<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-1210">
  <Title>Automatic Detection of Causal Relations for Question Answering</Title>
  <Section position="5" start_page="0" end_page="0" type="evalu">
    <SectionTitle>
5 Results
</SectionTitle>
    <Paragraph position="0"> To validate the constraints for extracting causal relations, we used the test corpus &amp;quot;B&amp;quot;.</Paragraph>
    <Paragraph position="1"> For each head of the noun phrases in the CAUSE and EFFECT positions, the system determined automatically the most general subsumers in WordNet for each sense. The test corpus contained 683 relationships of the type a0a2a1a4a3 a5 verb a1a4a3a32a15a18a17 , from which only 115 were causal patterns. The results provided by the causal relation discovery procedure were validated by a human annotator.</Paragraph>
    <Paragraph position="2"> Let us define the precision and recall performance metrics in this context.</Paragraph>
    <Paragraph position="4"> The system retrieved 138 relations, of which 102 were causal relations and 36 were non-causal relations, yielding a precision of 73.91% and a recall of 88.69%. Table 3 shows the results obtained for the pattern considered.</Paragraph>
    <Paragraph position="5"> However, there were other 38 causal relations found in the corpus, expressed by other than the lexico-syntactic pattern considered in this paper,  The errors are explained mostly by the fact that the causal pattern is very ambiguous. This lexico-syntactic pattern encode numerous relations which are very difficult to disambiguate based only on the list of connectors.</Paragraph>
    <Paragraph position="6"> The errors were also caused by the incorrect parsing of noun phrases, the use of the rules with smaller accuracy (e.g. 63a0 ), and the lack of named entities recognition in WordNet (e.g., names of people, places, etc.).</Paragraph>
    <Paragraph position="7"> Some of the factors that contributed a lot to the precision and recall results were the size and the accuracy of the positive and negative examples in the training corpus. For this experiment we used only a fairly small training corpus of 6,523 examples.</Paragraph>
  </Section>
  <Section position="6" start_page="0" end_page="0" type="evalu">
    <SectionTitle>
6 Importance and application of causal
</SectionTitle>
    <Paragraph position="0"> relations in Question Answering Causation relationships are very pervasive, but most of the time they are ambiguous or implicit. The degree of ambiguity of these relations varies with the semantic possibilities of interpretation of the constituent syntactic terms. This disambiguation proves to be very useful for applications like Question Answering. null Causation questions can be mainly introduced by the following question types: what, which, name (what causes/be the cause of, what be the effect of, what happens when/after, what cause vb a0 objecta17 ),  accuracy for the causal pattern used for this research. how (how a0 causation adja17 ), and why. However, an analysis of these question types alone is not sufficient for causation, another classification criteria being required. Based on our observation of cause-effect questions, we propose the following question classes based on their ambiguity: 1. Explicit causation questions The question contains explicit unambiguous key-words that define the type of relation, and determines the semantic type of the question (e.g., effect, cause, consequence, etc.) &amp;quot;What are the causes of lung cancer?&amp;quot; &amp;quot;Name the effects of radiation on health.&amp;quot; &amp;quot;Which were the consequences of Mt. Saint Elena eruption on fish?&amp;quot; 2. Ambiguous (semi-explicit) causation questions The question contains explicit but ambiguous key-words that refer to the causation relation. Once disambiguated, they help in the detection of the semantic type of the question (e.g., lead to, produce, generate, trigger, create, etc.) &amp;quot;Does watching violent cartoons create aggression in children?&amp;quot; &amp;quot;What economic events led to the extreme wealth among Americans in the early 1920's?&amp;quot; 3. Implicit causation questions This type of questions involves reasoning, based on deep semantic analysis and background knowledge.</Paragraph>
    <Paragraph position="1"> They are usually introduced by the semantic types why, what, how, and can be further classified in two important subtypes: a) Causation questions disambiguated based on the semantic analysis of question keywords &amp;quot;Why did Socrates die?&amp;quot; &amp;quot;What killed Socrates?&amp;quot; &amp;quot;How dangerousis a volcanic eruption?&amp;quot; &amp;quot;Is exercise good to the brain?&amp;quot; It is recognized that questions of type what, and even how and why, are ambiguous, and usually the question is disambiguated by other keywords in the question.</Paragraph>
    <Paragraph position="2"> In the example question &amp;quot;What killed Socrates?&amp;quot;, the verb kill is a causation verb meaning cause to die, so the second question asks for the cause of the Socrates' death.</Paragraph>
    <Paragraph position="3"> The why questions are more complex asking for explanations or justifications. Explanations can be expressed in English in different ways, not always referring to causation. Thus, it is very difficult to determine directly from the question what kind of information we should look for in the answer.</Paragraph>
    <Paragraph position="4"> b) Causation questions that are disambiguated based on how the answer is expressed in the text Behavioral psychologists illustrated that there are several different ways of answering why questions in biology. For example, the question &amp;quot;Why do robins sing in the spring?&amp;quot; can have multiple categories of answers: Causation. (What is the cause?) Answer: &amp;quot;Robins sing in spring because increases in day length trigger hormonal action&amp;quot;.</Paragraph>
    <Paragraph position="5"> Development. (How does it develop?) Answer: &amp;quot;Robins sing in spring because they have learned songs from their fathers and neighbors.&amp;quot; Origin. (How did it evolve?) Answer: &amp;quot;Song evolved as a means of communication early in the avian lineage&amp;quot;.</Paragraph>
    <Paragraph position="6"> Function. (What is the function?) Answer: &amp;quot;Robins sing in spring to attract mates.&amp;quot; The algorithm for automatic extraction of causation relations presented in section 4 was tested on a list of 50 natural language causation questions (50 explicit and 50 ambiguous) using a state-of-the-art Question Answering system (Harabagiu et al. 2001). The questions were representative for the first two categories of causation questions presented above, namely explicit and ambiguous causation questions. We selected for this purpose the TREC9 text collection and we (semi-automatically) searched it for 50 distinct relationships of the type a0a2a1a4a3 a5a30a7a10a9a12a11a14a13 a1a4a3 a15 a17 , where the verb was one of the 60 causal verbs considered. For each such relationship we formulated a cause-effect question of the first two types presented above. We also made sure each question had the answer in the documents generated by the IR module.</Paragraph>
    <Paragraph position="7"> Table 4 shows two examples of questions from each class. We also considered as good answer any other correct answer different from the one represented by the causal pattern. However these answers were not taken into consideration in the precision calculation of the QA system with the causation module included. The rational was that we wanted to measure only the contribution of the causal relations method. The 50 questions were tested on the QA system with (61% precision) and without (36% precision) the causation module included, with a gain in precision of 25%.</Paragraph>
  </Section>
class="xml-element"></Paper>