<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2105">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics A Logic-based Semantic Approach to Recognizing Textual Entailment</Title>
  <Section position="5" start_page="819" end_page="821" type="metho">
    <SectionTitle>
3 Knowledge Representation
</SectionTitle>
    <Paragraph position="0"> For the textual entailment task, our logic prover uses a two-layered logical representation which captures the syntactic and semantic propositions encoded in a text fragment.</Paragraph>
    <Section position="1" start_page="819" end_page="820" type="sub_section">
      <SectionTitle>
3.1 Logic Form Transformation
</SectionTitle>
      <Paragraph position="0"> In the first stage of our representation process, COGEX converts a1 and a0 into logic forms (Moldovan and Rus, 2001). More specifically, a predicate is created for each noun, verb, adjective and adverb. The nouns that form a noun compound are gathered under a nn NNC predicate. Each named entity class of a noun has a corresponding predicate which shares its argument with the noun predicate it modifies. Predicates for  prepositions and conjunctions are also added to link the text's constituents. This syntactic layer of the logic representation is, automatically, derived from a full parse tree and acknowledges syntax-based relationships such as: syntactic subjects, syntactic objects, prepositional attachments, complex nominals, and adjectival/adverbial adjuncts. In order to objectively evaluate our representation, we derived it from two different sources: constituency parse trees (generated with our implementation of (Collins, 1997)) and dependency parse trees (created using Minipar (Lin, 1998))1. The two logic forms are slightly different. The dependency representation captures more accurately the syntactic dependencies between the concepts, but lacks the semantic information that our semantic parser extracts from the constituency parse trees. For instance, the sentence Gilda Flores was kidnapped on the 13th of January 19902 is &amp;quot;constituency&amp;quot; represented  The exceptions to the one-predicate-peropen-class-word rule include the adverbs not and never. In cases similar to further details were not released, the system removes  The RTE datasets will be described in Section 7.</Paragraph>
      <Paragraph position="1"> not RB(x3,e1) and negates the verb's predicate (-release VB(e1,x1,x2)).</Paragraph>
      <Paragraph position="2"> Similarly, for nouns whose determiner is no, for example, No case of indigenously acquired rabies infection has been confirmed, the verb's predicate is negated (case NN(x1) &amp; -confirm VB(e2,x15,x1)).</Paragraph>
    </Section>
    <Section position="2" start_page="820" end_page="820" type="sub_section">
      <SectionTitle>
3.2 Semantic Relations
</SectionTitle>
      <Paragraph position="0"> The second layer of our logic representation adds the semantic relations, the underlying relationships between concepts. They provide the semantic background for the text, which allows for a denser connectivity between the concepts expressed in text. Our semantic parser takes free English text or parsed sentences and extracts a rich set of semantic relations3 between words or concepts in each sentence. It focuses not only on the verb and its arguments, but also on semantic relations encoded in syntactic patterns such as complex nominals, genitives, adjectival phrases, and adjectival clauses. Our representation module maps each semantic relation identified by the parser to a predicate whose arguments are the events and entities that participate in the relation and it adds these semantic predicates to the logic form. For example, the previous logic form is augmented with the THEME SR(x3,e1) &amp;</Paragraph>
      <Paragraph position="2"> the theme of the kidnap event and 13th of January 1990 shows the time of the kidnapping).</Paragraph>
    </Section>
    <Section position="3" start_page="820" end_page="821" type="sub_section">
      <SectionTitle>
3.3 Temporal Representation
</SectionTitle>
      <Paragraph position="0"> In addition to the semantic predicates, we represent every date/time into a normalized form time TMP(BeginFn(event), year, month, date, hour, minute, second) &amp; time TMP(EndFn(event), year, month, date, hour, minute, second). Furthermore, temporal reasoning  predicates are derived from both the detected semantic relations as well as from a module which utilizes a learning algorithm to detect temporally ordered events (a3a1a0 a4a3a2a5a4 a4a3a2a7a6 a6 , where a0 is the temporal signal linking two events a2 a4 and a2 a6 ) (Moldovan et al., 2005). From each triple, temporally related SUMO predicates are generated based on hand-coded rules for the signal classes (a3a1a0 sequence, a2a5a4 a4a3a2a7a6 a6 a8 earlier TMP(e1,e2), a3a1a0 contain, a2 a4 a4a3a2 a6 a6a9a8 during TMP(e1,e2), etc.). In the above example, 13th of January 1990 is normalized to the interval time TMP(BeginFn(e2), 1990, 1, 13, 0, 0, 0) &amp; time TMP(EndFn(e2), 1990, 1, 13, 23, 59, 59) and during TMP(e1,e2) is added to the logical representation to show when the kidnapping occurred.</Paragraph>
