="3" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2 Semantic Structure
</SectionTitle>
    <Paragraph position="0"> Semantics is the denotation of a string of symbols, either a sentence or a word. Similar to a syntactic parser, which shows how a larger string is formed by smaller strings from a formal point of view, the semantic parser shows how the denotation of a larger string - sentence, is formed by denotations of smaller strings - words. Syntactic relations can be described using a set of rules about how a sentence string is formally generated using word strings. Instead, semantic relations between semantic constituents depend on our understanding of the world, which is across languages and syntax.</Paragraph>
    <Paragraph position="1"> We can model the sentence semantics as describing entities and interactions between entities. Entities can represent physical objects, as well as time, places, or ideas, and are usually formally realized as nouns or noun phrases. Interactions, usually realized as verbs, describe relationships or interactions between participating entities. Note that a participant can also be an interaction, which can be regarded as an entity nominalized from an interaction. We assign semantic roles to participants and their semantic relations are identified by the case frame introduced by their interaction.</Paragraph>
    <Paragraph position="2"> In a sentence, participants and interactions can be further modified by various modifiers, including descriptive modifiers that describe attributes such as drive slowly, restrictive modifiers that enforce a general denotation to become more specific such as musical instrument, referential modifiers that indicate particular instances such as the pizza I ordered. Other semantic relations can also be identified, such as coreference, complement, and others. Based on the principle of compositionality, the sentence semantic structure is recursive, similar to a tree.</Paragraph>
    <Paragraph position="3"> Note that the semantic parser analyzes shallow-level semantics, which is derived directly from linguistic knowledge, such as rules about semantic role assignment, lexical semantic knowledge, and syntactic-semantic mappings, without taking into account any context or common sense knowledge. Hence, the parser can be used as an intermediate semantic processing level before higher levels of text understanding.</Paragraph>
  </Section>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
3 Knowledge Bases for Semantic Parsing
</SectionTitle>
    <Paragraph position="0"> The parser relies on two main types of knowledge - about words, and about relations between words. The first type of knowledge is drawn from WordNet - a large lexical database with rich information about words and concepts. We refer to this as word-level knowledge. The latter is derived from FrameNet - a resource that contains information about different situations, called frames, in which semantic relations are syntactically realized in natural language sentences. We call this sentence-level knowledge. In addition to these two lexical knowledge bases, the parser also utilizes a set of manually defined rules, which encode mappings from syntactic structures to semantic relations, and which are used to handle those structures not explicitly addressed by FrameNet or WordNet. In this section, we describe the type of information extracted from these knowledge bases, and show how this information is encoded in a format accessible to the semantic parser.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
3.1 Sentence Level Knowledge
</SectionTitle>
      <Paragraph position="0"> FrameNet (Johnson et al., 2002) provides the knowledge needed to identify case frames and semantic roles.</Paragraph>
      <Paragraph position="1"> FrameNet is based on the theory of frame semantics, and defines a sentence level ontology. In frame semantics, a frame corresponds to an interaction and its participants, both of which denote a scenario, in which participants play some kind of roles. A frame has a name, and we use this name to identify the semantic relation that groups together the semantic roles. Nouns, verbs and adjectives can be used to identify frames.</Paragraph>
      <Paragraph position="2"> Each annotated sentence in FrameNet exemplifies a possible syntactic realization for the semantic roles associated with a frame for a given target word. By extracting the syntactic features and corresponding semantic roles from all annotated sentences in the FrameNet corpus, we are able to automatically build a large set of rules that encode the possible syntactic realizations of semantic frames.</Paragraph>
      <Paragraph position="3">  FrameNet data &amp;quot;is meant to be lexicographically relevant, not statistically representative&amp;quot; (Johnson et al., 2002), and therefore we are using FrameNet as a starting point to derive rules for a rule-based semantic parser.</Paragraph>
      <Paragraph position="4"> To build the rules, we are extracting several syntactic features. Some are explicitly encoded in FrameNet, such as the grammatical function (GF) and phrase type (PT) features.</Paragraph>
      <Paragraph position="5"> In addition, other syntactic features are extracted from the sentence context. One such feature is the relative position (RP) to the target word. Another feature is the voice of the sentence. If the phrase type is prepositional phrase (PP), we also record the actual preposition that precedes the phrase.</Paragraph>
      <Paragraph position="6"> After we extract all these syntactic features, the semantic role is appended to the rule, which creates a mapping from syntactic features to semantic roles.</Paragraph>
      <Paragraph position="7"> Feature sets are arranged in a list, the order of which is identical to that in the sentence. Altogether, the rule for a possible realization of a frame exemplified by a tagged sentence is an ordered sequence of syntactic features with their semantic roles. For example, the corresponding formalized rule for the sentence I had chased Selden over the moor is: [active, [ext,np,before,theme], [obj,np,after,goal], [comp,pp,after,over,path]] In FrameNet, there are multiple annotated sentences for each frame to demonstrate multiple possible syntactic realizations. All possible realizations of a frame are collected and stored in a list for that frame, which also includes the target word, its syntactic category, and the name of the frame. All the frames defined in FrameNet are transformed into this format, so that they can be easily handled by the rule-based semantic parser.</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
