File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/06/w06-1808_metho.xml
Size: 22,334 bytes
Last Modified: 2025-10-06 14:10:46
<?xml version="1.0" standalone="yes"?> <Paper uid="W06-1808"> <Title>Numerical Data Integration for Cooperative Question-Answering</Title> <Section position="4" start_page="0" end_page="0" type="metho"> <SectionTitle> 1.2.4 Alternative </SectionTitle> <Paragraph position="0"> The alternative relation defines a set of inconsistent answers. In the case of questions expecting a unique answer, only one answer among candidates is correct. On the contrary, all candidates can be correct answers.</Paragraph> <Paragraph position="1"> (1) A simple solution is to propose a disjunc null tion of candidate answers. For example, if the question When does autumn begin? has the candidate answers Autumn begins on September 21st and Autumn begins on September 20th, an answer such as Autumn begins on either September 20th or September 21st can be proposed. (Moriceau, 2005) proposes an integration method for answers of type date.</Paragraph> <Paragraph position="2"> (2) If candidate answers have common characteristics, it is possible to integrate them according to these characteristics (&quot;greatest common denominator&quot;). For example, the question When does the &quot;f^ete de la musique&quot; take place? has the following answers June 1st 1982, June 21st 1983, ..., June 21st 2005. Here, the extraction engine selects pages containing the dates of music festivals over the years. Since these candidate answers have day and month in common, an answer such as The &quot;f^ete de la musique&quot; takes place every June 21st can be proposed (Moriceau, 2005).</Paragraph> <Paragraph position="3"> (3) Numerical values can be integrated in the form of an interval, average or comparison. For example, if the question How far is Paris from Toulouse? has the candidate answers 713 km, 678 km and 681 km, answers such as Paris is at about 690 km from Toulouse (average) or The distance between Paris and Toulouse is between 678 and 713 km (interval) can be proposed.</Paragraph> </Section> <Section position="5" start_page="0" end_page="5" type="metho"> <SectionTitle> 2 Motivations </SectionTitle> <Paragraph position="0"> In this paper, we focus on answer elaboration from several answers of type numerical (case (3) above). Numerical questions deal with numerical properties such as distance, quantity, weight, age, etc. In order to identify the different problems, let us consider the following example : What is the average age of marriage in France? - In 1972, the average age of marriage was 24.5 for men and 22.4 for women. In 2005, it is 30 for men and 28 for women.</Paragraph> <Paragraph position="1"> - According to an investigation carried out by FNAIM in 1999, the average age of marriage is 27.7 for women and 28.9 for men.</Paragraph> <Paragraph position="2"> - The average age of marriage in France increased from 24.5 to 26.9 for women and from 26.5 to 29 for men between 1986 and 1995.</Paragraph> <Paragraph position="3"> This set of potential answers may seem incoherent but their internal coherence can be made ap- null parent once a variation criterion is identified. In a cooperative perspective, an answer can be for example: null In 2005, the average age of marriage in France is 30 for men and 28 for women.</Paragraph> <Paragraph position="4"> It increased by about 5.5 years between 1972 and 2005.</Paragraph> <Paragraph position="5"> This answer is composed of: 1. a direct answer to the question, 2. an explanation characterizing the variation mode of the numerical value.</Paragraph> <Paragraph position="6"> To generate this kind of answer, it is necessary (1) to integrate candidate answers in order to elaborate a direct answer (for example by solving inconsistencies), and (2) to integrate candidate answers characteristics in order to generate an explanation. In the following sections, we first define a typology of numerical answers and then briefly present the general architecture of the system which generates cooperative numerical answers.</Paragraph> <Section position="1" start_page="0" end_page="0" type="sub_section"> <SectionTitle> 2.1 A typology of numerical answers </SectionTitle> <Paragraph position="0"> To define the different types of numerical answers, we collected a set of 80 question-answer pairs about prices, quantities, age, time, weight, temperature, speed and distance. The goal is to identify for each question-answer pair: - if the question expects one or several answers (learnt from texts and candidate answers), - why extracted numerical values are different (is this an inconsistency? an evolution?).</Paragraph> <Paragraph position="1"> 2.1.1 The question accepts only one answer For example, How long is the Cannes International Film Festival?. In this case, if there are several candidate answers, there is an inconsistency which has to be solved (cf. section 4.1).</Paragraph> <Paragraph position="2"> This is the case when numerical values vary according to certain criteria. Let us consider the following examples.</Paragraph> <Paragraph position="3"> Example 1 : How many inhabitants are there in France? - Population census in France (1999): 61632485. - 61.7: number of inhabitants in France in 2004. In this example, the numerical value (quantity) is a property which changes over time (1999, 2004). - In Iran, the average age of marriage of women went from 19 to 21 years in 2004.</Paragraph> <Paragraph position="4"> - In 2004, Moroccan women get married at the age of 27.