    </Section>
  </Section>
  <Section position="6" start_page="821" end_page="822" type="metho">
    <SectionTitle>
4 Axioms on Demand
</SectionTitle>
    <Paragraph position="0"> COGEX's usable list consists of all the axioms generated either automatically or by hand. The system generates axioms on demand for a given a3 a1a5a4 a0a7a6 pair whenever the semantic connectivity between two concepts needs to be established in a proof. The axioms on demand are lexical chains and world knowledge axioms. We are keen on the idea of axioms on demand since it is not possible to derive apriori all axioms needed in an arbitrary proof. This brings a considerable level of robustness to our entailment system.</Paragraph>
    <Section position="1" start_page="821" end_page="822" type="sub_section">
      <SectionTitle>
4.1 eXtended WordNet lexical chains
</SectionTitle>
      <Paragraph position="0"> For the semantic entailment task, the ability to recognize two semantically-related words is an important requirement. Therefore, we automatically construct lexical chains of WordNet relations from a1 's constituents to a0 's (Moldovan and Novischi, 2002). In order to avoid errors introduced by a Word Sense Disambiguation system, we used the first a10 senses for each word5 unless the source and the target of the chain are synonyms. If a chain exists6, the system generates, on demand, an axiom with the predicates of the source (from a1 ) and the target (from a0 ).</Paragraph>
      <Paragraph position="1">  erties: shorter chains are better than longer ones, the relations are not equally important and their order in the chain influences its strength. If the weight of a chain is above a given threshold, the lexical chain is discarded.</Paragraph>
      <Paragraph position="2"> For example, given the ISA relation between murder#1 and kill#1, the system generates, when needed, the axiom murder VB(e1,x1,x2) a16 kill VB(e1,x1,x2). The remaining of this section details some of the requirements for creating accurate lexical chains.</Paragraph>
      <Paragraph position="3"> Because our extended version of Word-Net has attached named entities to each noun synset, the lexical chain axioms append the entity name of the target concept, whenever it exists. For example, the logic prover uses the axiom Nicaraguan JJ(x1,x2) a16 Nicaragua NN(x1) &amp; country NE(x1) when it tries to infer electoral campaign is held in Nicaragua from Nicaraguan electoral campaign.</Paragraph>
      <Paragraph position="4"> We ensured the relevance of the lexical chains by limiting the path length to three relations and the set of WordNet relations used to create the chains by discarding the paths that contain certain relations in a particular order. For example, the automatic axiom generation module does not consider chains with an IS-A relation followed by a</Paragraph>
      <Paragraph position="6"> with more than one HYPONYMY relations. Although these relations link semantically related concepts, the type of semantic similarity they introduce is not suited for inferences. Another restriction imposed on the lexical chains generated for entailment is not to start from or include too general concepts7. Therefore, we assigned to each noun and verb synset from WordNet a generality weight based on its relative position within its hierarchy and on its frequency in a large corpus. If  In our experiments, we discarded the chains with concepts whose generality weight exceeded 0.8 such as object NN#1, act VB#1, be VB#1, etc.</Paragraph>
      <Paragraph position="7"> Another important change that we introduced in our extension of WordNet is the refinement of the DERIVATION relation which links verbs with their corresponding nominalized nouns. Because the relation is ambiguous regarding the role of the noun, we split  this relation in three: ACT-DERIVATION, AGENT-DERIVATION and THEME-DERIVATION. The role of the nominalization determines the argument given to the noun predicate. For instance, the axioms act VB(e1,x1,x2) a16 acting NN(e1)(ACT), act VB(e1,x1,x2) a16 actor NN(x1) (AGENT) reflect different types of derivation.</Paragraph>
    </Section>
    <Section position="2" start_page="822" end_page="822" type="sub_section">
      <SectionTitle>
4.2 NLP Axioms
</SectionTitle>
