JP2013143066A - Question and answer program, server and method which use large amount of comment texts - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a question and answer server etc. which can clearly show (or narrow down to) an answer sentence in which a user intention is reflected, when there are a plurality of candidates for the answer sentence to a question sentence from the user.SOLUTION: A question and answer program comprises: question keyword extraction means which extracts a plurality of question keywords from a question sentence; comment text retrieval means which retrieves comment texts including the question keywords; topic classification means which classifies the retrieved plurality of comment texts into a plurality of topic groups; answer sentence detection means which associates an answer sentence whose similarity with each topic and each answer sentence becomes more than a prescribed threshold; representative keyword extraction means which extracts a representative keyword for each topic; differential keyword extraction means which extracts the representative keyword occurring only in the topic as a differential keyword; differential keyword selection means which clearly shows a plurality of differential keywords to a user so as to be selectable; and answer sentence output means which clearly shows the answer sentence corresponding to the differential keywords to the user.

Description

  The present invention relates to a technique for a question answering program that outputs an optimum answer sentence in response to a question sentence input.

In recent years, a question answering system based on FAQ (Frequently Asked Questions) has been constructed. “FAQ” refers to a collection of answers to questions that are frequently asked by many people in common. The question answering system is software that inputs a question sentence concerning a specific type of information from a user in a natural language and outputs the answer sentence. Generally, the question answering system stores a virtual question sentence and an answer candidate sentence associated therewith in a database in advance. In addition, the question answering system executes processing in the following steps.
(1) A characteristic word is extracted as a query from a question sentence input by a user.
(2) Using a search engine, select a virtual question sentence with a high appearance frequency of a plurality of queries.
(3) Select an answer sentence for the selected virtual selection sentence.
(4) Present the selected answer sentence to the user.

  Some of such question answering systems exist as a single device for the user, and others are connected as a question answering server on the Internet. The question answering server receives a question sentence from a user-operated terminal via a network, and transmits the answer sentence to the terminal (see, for example, Non-Patent Document 1).

  As another technique, a blog (Web log) server or a mini blog (for example, twitter (registered trademark)) server is connected to the Internet. Such a blog server receives comment texts from an unspecified number of third parties and publishes them to other third parties. Such comment texts are disclosed on various topics, and of course, a lot of comment texts related to the question texts and answer texts input to and output from the question answering system described above are also discussed.

JP 2011-81626 A JP 2005-141428 A JP 2005-284209 A

KDDI, "au one NET Concierge", [online], [Search on December 18, 2011], Internet <URL: http://concierge.auone-net.jp/inagoNetPeople/BrowserClient/GUI/help.html> Masashi Tsubosaka, “Introduction to Latent Dirichlet Allocation”, [online], [Search December 18, 2011], Internet <URL: http://www.slideshare.net/tsubosaka/tokyotextmining>

  However, there may be a plurality of intentions of the user's question even in the same question sentence. In such a case, an appropriate answer sentence is often not returned to the user.

Examples of user questions Q “Lost mobile phone”
For this question sentence, the question answering system extracts the following two keywords.
"Mobile phone""Lost"
When answer sentences are searched using these keywords as queries, there are a plurality of answer options.
A “Responding to“ How to find a mobile phone and secure service ”A Answer to“ How to use mobile phone to find a safe service ”In this case, the user inquires about“ how to use ”to lock a lost mobile phone remotely. In spite of the intention, the question answering system may answer about the “application method”.

  Therefore, the present invention provides a question answering program, server, and method capable of clearly specifying (restricting to) an answer sentence reflecting the user's intention when there are a plurality of answer sentence candidates for the user's question sentence. The purpose is to provide.