</Paragraph> <Paragraph position="5"> In this example, the numerical value (age of marriage) varies according to place (in Iran, Moroccan).</Paragraph> <Paragraph position="6"> Example 3 : At which temperature do I have to serve wine? - Red wine must be served at room temperature. - Champagne: between 8 and 10 @ C.</Paragraph> <Paragraph position="7"> - White wine: between 8 and 11 @ C.</Paragraph> <Paragraph position="8"> Here, the numerical value (temperature) varies according to the question focus (wine). The corpus analysis allows us to identify 3 main variation criteria, namely time, place and restriction (restriction on the focus, for example: Champagne/wine). These criteria can be combined: some numerical values vary according to time and place, to time and restrictions, etc. (for example, the average age of marriage vary according to time, place and restrictions on men/women). Note that there are several levels of restrictions and that only restrictions of the same type can be compared (cf. section 3.2). For example, metropolitan population and population of overseas regions are restrictions of the same ontological type (geographical place) whereas prison population is a restriction of a different type and is not comparable to the previous ones.</Paragraph> </Section> <Section position="2" start_page="0" end_page="0" type="sub_section"> <SectionTitle> 2.2 Architecture of the system </SectionTitle> <Paragraph position="0"> Figure 1 presents the general architecture of our system which allows us to generate answers and explanations from several different numerical answers. null Questions are submitted in natural language to QRISTAL which analyses them (focus, answer expected type) and which selects potential answers from the web: QRISTAL searches web pages containing the keywords of the query and synonyms (extraction engine). Then, an extraction grammar constructs a set of frames from candidate web pages. From the frame set, the variation criteria and mode of the searched numerical value are identified. Finally, a natural language answer is generated explaining those characteristics. Each of these stages is presented in the next sections.</Paragraph> <Paragraph position="1"> 3 Answer characterization Answer characterization consists in 2 main stages: - information extraction from candidate web pages, - characterization of variation (criteria and mode) of numerical values if necessary.</Paragraph> </Section> <Section position="3" start_page="0" end_page="5" type="sub_section"> <SectionTitle> 3.1 Answer extraction </SectionTitle> <Paragraph position="0"> Once QRISTAL has selected candidate web pages (those containing the question focus and having the expected semantic type), a grammar is applied to extract information needed for the generation of an appropriate cooperative answer.</Paragraph> <Paragraph position="1"> This information is mainly: - the searched numerical value (val), - the unit of measure, - the question focus and its synonyms (focus) (for the moment, synonyms are not considered because it requires a lot of resources, especially in an open domain), - the date and place of the information, - the restriction(s) on the question focus (essentially, adjectives or relative clauses). In addition, the corpus analysis shows that some other information is essential for infering the precision degree or the variation mode of values. It is mainly linguistic clues indicating: - the precision of the numerical value (for example adverbs or prepositions such as in about 700, ...), - a variation of the value (for example temporal adverbs, verbs of change/movement as in the price increased to 200 euro).</Paragraph> <Paragraph position="2"> We define a frame ai which gathers all this information for a numerical value: A dedicated grammar extracts this information from candidate web pages and produces the set A of N candidate answers: A = fa1; :::; aNg. We use a gapping grammar (Dahl and Abramson, 1984) to gap elements which are not useful (in the example According to an investigation carried out by FNAIM in 1999, the average age of marriage is 27.7 for women and 28.9 for men, elements in bold are not useful). We give below the main rules of the grammar, optional elements are A syntactic analysis is also necessary to check the relevance of extracted information. For example, suppose that the answer population of cities of France which have more than 2000 inhabitants (...) is proposed to the question How many inhabitants are there in France?. A syntactic analysis has to identify the expression cities of France which (...) as a restriction of population and to infer that 2000 inhabitants is a property of those cities and that it is not an answer to the question. We plan to investigate the lexical elements (prepositions, predicative terms, etc.) necessary to this analysis.</Paragraph> <Paragraph position="3"> Elements of extraction evaluation are presented in figure 3: we submitted 30 questions to Google and QRISTAL. Our system can select the correct direct answer provided that QRISTAL returns the correct answer among relevant pages (for 87% of the questions we evaluated) and that our grammar succeeds in extracting relevant information (this has to be evaluated).