Reading Report on Question Answering

Slides:



Advertisements
Similar presentations
Learning to Suggest: A Machine Learning Framework for Ranking Query Suggestions Date: 2013/02/18 Author: Umut Ozertem, Olivier Chapelle, Pinar Donmez,
Advertisements

1 Evaluation Rong Jin. 2 Evaluation  Evaluation is key to building effective and efficient search engines usually carried out in controlled experiments.
Knowledge Base Completion via Search-Based Question Answering
QA-LaSIE Components The question document and each candidate answer document pass through all nine components of the QA-LaSIE system in the order shown.
WWW 2014 Seoul, April 8 th SNOW 2014 Data Challenge Two-level message clustering for topic detection in Twitter Georgios Petkos, Symeon Papadopoulos, Yiannis.
WSCD INTRODUCTION  Query suggestion has often been described as the process of making a user query resemble more closely the documents it is expected.
Leveraging Community-built Knowledge For Type Coercion In Question Answering Aditya Kalyanpur, J William Murdock, James Fan and Chris Welty Mehdi AllahyariSpring.
Query Dependent Pseudo-Relevance Feedback based on Wikipedia SIGIR ‘09 Advisor: Dr. Koh Jia-Ling Speaker: Lin, Yi-Jhen Date: 2010/01/24 1.
Gimme’ The Context: Context- driven Automatic Semantic Annotation with CPANKOW Philipp Cimiano et al.
Scalable Text Mining with Sparse Generative Models
Enhance legal retrieval applications with an automatically induced knowledge base Ka Kan Lo.
Finding Advertising Keywords on Web Pages Scott Wen-tau YihJoshua Goodman Microsoft Research Vitor R. Carvalho Carnegie Mellon University.
CSC 9010 Spring Paula Matuszek A Brief Overview of Watson.
Probabilistic Model for Definitional Question Answering Kyoung-Soo Han, Young-In Song, and Hae-Chang Rim Korea University SIGIR 2006.
SEEKING STATEMENT-SUPPORTING TOP-K WITNESSES Date: 2012/03/12 Source: Steffen Metzger (CIKM’11) Speaker: Er-gang Liu Advisor: Dr. Jia-ling Koh 1.
1 Context-Aware Search Personalization with Concept Preference CIKM’11 Advisor : Jia Ling, Koh Speaker : SHENG HONG, CHUNG.
AnswerBus Question Answering System Zhiping Zheng School of Information, University of Michigan HLT 2002.
UOS 1 Ontology Based Personalized Search Zhang Tao The University of Seoul.
Assigning Global Relevance Scores to DBpedia Facts Philipp Langer, Patrick Schulze, Stefan George, Tobias Metzke, Ziawasch Abedjan, Gjergji Kasneci DESWeb.
11 A Hybrid Phish Detection Approach by Identity Discovery and Keywords Retrieval Reporter: 林佳宜 /10/17.
Presenter: Lung-Hao Lee ( 李龍豪 ) January 7, 309.
Detecting Dominant Locations from Search Queries Lee Wang, Chuang Wang, Xing Xie, Josh Forman, Yansheng Lu, Wei-Ying Ma, Ying Li SIGIR 2005.
1 Learning Sub-structures of Document Semantic Graphs for Document Summarization 1 Jure Leskovec, 1 Marko Grobelnik, 2 Natasa Milic-Frayling 1 Jozef Stefan.
Binxing Jiao et. al (SIGIR ’10) Presenter : Lin, Yi-Jhen Advisor: Dr. Koh. Jia-ling Date: 2011/4/25 VISUAL SUMMARIZATION OF WEB PAGES.
Contextual Ranking of Keywords Using Click Data Utku Irmak, Vadim von Brzeski, Reiner Kraft Yahoo! Inc ICDE 09’ Datamining session Summarized.
Question Answering over Implicitly Structured Web Content
Keyword Query Routing.
Indirect Supervision Protocols for Learning in Natural Language Processing II. Learning by Inventing Binary Labels This work is supported by DARPA funding.
Google’s Deep-Web Crawl By Jayant Madhavan, David Ko, Lucja Kot, Vignesh Ganapathy, Alex Rasmussen, and Alon Halevy August 30, 2008 Speaker : Sahana Chiwane.