According to the present invention, the computer has a comment text storage unit that stores a large number of comment texts and an answer text storage unit that stores a large number of response texts, and extracts a response text to a question text from a user. A question answering program that works,
A question sentence input means for inputting a question sentence;
A question keyword extracting means for extracting a plurality of question keywords included in a question sentence;
Comment text search means for searching for comment text containing a question keyword using the comment text storage unit;
A topic classification means for classifying a plurality of searched comment sentences into a plurality of topic groups from the distribution of appearance words;
An answer sentence detection means for calculating a similarity between a comment sentence group included in each topic group and a sentence included in each answer sentence, and associating an answer sentence having a similarity equal to or greater than a predetermined threshold with each topic group;
For each topic group, representative keyword extraction means for extracting a representative keyword characterizing the topic group from the keywords included in the associated answer sentence;
For each topic group, a differential keyword extraction unit that extracts a representative keyword that appears only in the topic group as a differential keyword;
The computer is caused to function as an answer sentence output means for clearly indicating an answer sentence detected by the answer sentence detecting means together with one or more corresponding difference keywords.

According to another embodiment of the question answering program of the present invention,
A differential keyword selecting unit that clearly indicates a plurality of differential keywords to the user via the user interface and that selects any one differential keyword according to a user operation,
The answer sentence output means preferably causes the computer to function so as to clearly indicate the answer sentence corresponding to the selected difference keyword via the user interface.

According to another embodiment of the question answering program of the present invention,
The topic classification means uses a computer to classify the comment text into any one topic group using an LDA (Latent Dirichlet Allocation) algorithm that calculates the likelihood (topic ratio) belonging to each classified topic group. It is also preferable to function.

According to another embodiment of the question answering program of the present invention,
The question keyword extraction means extracts a keyword from a question sentence by morphological analysis, and extracts a characteristic word as a question keyword by TF-IDF (Term Frequency-Inverse Document Frequency). ,
And / or
The representative keyword extracting means preferably extracts the keyword from the answer sentence by morphological analysis and also causes the computer to function so as to extract a characteristic word as a representative keyword by TF-IDF.

According to another embodiment of the question answering program of the present invention,
Answer detection means
A keyword is extracted by morphological analysis from a comment sentence group included in each topic group, and a first feature vector in the topic group is calculated by TF-IDF.
A keyword is extracted from each answer sentence stored in the answer sentence storage unit by morphological analysis, and a second feature vector in the answer sentence is calculated by TF-IDF.
It is also preferable to cause the computer to function to calculate the similarity based on the cosine distance between the first vector of the topic group and the second vector of the answer sentence.

According to another embodiment of the question answering program of the present invention,
The representative keyword extracting means preferably causes the computer to function so that the representative keywords of each topic group are arranged in priority order according to the Akaike information amount standard.

According to another embodiment of the question answering program of the present invention,
Comment text is posted by an unspecified number of third parties,
It is also preferable that the comment text storage unit allows the computer to function so as to collect and store the comment text posted on the mini web log server.

According to the present invention, there is provided a question answering server that has a comment sentence accumulating unit that accumulates a large number of comment sentences and an answer sentence accumulating unit that accumulates a large number of answer sentences, and extracts an answer sentence for a question sentence from a user. There,
A question sentence input means for inputting a question sentence from a terminal;
A question keyword extracting means for extracting a plurality of question keywords included in a question sentence;
Comment text search means for searching for comment text containing a question keyword using the comment text storage unit;
A topic classification means for classifying a plurality of searched comment sentences into a plurality of topic groups from the distribution of appearance words;
A comment sentence group included in each topic group and an answer sentence calculating means for calculating a similarity between each answer sentence and associating each topic group with an answer sentence having a similarity equal to or greater than a predetermined threshold;
For each topic group, representative keyword extraction means for extracting a representative keyword characterizing the topic group from the keywords included in the associated answer sentence;
For each topic group, a differential keyword extraction unit that extracts a representative keyword that appears only in the topic group as a differential keyword;
Answer text output means for clearly indicating the answer text detected by the answer text detection means together with one or more corresponding difference keywords.

According to another embodiment of the question answering server of the present invention,
A differential keyword selecting unit that clearly indicates a plurality of differential keywords to the user via the user interface and that selects any one differential keyword according to a user operation,
It is also preferable that the answer sentence output means clearly indicates the answer sentence corresponding to the selected difference keyword via the user interface.

