Combining Logic and Machine Learning for Answering Questions

Glöckner, Ingo; Pelzer, Björn

doi:10.1007/978-3-642-04447-2_47

Cited by 5 publications

(12 citation statements)

References 6 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since many aspects of LogAnswer are already described elsewhere [1,4,5], we focus on novel developments added for ResPubliQA. We then detail the results of LogAnswer and show the effectiveness of the measures taken to prepare LogAnswer for ResPubliQA.…”

Section: Introductionmentioning

confidence: 99%

“…But JRC Acquis is hard to parse, so we have now included sentences with a failed or incomplete parse as well. Since LogAnswer also indexes the possible answer types found in the sentences [1], the existing solution for extracting answer types had to be extended to recognize expressions of these types in arbitrary sentences.…”

Section: Improvements Of Document Analysis and Indexingmentioning

confidence: 99%

“…3 It was first evaluated in QA@CLEF 2008 [1]. The ResPubliQA task [2] posed some new challenges for LogAnswer:…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Extending a Logic-Based Question Answering System for Administrative Texts

Glöckner

Pelzer

2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. LogAnswer is a question answering (QA) system for German that uses machine learning for integrating logic-based and shallow (lexical) validation features. For ResPubliQA 2009, LogAnswer was adjusted to specifics of administrative texts, as found in the JRC Acquis corpus. Moreover, support for a broader class of questions relevant to the domain was added, including questions that ask for a purpose, reason, or procedure. Results confirm the success of these measures to prepare LogAnswer for ResPubliQA, and of the general consolidation of the system. According to the C@1/Best IR baseline metric that tries to abstract from the language factor, LogAnswer was the third best of eleven systems participating in ResPubliQA. The system was especially successful at detecting wrong answers, with 73% correct rejections.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Improvements Of Document Analysis and Indexingmentioning

confidence: 99%

See 1 more Smart Citation

Extending a Logic-Based Question Answering System for Administrative Texts

Glöckner

Pelzer

2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…The question classification identifies the descriptive core of the question, the expected answer type and question category. Sanity tests eliminate trivial answers and non-informative answers to definition questions [3]. Failure of temporal restrictions and incompatibility of measurement units is also detected.…”

Section: The Rave Validatormentioning

confidence: 99%

“…2 RAVE then extracts the number of proven literals and other features from the prover results; about half of all features are logic-based [3,5].…”

Section: The Rave Validatormentioning

confidence: 99%

RAVE: A Fast Logic-Based Answer Validator

Glöckner

2009

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. RAVE (Real-time Answer Validation Engine) is a logic-based answer validator/selector designed for real-time question answering. Instead of proving a hypothesis for each answer, RAVE uses logic only for checking if a considered passage supports a correct answer at all. In this way parsing of the answers is avoided, yielding low validation/selection times. Machine learning is used for assigning local validation scores based on logical and shallow features. The subsequent aggregation of these local scores strives to be robust to duplicated information in the support passages. To achieve this, the effect of aggregation is controlled by the lexical diversity of the support passages for a given answer. Description of the Validation TaskThe Answer Validation Exercise (AVE) [1] introduces a test set of validation items i ∈ I comprising the question q i , answer candidate a i and supporting snippet s i . Let Q = {q i : i ∈ I} be the set of all questions and I q = {i ∈ I : q i = q} the set of validation items for a question q ∈ Q. The validator must assign a validation decision v i ∈ {REJECTED, SELECTED, VALIDATED} and confidence score c i ∈ [0, 1] to each i ∈ I. At most one answer per question can be selected. Answers can only be validated if an answer was selected as best answer. The RAVE ValidatorThe input to the validator comprises a question together with answer candidates for the question and the supporting text snippets, as represented by I q . Let A q = {a i : q i = q} denote the set of answer candidates for q in the test set. The AVE 2008 test set is redundancy-free, i.e. for each a ∈ A q , there is only one item i ∈ I q supporting a. As the basis for aggregation, the IRSAW system [2] was used to actively search for additional supporting snippets for each of the answer candidates. Answers were clustered into groups of minor variants with the same 'answer key' κ(a i ) by applying a simplification function κ (which drops accents etc.) For example, κ(in the year 2001) = 2001. The result is a set of auxiliary items i ∈ I q with q i = q and κ(a i ) = κ(a j ) for some original answer a j ∈ A q , and supporting snippet s i for a i found by IRSAW. The original and auxiliary validation items are joined into the enhanced validation pool I * q = I q ∪ I q .

show abstract

Logic-Based Question Answering

et al. 2010

Self Cite

View full text Add to dashboard Cite

Question answering systems aim to provide concise and correct responses to arbitrary questions, communicating with the user in a natural language. This way they help making the knowledge of large textual sources accessible in an intuitive manner which goes beyond the capabilities of conventional search engines. In the LogAnswer project the universities of Hagen and Koblenz cooperate to build a German language question answering system which combines computational linguistics and automated reasoning to deduce answers from a knowledge base derived from Wikipedia.

show abstract

Combining Logic and Machine Learning for Answering Questions

Cited by 5 publications

References 6 publications

Extending a Logic-Based Question Answering System for Administrative Texts

Extending a Logic-Based Question Answering System for Administrative Texts

RAVE: A Fast Logic-Based Answer Validator

Logic-Based Question Answering

Contact Info

Product

Resources

About