Facilitating Document Annotation using Content and Querying Value.
Algorithmic Detection of Semantic Similarity WWW 2005.
Authors: Marius Pasca and Benjamin Van Durme Presented by Bonan Min Weakly-Supervised Acquisition of Open- Domain Classes and Class Attributes from Web.
Using linked data to interpret tables Varish Mulwad September 14,
August 17, 2005Question Answering Passage Retrieval Using Dependency Parsing 1/28 Question Answering Passage Retrieval Using Dependency Parsing Hang Cui.
Comparing Document Segmentation for Passage Retrieval in Question Answering Jorg Tiedemann University of Groningen presented by: Moy’awiah Al-Shannaq
Mining Dependency Relations for Query Expansion in Passage Retrieval Renxu Sun, Chai-Huat Ong, Tat-Seng Chua National University of Singapore SIGIR2006.
1 Evaluating High Accuracy Retrieval Techniques Chirag Shah,W. Bruce Croft Center for Intelligent Information Retrieval Department of Computer Science.
Answer Mining by Combining Extraction Techniques with Abductive Reasoning Sanda Harabagiu, Dan Moldovan, Christine Clark, Mitchell Bowden, Jown Williams.
LINDEN : Linking Named Entities with Knowledge Base via Semantic Knowledge Date : 2013/03/25 Resource : WWW 2012 Advisor : Dr. Jia-Ling Koh Speaker : Wei.
SEMANTIC VERIFICATION IN AN ONLINE FACT SEEKING ENVIRONMENT DMITRI ROUSSINOV, OZGUR TURETKEN Speaker: Li, HueiJyun Advisor: Koh, JiaLing Date: 2008/5/1.
Identifying “Best Bet” Web Search Results by Mining Past User Behavior Author: Eugene Agichtein, Zijian Zheng (Microsoft Research) Source: KDD2006 Reporter:
Date: 2013/9/25 Author: Mikhail Ageev, Dmitry Lagun, Eugene Agichtein Source: SIGIR’13 Advisor: Jia-ling Koh Speaker: Chen-Yu Huang Improving Search Result.
Usefulness of Quality Click- through Data for Training Craig Macdonald, ladh Ounis Department of Computing Science University of Glasgow, Scotland, UK.
GoRelations: an Intuitive Query System for DBPedia Lushan Han and Tim Finin 15 November 2011
Question Answering Passage Retrieval Using Dependency Relations (SIGIR 2005) (National University of Singapore) Hang Cui, Renxu Sun, Keya Li, Min-Yen Kan,
Knowledge and Information Retrieval Dr Nicholas Gibbins 32/4037.
Learning Relational Dependency Networks for Relation Extraction
Automatically Labeled Data Generation for Large Scale Event Extraction
Evaluation Anisio Lacerda.
A Brief Introduction to Distant Supervision
Object-Oriented Software Engineering Using UML, Patterns, and Java,
An Empirical Study of Learning to Rank for Entity Search
Reading Report on Hybrid Question Answering System
Reading Report Semantic Parsing: Sempre (自始至终)
Google China Faculty Summit
Generating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning Shizhu He, Cao liu, Kang Liu and Jun Zhao.
Web IR: Recent Trends; Future of Web Search
Extracting Semantic Concept Relations
Intent-Aware Semantic Query Annotation
Learning to Parse Database Queries Using Inductive Logic Programming
Table Cell Search for Question Answering Huan Sun
Introduction Task: extracting relational facts from text
CS246: Information Retrieval
Enriching Taxonomies With Functional Domain Knowledge
Facilitating Navigation on Linked Data through Top-K Link Patterns
Reading Report Semantic Parsing (续)
Template-based Question Answering over RDF Data
Topic: Semantic Text Mining
Presenter: Yu Chen Computer Science Department
CoXML: A Cooperative XML Query Answering System
Presentation transcript:

Reading Report on Question Answering 论文阅读 瞿裕忠 南京大学计算机系

Articles Open Domain Question Answering via Semantic Enrichment WWW2015, Microsoft, UIUC HAWK – Hybrid Question Answering using Linked Data ESWC2015, University of Leipzig

Agenda Introduction Methodology Feature development (Ranking) Answer type prediction (Probabilistic models) Experiments Conclusion

Introduction Web Search  open domain QA KB-based QA (structured knowledge bases) Corpus-based QA (unstructured corpus)

Introduction Difficulty for KB-based QA systems Incompleteness of KB: Information required to answer a question may not always exist in KBs. Semantic parsing: Although semantic parsing [2, 3] has been a hot research topic recently, the problem of mapping natural language utterances to logical-form queries is still considered largely unsolved. Weakness of Web-based QA systems Insufficient knowledge about the generated answer candidates. Different mentions of the same entity such as “President Obama” and “Barack Obama” are viewed as different answer candidates. Answer type checking relies on a generic named entity recognition component that provides a small set of crude type labels.

Introduction A new QA system framework, named QuASE Question Answering via Semantic Enrichment

Who was the first American in space? Example Who was the first American in space? Submit it to a search engine Get a set of relevant sentences On May 5, 1961, Shepard piloted the Freedom 7 mission... ; Alan Shepard became the first American in space when the Freedom 7...; Linking entity to Freebase Freedom 7, Alan Shepard, Sally Ride, … Such linked entities are treated as answer candidates to the given question. Semantic features are integrated into a ranking algorithm. Alan Shepard

Example Who was the first American in space?

Methodology Web Sentence Selection via Search Engine Answer Candidate Generation via Entity Linking Feature Generation and Ranking.

Methodology (1) Web Sentence Selection via Search Engine Submit the question as a query to a search engine Collect the top-50 returned snippets, as well as the top-50 documents. Compute the word count vector based on the returned snippets to represent the information for the query, denoted as wq. For each sentence from the top-50 returned documents, we compute its word count vector ws, and select those sentences with a high cos(ws, wq) into the high-quality sentence set.

Methodology (2) Answer Candidate Generation via Entity Linking Primarily focus on those questions targeted at certain entities in KBs. ( e.g. excluding “when” question) Use one of the entity linking systems [13] to identify answer candidates linked to Freebase. This system achieves the best scores at TAC-KBP 2013, by several novel designs such as postponing surface form boundary detections and discriminating concepts and entities in Wikipedia pages.

Methodology (3) Feature Generation and Ranking For each answer candidate, Freebase contains a wealth of information, such as their description texts and entity types. A set of semantic features shall be developed based on such rich information, and subsequently utilized in a ranking algorithm to evaluate the appropriateness of each candidate as the true answer.

Features Count: high frequency of answer candidate serves as a significant indicator of being the correct answer Textual Relevance Answer Type Related Features Propose probabilistic models to directly measure the matching degree between a question and an answer candidate’s Freebase types.

Word to Answer Type (WAT) Model

JQA model Joint <question, answer type> association (JQA) model

TREC dataset: factoid questions from TREC 8-12 Experimental Setup TREC dataset: factoid questions from TREC 8-12 Among the remaining 1902 questions (entity-oriented) Bing query: crowdsourcing, entity answers in Freebase. Approximately 6000 question-answer pairs

Training Dataset for JQA and WAT Experimental Setup Training Dataset for JQA and WAT Around 1.3 million <question, answer types> pairs based on Bing query logs. <query, clicked url> pairs from the query click logs each entity in Freebase is also linked to some urls that are related to this entity (mostly Wikipedia pages or official web sites of this entity). Freebase types of the entity corresponding to the clicked url as the answer types.

Answer Candidate Ranking Experimental Setup Answer Candidate Ranking Use an in-house fast implementation of the MART gradient boosting decision tree algorithm [9, 21] to learn the ranker using the training set of our data.