According to the present invention, a question answer in an apparatus that has a comment text storage unit that stores a large number of comment texts and a response text storage unit that stores a large number of response texts and extracts a response text to a question text from a user A method,
A first step of inputting a question sentence;
A second step of extracting a plurality of question keywords included in the question sentence;
A third step of searching for a comment sentence including a question keyword using the comment sentence storage unit;
A fourth step of classifying the plurality of searched comment sentences into a plurality of topic groups from the distribution of appearance words;
A fifth step of calculating a similarity between a comment sentence group included in each topic group and each answer sentence, and associating an answer sentence having a similarity equal to or greater than a predetermined threshold to each topic group;
For each topic group, a sixth step of extracting a representative keyword characterizing the topic group from the keywords included in the associated answer sentence;
For each topic group, a seventh step of extracting a representative keyword that appears only in the topic group as a difference keyword;
And an eighth step of clearly indicating the answer sentence detected by the fifth step together with the corresponding one or more difference keywords.

According to another embodiment of the question answering method of the present invention,
For the eighth step,
A plurality of difference keywords are clearly indicated to the user via the user interface, and one of the difference keywords is selected according to a user operation.
It is also preferable to clearly indicate the answer sentence corresponding to the selected difference keyword via the user interface.

  According to the question answering program, server and method of the present invention, when there are a plurality of answer sentence candidates for the user's question sentence, the answer sentence reflecting the user's intention can be clearly specified (restricted). .

It is a system configuration diagram in the present invention. It is a function block diagram of the question answering server in this invention. It is explanatory drawing showing the process of a question keyword extraction part and a comment text search part. It is explanatory drawing showing the process of a topic classification | category part. It is explanatory drawing showing the process of an answer sentence detection part. It is explanatory drawing showing the process of a representative keyword extraction part, a difference keyword extraction part, a difference keyword selection part, and an answer sentence output part. It is a sequence diagram in the present invention.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a system configuration diagram according to the present invention.

  According to FIG. 1, a question answering server 1 according to the present invention is connected to the Internet. The question answering server 1 may store the answer text in advance, or may receive the answer text from another answer text storage server 2. According to the present invention, there is no need to associate and store question sentence candidates and answer sentence candidates such as FAQ in advance. Only answer sentence candidates are stored in advance.

  The terminal 4 operated by the questioner accesses the question answering server 1 via the access network and the Internet. Then, the terminal 4 transmits the question text to the question answering server 1 and receives the answer text from the question answering server 1. In the following embodiment, it is assumed that the questioner inputs the natural language text to the terminal 4, but the questioner may be input by voice and converted into text.

  In addition, according to FIG. 1, a blog server 2 that publishes comment text posted by an unspecified number of third parties is further connected to the Internet. The blog server 3 is a mini blog server such as a twitter (registered trademark) server. An unspecified number of third parties can freely post a comment sentence to the miniblog server 3 using the terminal 5 possessed by the third party.

  The question answering server 1 in the present invention collects a large amount of comment text from the miniblog server 3. Then, when there are a plurality of answer sentence candidates for the user's question sentence, the question / answer server 1 specifies (restricts) the answer sentence reflecting the user's intention using the collected comment sentences.

  FIG. 2 is a functional configuration diagram of the question answering server according to the present invention.

  According to FIG. 2, the question answering server 1 includes a communication interface unit 10, an answer sentence accumulating part 101, an answer sentence acquiring part 111, a comment sentence accumulating part 102, and a comment sentence collecting part 112.

  The answer sentence storage unit 101 stores a large number of answer sentences. The answer sentence acquisition unit 111 may receive these answer sentences from the answer sentence storage server 2 via the network and store them in the answer sentence storage unit 101.

  The comment text storage unit 102 stores a large number of comment text posted by an unspecified number of third parties. The comment text collection unit 112 may receive these comment texts from the blog server 3 via the network and store them in the comment text storage unit 102.

  The “comment text” is, for example, a Japanese “tweet” (maximum number of characters: 140 characters) transmitted by twitter (registered trademark). The comment text includes, for example, a user id (from_user_id), a tweet ID (id_str), a transmission time (created_at), and a tweet (texts). Here, the comment sentence collection unit 112 can also collect only comment sentences including a plurality of keywords specified in advance.