      <Paragraph position="0"> Our NLP axioms are linguistic rewriting rules that help break down complex logic structures and express syntactic equivalence. After analyzing the logic form and the parse trees of each text fragment, the system, automatically, generates axioms to break down complex nominals and coordinating conjunctions into their constituents so that other axioms can be applied, individually, to the components. These axioms are made available only to the a3 a1a5a4 a0a7a6 pair that generated them. For example, the axiom nn NNC(x3,x1,x2)</Paragraph>
    </Section>
    <Section position="3" start_page="822" end_page="822" type="sub_section">
      <SectionTitle>
4.3 World Knowledge Axioms
</SectionTitle>
      <Paragraph position="0"> Because, sometimes, the lexical or the syntactic knowledge cannot solve an entailment pair, we exploit the WordNet glosses, an abundant source of world knowledge. We used the logic forms of the glosses provided by eXtended WordNet8 to, automatically, create our world knowledge axioms. For example, the first sense of noun Pope and its definition the head of the Roman Catholic Church introduces the axiom Pope NN(x1)  died, became a place of celebration, as Roman Catholic faithful gathered in downtown Chicago to mark the installation of new Pope Benedict XVI. and a0 : Pope Benedict XVI is the new leader of the Roman Catholic Church.</Paragraph>
      <Paragraph position="1"> We also incorporate in our system a small common-sense knowledge base of 383 hand-coded world knowledge axioms, where 153 have been manually designed based on the entire de- null velopment set data, and 230 originate from previous projects. These axioms express knowledge that could not be derived from WordNet regarding employment9, family relations, awards, etc.</Paragraph>
    </Section>
  </Section>
  <Section position="7" start_page="822" end_page="823" type="metho">
    <SectionTitle>
5 Semantic Calculus
</SectionTitle>
    <Paragraph position="0"> The Semantic Calculus axioms combine two semantic relations identified within a text fragment and increase the semantic connectivity of the text (Tatu and Moldovan, 2005). A semantic axiom which combines two relations, a1 a30 and a1a3a2 , is devised by observing the semantic connection between the a4 a4 and a4a6a5 words for which there exists at least one other word, a4 a6 , such that a1 a30 a3a7a4 a4 a4a8a4 a6 a6</Paragraph>
    <Paragraph position="2"> a4a10a5 ) hold true.</Paragraph>
    <Paragraph position="3"> We note that not any two semantic relations can be combined: a1 a30 and a1a3a2 have to be compatible with respect to the part-of-speech of the common argument. Depending on their properties, there are up to 8 combinations between any two semantic relations and their inverses, not counting the combinations between a semantic relation and itself10. Many combinations are not semantically significant, for example, KINSHIP SR(x1,x2) &amp; TEMPORAL SR(x2,e1) is unlikely to be found in text. Trying to solve the semantic combinations one comes upon in text corpora, we analyzed the RTE development corpora and devised rules for some of the a1 a30a14a13 a1a3a2 combinations encountered. We validated these axioms by checking all the a3a7a4a83a4 a4a8a4 a5 a6 pairs from the LA Times text collection such that a3</Paragraph>
    <Paragraph position="5"> holds. We have identified 82 semantic axioms that show how semantic relations can be combined. These axioms enable inference of unstated meaning from the semantics detected in text.</Paragraph>
    <Paragraph position="6"> For example, if a1 states explicitly the KINSHIP (KIN) relations between Nicholas Cage and  the system infers that John lives in Texas. The system applies the 82 axioms independent of the concepts involved in the semantic composition. There are rules that can be applied only if the concepts that participate satisfy a certain condition or if the relations are of a certain type. For example, LOCATION SR(x1,x2)</Paragraph>
    <Paragraph position="8"> relation shows inclusion (John is in the car in the garage a16 LOCATION SR(John,garage).</Paragraph>
    <Paragraph position="9"> John is near the car behind the garage a2a16</Paragraph>
  </Section>
  <Section position="8" start_page="823" end_page="823" type="metho">
    <SectionTitle>
LOCATION SR(John,garage)).
6 Temporal Axioms
</SectionTitle>
    <Paragraph position="0"> One of the types of temporal axioms that we load in our logic prover links specific dates to more general time intervals. For example, October 2000 entails the year 2000. These axioms are automatically generated before the search for a proof starts. Additionally, the prover uses a SUMO knowledge base of temporal reasoning axioms that consists of axioms for a representation of time points and time intervals, Allen (Allen, 1991) primitives, and temporal functions. For example, during is a transitive Allen primitive: during TMP(e1,e2) &amp; during TMP(e2,e3) a16 during TMP(e1,e3).</Paragraph>
  </Section>
class="xml-element"></Paper>