3.2 Word Level Knowledge
</SectionTitle>
      <Paragraph position="0"> WordNet (Miller, 1995) is the resource used to identify shallow semantic features that can be attached to lexical units.</Paragraph>
      <Paragraph position="1"> For instance, attribute relations, adjective/adverb classifications, and others, are semantic features extracted from Word-Net and stored together with the words, so that they can be directly used in the parsing process.</Paragraph>
      <Paragraph position="2"> All words are uniformly defined, regardless of their class.</Paragraph>
      <Paragraph position="3"> Features are assigned to each word, including syntactic and shallow semantic features, indicating the functions played by the word. Syntactic features are used by the feature-augmented syntactic analyzer to identify grammatical errors and produce syntactic information for semantic role assignment. Semantic features encode lexical semantic information extracted from WordNet that is used to determine semantic relations between words in various situations.</Paragraph>
      <Paragraph position="4"> Features can be arbitrarily defined, as long as there are rules to handle them. The features we define encode information about the syntactic category of a word, number and countability for nouns, transitivity and form for verbs, type, degree, and attribute for adjectives and adverbs, and others.</Paragraph>
      <Paragraph position="5"> For example, for the adjective slow, the entry in the lexicon is defined as: lex(slow,W):- W= [parse:slow, cat:adj, attr:speed, degree:base, type:descriptive].</Paragraph>
      <Paragraph position="6"> Here, the category (cat) is defined as adjective, the type is descriptive, degree is base form. We also record the attr feature, which is derived from the attribute relation in Word-Net, and links a descriptive adjective to the attribute (noun) it modifies, such as slow a0 speed.</Paragraph>
    </Section>
  </Section>
  <Section position="5" start_page="0" end_page="0" type="metho">
    <SectionTitle>
4 The Semantic Parser
</SectionTitle>
    <Paragraph position="0"> The parsing algorithm is implemented as a rule-based system. The general procedure of semantic parsing consists of three main steps: (1) syntactic parsing into an intermediate format, using a feature-augmented syntactic parser, and assignment of shallow semantic features; (2) semantic role assignment; (3) application of default rules.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
4.1 Feature Augmented Syntactic/Semantic Analyzer
</SectionTitle>
      <Paragraph position="0"> The semantic parser is based on dependencies between words that are identified using a structure analyzer. The analyzer generates an intermediate format, where target words and syntactic arguments are explicitly identified, so that they can be matched against the rules derived from FrameNet.</Paragraph>
      <Paragraph position="1"> The intermediate format also encodes some shallow semantic features, including word level semantics (e.g. attribute, gender), and semantic relations that have direct syntactic correspondence (e.g. modifier types). The function of the sentence is also identified, as assertion, query, yn-query, command.</Paragraph>
      <Paragraph position="2"> The analyzer is based on a feature augmented grammar, and has the capability of detecting if a sentence is grammatically correct (unlike statistical parsers, which attempt to parse any sentence, regardless of their well-formness). Constituents are assigned with features, and the grammar consists of a set of rules defining how constituents can connect to each other, based on the values of their features.</Paragraph>
      <Paragraph position="3"> Since features can contain both syntactic and semantic information, the analyzer can reject some grammatically incorrect sentences such as: I have much apples, You has my car, or even some semantically incorrect sentences: The technology is very military1.</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
4.2 Semantic Role Assignment
</SectionTitle>
      <Paragraph position="0"> In the process of semantic role assignment, we first start by identifying all possible frames, according to the target word.</Paragraph>
      <Paragraph position="1"> Next, a matching algorithm is used to find the most likely match among all rules derived for these frames, to identify the correct frame (if several are possible), and assign semantic roles.</Paragraph>
      <Paragraph position="2"> In a sentence describing an interaction, we usually select the verb or predicative adjective as the target word, which triggers the sentence level frame. A noun can also play the role of target word, but only within the scope of the noun phrase it belongs to, and it can be used to assign semantic roles only to its modifiers.</Paragraph>
      <Paragraph position="3"> The matching algorithm relies on a scoring function to evaluate the similarity between two sequences of syntactic features. The matching starts from left to right. Whenever an exact match is found, the score will be increased by 1.</Paragraph>
      <Paragraph position="4"> It should be noted that the search sequence is uni-directional which means that once you find a match, you can go ahead to check features to the right, but you cannot go back to check  nected to the degree modifier very.</Paragraph>
      <Paragraph position="5"> rules you have already checked. This guarantees that syntactic features are matched in the right order, and the order of sequence in the rule is maintained. Since the frame of a target word may have multiple possible syntactic realizations, which are exemplified by different sentences in the corpus, we try to match the syntactic features in the intermediate format with all the rules available for the target word, and compare their matching scores. The rule with the highest score is selected, and used for semantic role assignment. Through this scoring scheme, the matching algorithm tries to maximize the number of syntactic realizations for semantic roles defined in FrameNet rules.</Paragraph>