  2, the question answering server 1 includes a question sentence input unit 121, a question keyword extraction unit 122, a comment sentence search unit 123, a topic classification unit 124, an answer sentence detection unit 125, and a representative keyword. An extraction unit 126, a difference keyword extraction unit 127, a difference keyword selection unit 128, and an answer sentence output unit 129 are included. These functional components are realized by executing a program that causes a computer mounted on the server to function.

[Question sentence input unit 121]
The question sentence input unit 121 receives a question sentence from the questioner's terminal 4 via the network. For example, the user's question text is as follows.
Q "Lost mobile phone"
The question text is output to the question keyword extraction unit 122.

  FIG. 3 is an explanatory diagram showing the processing of the question keyword extraction unit and the comment text search unit.

[Question keyword extraction unit 122]
The question keyword extraction unit 122 extracts a plurality of question keywords included in the question sentence. Here, the question keyword extraction unit 122 extracts a keyword from a question sentence by morphological analysis, and asks a characteristic word by TF-IDF (Term Frequency-Inverse Document Frequency) as a question. Extract as keywords.

  First, the question keyword extraction unit 122 extracts words from the question sentence by morphological analysis. “Morphological analysis” refers to a technique in which sentences are divided into meaningful words and the part of speech and contents are discriminated using a dictionary. The “morpheme” means the smallest unit having meaning among the elements of the sentence. Instead of searching by word unit as in morphological analysis, analysis may be performed by “N-gram” that decomposes by character unit and obtains the appearance frequency in a state including the following N-1 characters.

  Here, for example, an open source morphological analysis engine “MeCab” can be used for the morphological analysis. This engine has a hierarchical part-of-speech system and can also analyze morpheme part-of-speech. For each morpheme, parts of speech such as “noun”, “proprietary noun”, “organization”, “region”, “general”, etc. are also output.

  Next, characteristic keywords are extracted as question keywords by TF-IDF. TF-IDF is a technology that weights each word, expresses sentences from a query in a vector space, and ranks them based on the similarity between the sentences and the query. The higher the ranked value, the more important keywords are recognized.

According to the example of FIG. 3, it is extracted as follows.
Question "Lost mobile phone"
Question keyword "mobile phone""lost"

[Comment text search unit 123]
The comment text search unit 123 uses the comment text storage unit 102 to search for a comment text including the question keyword. Specifically, using a question keyword as a query, a TF (Term Frequency) value and a DF (Document Frequency) value are extracted from each comment sentence, and a plurality of comment sentences whose values are equal to or greater than a predetermined threshold are searched. The TF value refers to the appearance frequency of a search word in a sentence, and the DF value refers to the relative sentence frequency in which an index word appears. The comment text search unit 123 is a social media search function that searches only tweets related to a question keyword from a large number of posted tweets.

  According to FIG. 3, for example, four comment sentences are searched. These comment sentences include at least “mobile phone” or “lost”.

  FIG. 4 is an explanatory diagram illustrating processing of the topic classification unit.

[Topic classification unit 124]
The topic classifying unit 124 classifies the plurality of searched comment sentences into a plurality of topic groups based on the distribution of appearance words. The topic classification unit 124 classifies the comment text into any one topic group by using an LDA (Latent Dirichlet Allocation) algorithm that calculates a probability (topic ratio) belonging to each classified topic group. That is, a large number of comment sentences related to the question keyword are classified into potential topic groups.

  LDA is a technique in which a probabilistic framework based on fluctuation is introduced into a feature vector of a word with respect to a technology (LSI (latent Semantic Indexin)) for dimensional compression of a word document matrix (see Non-Patent Document 2, for example). The compressed set of dimensions is called a topic.

According to FIG. 4, the topic classification unit 124 executes processing in the following steps.
(S41) Words are extracted from a large number of comment sentences related to the question keyword, and the appearance frequency (number of appearances) for each word is input to the LDA process. And the appearance frequency of each word is counted for every comment sentence.