</Paragraph> </Section> <Section position="4" start_page="5" end_page="5" type="sub_section"> <SectionTitle> 3.2 Variation criteria </SectionTitle> <Paragraph position="0"> Once we have the frames representing the different numerical values, the goal is to determine if there is a variation and to identify the variation criteria of the value. In fact, we assume that there is a variation if there is at least k different numerical values with different criteria (time, place, restriction) among the N frames (k is a rate which depends on N: the more candidate answers there are, the greater is k). Thus, a numerical value varies according to: 1. time if card (fai; such as 9 ai; aj 2 A;</Paragraph> <Paragraph position="2"> 2. place if card (fai; such as 9 ai; aj 2 A;</Paragraph> <Paragraph position="4"> 4. time and place if (1) ^ (2) 5. time and restriction if (1) ^ (3) 6. place and restriction if (2) ^ (3) 7. time, place and restriction if (1)^(2)^(3) Numerical values can be compared only if they have the same unit of measure. If not, they have to be converted.</Paragraph> <Paragraph position="5"> For each criterion (time, place or restriction), only information of the same semantic type and of the same ontological level can be compared. For example, metropolitan population and prison population are restrictions of a different ontological level and cannot be compared. In the same way, place criteria can only be compared if they have the same ontological level: for example, prices in Paris and in Toulouse can be compared because the ontological level of both places is city. On the contrary, prices in Paris and in France cannot be compared since the ontological levels are respectively city and country. Several ontologies of geographical places exist, for example (Maurel and Piton, 1999) but a deep analysis of restrictions is necessary to identify the kind of implied knowledge. null In the particular cases where no information has been extracted for some criteria, it is also necessary to define some comparison rules. Thus, let crit 2 ftime; place; restrictiong and ai; aj 2 A, - if no information has been extracted for 2 compared criteria, then we consider that those criteria are equal (there is no information indicating that there is a variation according to those criteria),</Paragraph> <Paragraph position="7"> - if no information has been extracted for one of the 2 compared criteria, then we consider that those criteria are different (there is a variation), i.e. if ai(crit) = ; and aj(crit) 6= ;, then ai(crit) 6= aj(crit) In the example of figure 2, the price varies according to time, place and restriction. In the following example (figure 4), the price of gas varies according to time (September 2005/ ;) and place (Paris/Toulouse). For space reasons, we give only 2 frames for each example but it is obviously not sufficient to conclude.</Paragraph> <Paragraph position="8"> Variation criteria of numerical values are learnt from texts but can also be infered (or confirmed), for some domains, by common knowledge. For example, the triangle inequality states that for any three points x;y;z, we have: distance(x, y) distance(x, z) + distance(z, y). From this, we can infer that a distance between two points vary according to restriction (itinerary). In the following sections, we focus on numerical values which vary according to time.</Paragraph> </Section> <Section position="5" start_page="5" end_page="5" type="sub_section"> <SectionTitle> 3.3 Variation mode </SectionTitle> <Paragraph position="0"> The last step consists in identifying the variation mode of values. The idea is to draw a trend (increase, decrease, ...) of variaton in time so that an explanation can be generated. For this purpose, we have a set of couples (numerical value, date) representing the set of extracted answers. From this set, we draw a regression line (a line which comes as close to the points as possible) which determines the relationship between the two variables value and date.</Paragraph> <Paragraph position="1"> The correlation between two variables reflects the degree to which the variables are related. In particular, Pearson's correlation (r) reflects the degree of linear relationship between two variables.</Paragraph> <Paragraph position="2"> It ranges from +1 to 1. A correlation of +1 means that there is a perfect positive linear relationship between variables. For example, figure 5 shows that a positive Pearson's correlation implies a general increase of values (trend) whereas a negative Pearson's correlation implies a general decrease. On the contrary, if r is low ( 0:6 < r < 0:6), then the trend (increase or decrease) is This method determines the variation mode of numerical values (it gives a variation trend) and determines if the values are strongly dependent on time or not (the highest r is, the more the numerical values are dependent on time).</Paragraph> <Paragraph position="3"> Figure 6 shows the results for the question How many inhabitants are there in France? Different numerical values and associated dates are extracted from web pages. The Pearson's correlation is 0:682 meaning that the number of inhabitants increases according to time (between 1999 and 2005).</Paragraph> </Section> </Section> <Section position="6" start_page="5" end_page="5" type="metho"> <SectionTitle> 4 Answer generation </SectionTitle> <Paragraph position="0"> Once the searched numerical values have been extracted and characterized by their variation criteria and mode, a cooperative answer is generated in natural language. It is composed of two parts: are there in France? In the following sections, we present some prerequisites to the construction of each of these parts in term of resources and knowledge.