      <Paragraph position="6"> Notice that the semantic role assignment is performed recursively, until all roles within frames triggered by all target words are assigned.</Paragraph>
      <Paragraph position="7">  Assume the following two rules, derived from FrameNet for the target word come: 1:[[ext,np,before,active,theme], [obj,np,after,active,goal], [comp,pp,after,active,by,mode_of_transportation]] 2:[[ext,np,before,active,theme], [obj,np,after,active,goal], [comp,pp,after,active,from,source]] And the sentences: A: I come here by train.</Paragraph>
      <Paragraph position="8"> B: I come here from home.</Paragraph>
      <Paragraph position="9"> The syntactic features identified by the syntactic analyzer for these two sentences are: A':[[ext,np,before,active], [obj,np,after,active], $[$comp,pp,after,active,by]] B':[[ext,np,before,active], [obj,np,after,active], $[$comp,pp,after,active,from]] Using the matching/scoring algorithm, the score for matching A' to rule 1 is determined as 3, and to rule 2 as 2. Hence, the matching algorithm selects rule 1, and the semantic role for train is mode of transportation. Similarly, when we match B' to rule 1, we obtain a score of 2, and a larger score of 3 for matching with rule 2. Therefore, for the second case, the role assigned to home is source.</Paragraph>
    </Section>
    <Section position="3" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
4.3 Applying Default Rules
</SectionTitle>
      <Paragraph position="0"> In a sentence, semantic roles are played by the subject, objects, and the prepositional phrases attached to the interaction described by the sentence. However, FrameNet defines roles only for some of these elements, and therefore the meaning of some sentence constituents cannot be determined using the rules extracted from FrameNet. In order to handle these constituents, and allow for a complete semantic interpretation of the sentence, we have defined a set of default rules that are applied as a last step in the process of semantic parsing. For example, FrameNet defines a role for the prepositional phrase on him in &amp;quot;I depend on him&amp;quot;, but it does not define a role for the phrase on the street in &amp;quot;I walk on the street&amp;quot;. To handle the interpretation of this phrase, we apply the default rule that &amp;quot;on something&amp;quot; modifies the location attribute of an interaction.</Paragraph>
      <Paragraph position="1"> We have defined about 100 such default rules, which are assigned in the last step of the semantic parsing process, if no other rule could be applied in previous steps. After this step, the semantic structure of the sentence is produced.</Paragraph>
    </Section>
  </Section>
  <Section position="6" start_page="0" end_page="0" type="metho">
    <SectionTitle>
5 Parser Output and Evaluation
</SectionTitle>
    <Paragraph position="0"> The semantic parser is demonstrated in this conference, which is perhaps the best evaluation we can offer. We illustrate here the output of the semantic parser on a natural language sentence, and show the corresponding semantic structure and tree. For example, for the sentence I like to eat Mexican food because it is spicy, the semantic parser produces the following encoding of sentence type, frames, semantic constituents and roles, and various attributes and modifiers:</Paragraph>
    <Paragraph position="2"> [[experiencer, [[entity, [i], reference(first)], [modification(attribute), quantity(single)]]], [interaction(experiencer\_subj),[love]], [modification(attribute), time(present)], [content, [ [interaction(ingestion), [eat]], [ingestibles, [entity, [food]] [[modification(restriction), [mexican]], ]]]], [reason, [[agent, [[entity, [it], reference(third)], [modification(attribute), quantity(single)]]], [description, [modification(attribute), time(present)]], [modification(attribute), taste\_property(spicy)]]]  referential modifier, sm = restrictive modifier) We have conducted evaluations of the semantic role assignment algorithm on 350 sentences randomly selected from FrameNet. The test sentences were removed from the FrameNet corpus, and the rules-learning procedure described earlier in the paper was invoked on this reduced corpus. All test sentences were then semantically parsed, and full semantic annotations were produced for each sentence. Notice that the evaluation is conducted only for semantic role assignment - since this is the only information available in FrameNet. The other semantic annotations produced by the parser (e.g. attribute, gender, countability) are not evaluated at this point, since there are no hand-validated annotations of this kind available in current resources. Both frames and frame elements are automatically identified by the parser. Out of all the elements correctly identified, we found that 74.5% were assigned with the correct role (this is therefore the accuracy of role assignment), which compares favorably with previous results reported in the literature for this task. Notice also that since this is a rule-based approach, the parser does not need large amounts of annotated data, but it works well the same for words for which only one or two sentences are annotated.</Paragraph>
  </Section>
  <Section position="7" start_page="0" end_page="0" type="metho">
    <SectionTitle>
6 Related Work
</SectionTitle>
    <Paragraph position="0"> All previous work in semantic parsing has exclusively focused on labeling semantic roles, rather than analyzing the full structure of sentence semantics, and is usually based on statistical models - e.g. (Gildea and Jurafsky, 2000), (Fleischman et al., 2003). To our knowledge, there was no previous attempt on performing semantic annotations using alternative rule-based algorithms. However, a rule-based approach is closer to the way humans interpret the semantic structure of a sentence. Moreover, as mentioned earlier, the FrameNet data is not meant to be &amp;quot;statistically representative&amp;quot;, but rather illustrative for various language constructs, and therefore a rule-based approach is more suitable for this lexical resource.</Paragraph>
  </Section>
class="xml-element"></Paper>