(S42) Next, in the LDA process, the word distribution for each topic and the topic ratio for each comment sentence (net side opinion) are acquired. This topic ratio classifies the topic group to which the comment text belongs. And the appearance frequency of each word contained in all the comment sentences is counted for every topic group.

(S43) Next, for each comment sentence, the words belonging to each topic group are counted. Then, the comment sentences are classified into topic groups with high count values.

  FIG. 5 is an explanatory diagram showing processing of the answer sentence detection unit.

[Answer sentence detector 125]
The answer sentence detection unit 125 calculates the similarity between the comment sentence group included in each topic group and the sentence included in each answer sentence, and determines an answer sentence having a similarity equal to or greater than a predetermined threshold for each topic group. Associate.

For example, the similarity is calculated as follows.
(S51) The answer sentence detection unit 125 extracts a keyword from a comment sentence group included in each topic group by morphological analysis, and calculates a first feature vector in the topic group by TF-IDF.
Each topic group: Ci (i = 1,2, ...)
Comment text included in topic group i: Tij (j = 1,2, ...)

(S52) A keyword is extracted from each answer sentence stored in the answer sentence storage unit 101 by morphological analysis, and a second feature vector in the answer sentence is calculated by TF-IDF.
Answer text: Ak (k = 1,2, ...)

(S53) The similarity is calculated based on the cosine distance between the first vector of the topic group and the second vector of the answer sentence. Specifically, a similarity Dist (Ci, Aj) between the topic group Ci including each comment sentence Ti1, Ti2,... And the answer sentence Aj is calculated.
Dist (Ci, Aj) = average value of cosin distances D (Ti1, Aj), D (Ti2, Aj), ...
= Arg _i max (Dist (Ci, Aj))

According to FIG. 5, a large number of answer sentences are accumulated in the answer sentence accumulation unit 101.
Answer 1 "..."
Answer 2 “How to apply for a secure service by searching for a mobile phone”
(・ ・ Mobile phones ... Terminals ... Safety ... Loss ... Applications ...)
Answer sentence 3 "..."
Answer sentence 4 "..."
Answer sentence 5 “How to use a secure service with a mobile search”
(・ ・ Mobile phones ... terminals ... discovery ...)
Answer 6 "..."

  According to FIG. 5, the similarity between the topic group 1 and the answer sentence 2 is higher than the predetermined threshold δ, and it is determined that both are similar. Further, the similarity between the topic group 2 and the answer sentence 5 is higher than the predetermined threshold δ, and it is determined that both are similar. As a result, zero or more answer sentences are assigned to each topic group C1, C2,.

  FIG. 6 is an explanatory diagram illustrating processing of the representative keyword extraction unit, the difference keyword extraction unit, the difference keyword selection unit, and the answer sentence output unit.

[Representative keyword extraction unit 126]
The representative keyword extraction unit 126 extracts, for each topic group, a representative keyword that characterizes the topic group from among keywords included in the associated answer sentence. Specifically, the representative keyword extraction unit 126 extracts a keyword from the answer sentence by morphological analysis, and extracts a characteristic word as a representative keyword by TF-IDF.

According to FIG. 6, the following three words are extracted as representative keywords from the answer sentence 2 corresponding to the topic group 1.
Answer 2 (How to apply for a secure service with a mobile search)
"Terminal""Reliable""Application"
Answer sentence 5 (How to use a reliable service by searching for a mobile phone)
"Terminal""Discovery"

  Here, it is preferable that the representative keyword extraction unit 126 arranges the representative keywords of each topic group in order of priority according to the Akaike information amount standard. Words appearing in any of the answer sentences assigned to the topic groups C1, C2,. Here, an index indicating whether or not the word w (i) is useful for determining the topic group Cj is given (see, for example, Patent Document 3).