Experimental Setup Evaluation Measures F1 score, which is the harmonic mean of precision and recall. Mean Reciprocal Rank (MRR).

Alternative QA systems Experimental Setup Alternative QA systems KB-based QA system: Sempre[2, 3] Web-based QA system: AskMSR+ [39]

Experimental Results

Experimental Results

Analysis of QuASE and AskMSR+ on their respective failed questions Experimental Results Analysis of QuASE and AskMSR+ on their respective failed questions Compared with AskMSR+, features in QuASE for ranking are effective as long as true answers are in the candidate list.

Experimental Results For QuASE, how to improve entity linking performance, in order to include true answers in the candidate list, can be important to further improve QA performance.

Conclusion Contributions Future work A new QA Framework, QuASE Answer Type Checking Models Extensive Experimental Evaluation Future work Relationships among entities can also be explored as semantic features to be incorporated in our system To improve entity linking performance

HAWK--Hybrid QA using Linked Data Introduction Methodology Evaluation Conclusion http://aksw.org/Projects/HAWK.html

Introduction Hybrid question answering Find and combine information stored in both structured and textual data sources Document Web Labels and abstracts in Linked Data sources Question Answering over Linked Data (QALD-4) Task 3: Hybrid question answering http://greententacle.techfak.uni-bielefeld.de/~cunger/qald/

Example Which recipients of the Victoria Cross died in the Battle of Arnhem? Cannot be answered by solely DBpedia or Wikipedia abstracts ?uri dbo:award dbr:Victoria_Cross The abstract for John Hollington Grayburn ‘he went into action in the Battle of Arnhem [...] but was killed after standing up in full view of a German tank’.

Architectural overview of HAWK Introduction Architectural overview of HAWK

Methodology POS-Tagging Entity Annotation Dependency Parsing Linguistic Pruning Semantic Annotation Generating SPARQL Queries Semantic Pruning of SPARQL Queries Ranking

Predicate-argument tree By Example Which recipients of the Victoria Cross died in the Battle of Arnhem? Predicate-argument tree Tree after pruning

Methodology Semantic Annotation nouns correspond to object type properties and classes verbs correspond to object type properties question words (e.g., who or where) correspond to classes (e.g., Person or Place)

Methodology Generating SPARQL Queries Traverses the tree in a pre-order walk Related information are situated close to each other in tree Information are more restrictive from left to right Triple pattern for generating queries while traversal E.g. a variable bound to the class Place will not have an outgoing predicate birthPlace. Semantic Pruning of SPARQL Queries

Methodology Ranking HAWK ranks queries using supervised training based on the gold standard answer set from the QALD-4 benchmark. Feature selection?

Evaluation To evaluate HAWK focus on this hybrid training dataset comprising 25 questions, 17 out of which are entity searches Using only DBpedia type information No aggregation process.

Experimental Results Red: inability to generate correct query, Green: missing recall. Blue: missing precision

Experimental Results

Failing entity annotation Error Analysis Failing entity annotation Queries 1, 11 and 15. Jane Austin, G8, Los Alamos. Without matching entity annotations a full-text search retrieves too many matches for reaching high precision values on limited result set. Query structure Queries 11 or 15 complex query structures lead to a multitude of interpretations Missing type information Some of the resources of the gold standard do not have appropriate type information leading to a high amount of queries that need to be ranked correctly.

Error Analysis Query example 1. Give me the currencies of all G8 countries. 11.Who composed the music for the film that depicts the early life of Jane Austin? 15. Of the people that died of radiation in Los Alamos, whose death was an accident?

Conclusion Contributions Future work HAWK, the first hybrid QA system for the Web of Data A generic approach to generate SPARQL queries out of predicate argument structures Achieve up to 0.68 F-measure on the QALD-4 benchmark. Future work Finding the correct ranking approach to map a predicate-argument tree to a possible interpretation Computational complexity Domain-specific applications (higher F-measures)

致谢 欢迎提问!