Corpus ID: 13508168

Automatic Coupling of Answer Extraction and Information Retrieval

@inproceedings{Yao2013AutomaticCO,
  title={Automatic Coupling of Answer Extraction and Information Retrieval},
  author={Xuchen Yao and Benjamin Van Durme and P. Clark},
  booktitle={ACL},
  year={2013}
}
Information Retrieval (IR) and Answer Extraction are often designed as isolated or loosely connected components in Question Answering (QA), with repeated overengineering on IR, and not necessarily performance gain for QA. We propose to tightly integrate them by coupling automatically learned features for answer extraction to a shallow-structured IR model. Our method is very quick to implement, and significantly improves IR for QA (measured in Mean Average Precision and Mean Reciprocal Rank) by… Expand
Discriminative Information Retrieval for Knowledge Discovery
We propose a framework for discriminative Information Retrieval (IR) atop linguistic features, trained to improve the recall of tasks such as answer candidate passage retrieval, the initial step inExpand
Indirect Supervision for Relation Extraction using Question-Answer Pairs
TLDR
A novel framework to leverage question-answer pairs as an indirect source of supervision for relation extraction, and adopt a novel margin-based QA loss to reduce noise in DS by exploiting semantic evidence from the QA dataset is proposed. Expand
A Joint Model for Answer Sentence Ranking and Answer Extraction
TLDR
A simple and intuitive joint probabilistic model is proposed that addresses both answer sentence ranking and answer extraction via joint computation but task-specific application of that quantity. Expand
Answer Extraction in Question Answering using Structure Features and Dependency Principles
TLDR
Experimental results show that structural features improve the accuracy of answer extraction when combined with the basic features and designed using dependency principles, possible reason behind the improvement in overall answer extraction accuracy. Expand
Discriminative Information Retrieval for Question Answering Sentence Selection
TLDR
A framework for discriminative IR atop linguistic features, trained to improve the recall of answer candidate passage retrieval, is proposed, demonstrating a 34%-43% improvement in recall for candidate triage for QA. Expand
Evidence Gathering and Language Alignment in Question Answering...
TLDR
To increase the performance of QA systems it is required to align a natural language question with another question that is able to extract the final answer, and results prove that for NLQA new structural features are better, and the accuracy ofNLQA is increased when these are combined with TW and other features. Expand
Feature-driven Question Answering With Natural Language Alignment
TLDR
This dissertation proposes the idea of feature-driven QA, a machine learning framework that automatically produces rich features from linguistic annotations of answer fragments and encodes them in compact log-linear models. Expand
Dualized Topic-Preserving Pseudo Relevance Feedback for Question Answering
This study proposes an effective pseudo relevance feedback method for information retrieval in the context of question answering. The method separates two retrieval models to improve the precision ofExpand
An Effective Corpus-Based Question Answering Pipeline for Italian
TLDR
A Question Answering pipeline for Italian and based on a corpus of documents pertaining a closed domain that exhibits functionalities for analyzing natural language questions in Italian by using lexical features and scoring and selecting candidate answers with respect to their type in order to determine the best one. Expand
Explaining relationships between entities
Modern search engines are increasingly aiming to understand users’ intent in order to answer information needs more effectively by providing richer information than the traditional “ten blue links”.Expand
...
1
2
3
...

References

SHOWING 1-10 OF 28 REFERENCES
Improving Text Retrieval Precision and Answer Accuracy in Question Answering Systems
TLDR
Going forward, to improve accuracy on the QA task, systems will need greater coordination between text retrieval and answer extraction modules. Expand
Structured retrieval for question answering
TLDR
It is demonstrated that the structured approach to retrieval for QA can retrieve more relevant results, more highly ranked, compared with bag-of-words, on a sentence retrieval task. Expand
Answer Sentence Retrieval by Matching Dependency Paths acquired from Question/Answer Sentence Pairs
TLDR
A novel algorithm is proposed that analyzes dependency structures of queries and known relevant text passages and acquires transformational patterns that can be used to retrieve relevant textual content. Expand
Answer Extraction as Sequence Tagging with Tree Edit Distance
TLDR
A linear-chain Conditional Random Field based on pairs of questions and their possible answer sentences, learning the association between questions and answer types is constructed, casting answer extraction as an answer sequence tagging problem for the first time. Expand
Question answering passage retrieval using dependency relations
TLDR
This work presents two methods for learning relation mapping scores from past QA pairs: one based on mutual information and the other on expectation maximization, which significantly outperforms state-of-the-art density-based passage retrieval methods. Expand
Rank learning for factoid question answering with linguistic and semantic constraints
TLDR
This work presents a general rank-learning framework for passage ranking within Question Answering (QA) systems using linguistic and semantic features, and shows that constraints based on semantic role labeling features are particularly effective for passage retrieval. Expand
Building a reusable test collection for question answering
TLDR
It is argued that document retrieval for question answering represents a different task than retrieving documents in response to more general retrospective information needs, and to guide future system development, specialized question answering test collections must be constructed. Expand
Using Semantic Roles to Improve Question Answering
TLDR
This work introduces a general framework for answer extraction which exploits semantic role annotations in the FrameNet paradigm and views semantic role assignment as an optimization problem in a bipartite graph and answer extraction as an instance of graph matching. Expand
Question-answering by predictive annotation
TLDR
Predictive Annotation identifies potential answers to questions in text, annotates them accordingly and indexes them, and produces a system effective at answering natural-language fact-seeking questions posed against large document collections. Expand
Answer typing for information retrieval
TLDR
Experimental results show that type-appropriate terms identified by the model are superior to terms most commonly associated with the query, providing strong evidence that answer typing techniques can find meaningful and appropriate terms. Expand
...
1
2
3
...