Below, the calculation method of the parameter | index E (w, C) whether the word w is useful for discrimination | determination of the topic group C is represented.
(S1) The following four types of frequencies are obtained from the set U of comment sentences (tweets) included in the topic group.
n11 = number of comment sentences similar to topic group C and word w appear n12 = number of comment sentences similar to topic group C and word w appear n21 = number of comment sentences similar to topic group C and word w appear N22 = number of comment sentences that are similar to those other than topic group C and do not appear in word w

(S2) Next, for n11, n12, n21, and n22, using the Akaike's Information Criterion (AIC), the value MLL_IM (w, C) for the independent model and the value MLL_DM (w for the dependent model) , C). This calculates an unreasonable ratio for each pair of a word and a topic group.
MLL_IM (w, C) = (n11 + n12) log (n11 + n12) + (n11 + n21) log (n11 + n21)
+ (N21 + n22) log (n21 + n22) + (n12 + n22) log (n12 + n22) -2 N log N
MLL_DM (w, C) = n11 log n11 + n12 log n12 + n21 log n21 + n22 log n22-N log N
However, N = n11 + n12 + n21 + n22

(S3) The following E (w, C) is calculated from the aforementioned MLL_IM (w, C) and MLL_DM (w, C).
AIC_IM (w, C) = -2 × MLL_IM (w, C) + 2 × 2
AIC_DM (w, C) = -2 × MLL_DM (w, C) + 2 × 3
E (w, C) = AIC_IM (w, C) − AIC_DM (w, C)

  E (w, C) calculated as described above represents an unreasonable ratio in which the word w appears biased to the topic group C. As for E (w, C), the value of E (w, C) becomes higher as the word is more useful for determining the topic group C according to the Akaike information criterion. According to the present invention, for each topic group Ci, m words Ci, 1, Ci, 2, Ci, 3,... Ci, m are extracted in descending order of E (w, C). The representative keyword of the topic group Ci.

[Difference Keyword Extraction Unit 127]
The difference keyword extraction unit 127 extracts, for each topic group, a representative keyword that appears only in the topic group as a difference keyword. According to FIG. 6, the following difference keywords are extracted.
Topic Group 1: “Reliable” “Application” (× terminal)
Topic Group 2: “Discovery” (× terminal)

[Difference keyword selection unit 128]
The difference keyword selection unit 128 clearly indicates a plurality of difference keywords to the user via the user interface, and causes any one difference keyword to be selected according to a user operation. When viewed from the user, for example, after inputting a question sentence with a keyboard, the difference keyword for each topic group is displayed on the display. Then, the user can select any difference keyword. According to FIG. 6, the user has selected “discovery”. The difference keyword “discovery” selected by the user is output to the answer sentence output unit 129.

[Answer sentence output unit 129]
The answer sentence output unit 129 specifies the answer sentence detected by the answer sentence detection unit together with one or more corresponding difference keywords. According to the present invention, the user's question is ambiguous, the comment sentence group is classified into a plurality of topic groups, and an answer sentence associated with each topic group can be obtained. Here, when the number of obtained answer sentences is small, the difference keyword is useful information for the user to recognize the tendency of the presented answer sentence.

  When there are a large number of answer sentences, it is preferable to narrow down the answer sentences by interacting with the user. Therefore, the answer sentence output unit 129 specifies the answer sentence corresponding to the selected difference keyword via the user interface. For example, the answer sentence is displayed on a display visually recognized by the user. According to FIG. 6, an answer sentence “How to find a mobile phone and use a reliable service” is displayed to the user. Thereby, the user can recognize the answer sentence to the question sentence.

  FIG. 7 is a sequence diagram in the present invention.

(S71) The question text of the user is transmitted from the terminal 4 operated by the questioner to the question answering server 1 (see the question text input unit 121 in FIG. 2).
(S72) The question answering server 1 extracts a plurality of question keywords included in the question sentence (see the question keyword extracting unit 122 in FIG. 2).
(S73) The question answering server 1 uses the comment text storage unit 102 to search for a comment text including the question keyword (see the comment text search unit 123 in FIG. 2).
(S74) The question answering server 1 classifies the searched comment sentences into a plurality of topic groups based on the distribution of appearance words (see the topic classification unit 124 in FIG. 2).
(S75) The question answering server 1 calculates the similarity between the comment sentence group included in each topic group and each answer sentence, and associates an answer sentence whose similarity is equal to or greater than a predetermined threshold with each topic group ( (See the answer sentence detection unit 125 in FIG. 2).
(S76) For each topic group, the question / answer server 1 extracts a representative keyword that characterizes the topic group from keywords included in the associated answer sentence (see the representative keyword extraction unit 126 in FIG. 2).
(S77) The question answering server 1 extracts, for each topic group, a representative keyword that appears only in the topic group as a difference keyword (see the difference keyword extraction unit 127 in FIG. 2).
(S78) The question answering server 1 transmits a plurality of difference keywords to the user-operated terminal 4 (see the difference keyword selection unit 128 in FIG. 2). And in the terminal 4, any one difference keyword is selected according to user operation. The selected difference keyword is transmitted from the terminal 4 to the question answering server 1.
(S79) The question / answer server 1 transmits an answer sentence corresponding to the selected difference keyword to the user's terminal 4 (see the answer sentence output unit 129 in FIG. 2).