</Paragraph> <Section position="1" start_page="5" end_page="5" type="sub_section"> <SectionTitle> 4.1 Direct answer generation </SectionTitle> <Paragraph position="0"> There are mainly two cases: either one or several criteria are constrained by the question (as in How many inhabitants are there in France in 2005? where criteria of place and time are given), or some criteria are omitted (or implicit) (as in How many inhabitants are there in France? where there is no information on time). In the first case, the numerical value satisfying the constraints is chosen (unification between the criteria of the question and those extracted from web pages). In the second case, we assume that the user wants to have the most recent information.</Paragraph> <Paragraph position="1"> We focus here on answers which vary according to time. Aberrant values are first filtered out by applying classical statistical methods. Then, when there is only one numerical value which satisfies the temporal constraint (given by the question or the most recent date), then the direct answer is generated from this value. When there is no numerical value satisfying the temporal constraint, only the second part of the answer (explanation) is generated.</Paragraph> <Paragraph position="2"> In the case of several numerical values satisfying the temporal constraint, there may be approximate values. For example, the following answers (cf figure 6) are extracted for the question How many inhabitants were there in France in 2004?: (1) 61.7 millions: number of inhabitants in France in 2004.</Paragraph> <Paragraph position="3"> (2) In 2004, the French population is estimated to 61 millions.</Paragraph> <Paragraph position="4"> (3) There are 62 millions of inhabitants in France in 2004.</Paragraph> <Paragraph position="5"> Each of these values is more or less approximate. The goal is then to identify which values are approximate and to decide which numerical value can be used for the generation task.</Paragraph> <Paragraph position="6"> For that purpose, we proposed to 20 subjects a set of question-answer pairs. For each question, subjects were asked to choose one answer among a set of precise and approximate values and to explain why. For the previous question, 75% of the subjects prefer answer (1) because it is the most precise one, even if they consider it as an approximation. In majority, subjects explain that an approximate value is sufficient for great numbers and that values must not be rounded up (they proposed 61.7 millions or almost 62 millions as an answer). On the contrary, subjects do not accept approximate values in the financial domain (price, salary, ...) but rather prefer an interval of values.</Paragraph> <Paragraph position="7"> Thus, the direct answer is generated from the most precise numerical value if available. If all values are approximate, then the generated answer has to explain it: we plan to use prepositions of approximation (about, almost, ...) or linguistics clues which have been extracted from web pages (precision in the frames). The choice of a particular preposition depends on the degree of precision/approximation of numerical values: PrepNet (Saint-Dizier, 2005) provides a relatively deep description of preposition syntactic and semantic behaviours. null</Paragraph> </Section> <Section position="2" start_page="5" end_page="5" type="sub_section"> <SectionTitle> 4.2 Explanation generation </SectionTitle> <Paragraph position="0"> Obviously, the generation of the cooperative part of the answer is the most complex because it requires complex lexical knowledge. We present briefly some of the necessary lexical resources.</Paragraph> <Paragraph position="1"> For example, verbs can be used in the answer to express numerical variations. Lexical descriptions are necessary and we use for that purpose a classification of French verbs (Saint-Dizier, 1999) based on the main classes defined by WordNet. The classes we are interested in for our task are mainly those of verbs of change (increase, decrease, etc.: in total, 262 verbs in French) and of verbs of movement (climb, move forward/backward, etc.: in total, 252 verbs in French) used metaphori48 KRAQ06 cally (Moriceau and Saint-Dizier, 2003). From these classes, we have characterized sub-classes of growth, decrease, etc., so that the lexicalisation task is constrained by the type of verbs which has to be used according to the variation mode (if verbs are extracted from web pages as linguistics clues of variation, they can also be reused in the answer).</Paragraph> <Paragraph position="2"> A deep semantics of verbs (change, movement) is necessary to generate an answer which takes into account the characteristics of numerical variation as well as possible: for example, the variation mode but also the speed and range of the variation. Thus, for each sub-class of verbs and its associated variation mode, we need a refined description of ontological domains and selectional restrictions so that an appropriate verb lexicalisation can be chosen: which verb can be applied to prices, to age, etc.? We plan to use proportional series representing verb sub-classes according to the speed and amplitude of variation. For example, the use of climb (resp. drop) indicates a faster growth (resp. decrease) than go up (resp. go down): the verb climb is prefered for the generation of The increase of gas prices climb to 20.3% in october 2005 whereas go up is prefered in The increase of gas prices go up to 7.2% in september 2005.</Paragraph> <Paragraph position="3"> As for direct answer generation, verbs can possibly be associated with a preposition that refines the information (The average age of marriage increased by about 5.5 years between 1972 and 2005).</Paragraph> </Section> </Section> class="xml-element"></Paper>