  As described above, according to the question answering server of the present invention, a representative keyword representing the intention of the question sentence is extracted from a large amount of comment sentences such as twitter, and the answer sentence is complemented by supplementing the question sentence. It is possible to search with high accuracy. Specifically, first, the keywords included in the question sentence are extracted to search social media, and a large amount of search results are quickly classified into a plurality of topic groups (corresponding to one search intention for each topic) An answer sentence similar to each topic is searched from the answer sentence storage unit. Next, a word (difference keyword) peculiar to each topic group is automatically extracted and presented to the user, and it is narrowed down to the answer sentence according to the user's selection result, and the interactive form with the user can be repeatedly executed. it can.

  As described above in detail, according to the question answering program, server and method of the present invention, when there are a plurality of answer sentence candidates for the user's question sentence, an answer sentence reflecting the user's intention is displayed. You can specify (narrow down).

  Various changes, modifications, and omissions of the above-described various embodiments of the present invention can be easily made by those skilled in the art. The above description is merely an example, and is not intended to be restrictive. The invention is limited only as defined in the following claims and the equivalents thereto.

DESCRIPTION OF SYMBOLS 1 Question answer server 10 Communication interface part 101 Answer sentence storage part 102 Comment sentence storage part 111 Answer sentence acquisition part 112 Comment sentence collection part 121 Question sentence input part 122 Question keyword extraction part 123 Comment sentence search part 124 Topic classification part 125 Answer sentence Detection unit 126 Representative keyword extraction unit 127 Difference keyword extraction unit 128 Difference keyword selection unit 129 Answer sentence output part 2 Answer sentence storage server 3 Blog server 4 Terminal 5 General-purpose terminal for comment author

Claims (11)

A question answering program that has a comment sentence accumulating part that accumulates a large number of comment sentences and an answer sentence accumulating part that accumulates a large number of answer sentences, and that allows a computer to function to extract answer sentences for a question sentence from a user. There,
A question sentence input means for inputting a question sentence;
Question keyword extraction means for extracting a plurality of question keywords included in the question sentence;
Using the comment sentence storage unit, comment sentence search means for searching for comment sentences including the question keyword;
A topic classification means for classifying a plurality of searched comment sentences into a plurality of topic groups from the distribution of appearance words;
An answer sentence detection means for calculating a similarity between a comment sentence group included in each topic group and a sentence included in each answer sentence, and associating an answer sentence having the similarity equal to or greater than a predetermined threshold with each topic group; ,
For each topic group, representative keyword extraction means for extracting a representative keyword characterizing the topic group from the keywords included in the associated answer sentence;
For each topic group, a differential keyword extraction unit that extracts a representative keyword that appears only in the topic group as a differential keyword;
A question answering program which causes a computer to function as an answer sentence output means for clearly indicating the answer sentence detected by the answer sentence detection means together with the corresponding one or more difference keywords. The difference keyword selecting means is further provided to clearly indicate the plurality of difference keywords to the user via a user interface and to select any one difference keyword according to a user operation.
The question answering program according to claim 1, wherein the answer sentence output unit causes the computer to function so as to clearly indicate an answer sentence corresponding to the selected difference keyword via a user interface.   The topic classification means classifies the comment text into any one topic group using an LDA (Latent Dirichlet Allocation) algorithm that calculates a probability (topic ratio) belonging to each classified topic group. The question answering program according to claim 1 or 2, wherein the computer functions. The question keyword extraction means extracts a keyword from the question sentence by morphological analysis, and at the same time, extracts a characteristic word from the question keyword by TF-IDF (Term Frequency-Inverse Document Frequency). Extract as
And / or
2. The representative keyword extracting means causes a computer to function so as to extract a keyword from the answer sentence by morphological analysis and to extract a characteristic word as the representative keyword by TF-IDF. 4. The question answering program according to any one of items 1 to 3. The answer sentence detection means includes:
A keyword is extracted from a comment sentence group included in each topic group by morphological analysis, and a first feature vector in the topic group is calculated by TF-IDF.
A keyword is extracted from each answer sentence stored in the answer sentence storage unit by morphological analysis, and a second feature vector in the answer sentence is calculated by TF-IDF.
5. The computer according to claim 1, wherein the computer is caused to calculate a similarity based on a cosine distance between a first vector of the topic group and a second vector of the answer sentence. The question answering program according to item 1.   6. The question according to claim 1, wherein the representative keyword extraction unit causes the computer to function so that the representative keywords of each topic group are arranged in a priority order in accordance with the Akaike information amount criterion. Answer program. The comment text is posted by an unspecified number of third parties,
7. The comment text storage unit causes a computer to function so as to collect and store comment text posted on a mini blog (mini Web log) server. The question answering program described in. A question answering server that has a comment sentence accumulating unit that accumulates a large number of comment sentences, and an answer sentence accumulating part that accumulates a large number of answer sentences, and extracts a response sentence to a question sentence from a user,
A question sentence input means for inputting a question sentence from a terminal;
Question keyword extraction means for extracting a plurality of question keywords included in the question sentence;
Using the comment sentence storage unit, comment sentence search means for searching for comment sentences including the question keyword;
A topic classification means for classifying a plurality of searched comment sentences into a plurality of topic groups from the distribution of appearance words;
A comment sentence group included in each topic group and an answer sentence calculating means for calculating a similarity between each answer sentence and associating each topic group with an answer sentence having the similarity equal to or greater than a predetermined threshold;
For each topic group, representative keyword extraction means for extracting a representative keyword characterizing the topic group from the keywords included in the associated answer sentence;
For each topic group, a differential keyword extraction unit that extracts a representative keyword that appears only in the topic group as a differential keyword;
A question answering server comprising answer text output means for clearly indicating the answer text detected by the answer text detection means together with the corresponding one or more difference keywords. The difference keyword selecting means is further provided to clearly indicate the plurality of difference keywords to the user via a user interface and to select any one difference keyword according to a user operation.
9. The question answering server according to claim 8, wherein the answer sentence output means specifies an answer sentence corresponding to the selected difference keyword via a user interface. A question answering method in a device that has a comment sentence accumulating unit that accumulates a large number of comment sentences and an answer sentence accumulating part that accumulates a large number of answer sentences, and extracts an answer sentence for a question sentence from a user,
A first step of inputting a question sentence;
A second step of extracting a plurality of question keywords included in the question sentence;
A third step of searching for a comment sentence including the question keyword using the comment sentence storage unit;
A fourth step of classifying the plurality of searched comment sentences into a plurality of topic groups from the distribution of appearance words;
A fifth step of calculating a similarity between a comment sentence group included in each topic group and each answer sentence, and associating an answer sentence with the similarity equal to or greater than a predetermined threshold to each topic group;
For each topic group, a sixth step of extracting a representative keyword characterizing the topic group from the keywords included in the associated answer sentence;
For each topic group, a seventh step of extracting a representative keyword that appears only in the topic group as a difference keyword;
And an eighth step of clearly indicating the answer sentence detected by the fifth step together with the corresponding one or more difference keywords. For the eighth step,
A plurality of the difference keywords are clearly indicated to the user through a user interface, and one of the difference keywords is selected according to a user operation,
11. The question answering method according to claim 10, wherein an answer sentence corresponding to the selected difference keyword is specified via a user interface.

Images