Spinning Straw into Gold: Using Free Text to Train Monolingual Alignment Models for Non-factoid Question Answering

@inproceedings{Sharp2015SpinningSI,
  title={Spinning Straw into Gold: Using Free Text to Train Monolingual Alignment Models for Non-factoid Question Answering},
  author={Rebecca Sharp and Peter Alexander Jansen and Mihai Surdeanu and Peter Clark},
  booktitle={NAACL},
  year={2015}
}
Monolingual alignment models have been shown to boost the performance of question answering systems by ”bridging the lexical chasm” between questions and answers. The main limitation of these approaches is that they require semistructured training data in the form of question-answer pairs, which is difficult to obtain in specialized domains or lowresource languages. We propose two inexpensive methods for training alignment models solely using free text, by generating artificial question-answer… Expand
Tell Me Why: Using Question Answering as Distant Supervision for Answer Justification
TLDR
A neural network architecture for QA that reranks answer justifications as an intermediate (and human-interpretable) step in answer selection and shows that with this end-to-end approach it is able to significantly improve upon a strong IR baseline in both justification ranking and answer selection. Expand
How consistent are our discourse annotations? Insights from mapping RST-DT and PDTB annotations
TLDR
This article proposes a method for aligning the discourse segments, and evaluates the observed against the expected mappings for explicit and implicit relations separately, finding that while agreement on explicit relations is reasonable, agreement between the frameworks on implicit relations is astonishingly low. Expand
Framing QA as Building and Ranking Intersentence Answer Justifications
TLDR
A question answering approach for standardized science exams that both identifies correct answers and produces compelling human-readable justifications for why those answers are correct is proposed, and it is shown that information aggregation is key to addressing the information need in complex questions. Expand
How compatible are our discourse annotation frameworks? Insights from mapping RST-DT and PDTB annotations
TLDR
This analysis highlights the influence of segmentation on subsequent discourse relation labelling, and shows that while agreement between frameworks is reasonable for explicit relations, agreement on implicit relations is low. Expand
How compatible are our discourse annotations? Insights from mapping RST-DT and PDTB annotations
TLDR
A method for automatically aligning the discourse segments is proposed, and existing mapping proposals are evaluated by comparing the empirically observed against the proposed mappings. Expand
Paraphrase-focused learning to rank for domain-specific frequently asked questions retrieval
TLDR
It is shown that supervised ranking models can yield significant improvements in the precision-at-rank-5 measure compared to unsupervised baselines, and that a supervised model trained using data labeled via a low-effort paraphrase-focused strategy has the same performance as that of the same modeltrained using fully labeled data. Expand
ADAPT.DCU at TREC LiveQA: A Sentence Retrieval based Approach to Live Question Answering
TLDR
The work done by ADAPT centre at Dublin City University towards automatically answering questions for the TREC LiveQA track is described, based on a sentence retrieval approach that first uses the title of a new question as a query to retrieve a ranked list of conceptually similar questions from an index of previously asked on Yahoo! Answers. Expand
This is how we do it: Answer Reranking for Open-domain How Questions with Paragraph Vectors and Minimal Feature Engineering
We present a simple yet powerful approach to non-factoid answer reranking whereby question-answer pairs are represented by concatenated distributed representation vectors and a multilayer perceptronExpand
Distant Supervision for Relation Extraction beyond the Sentence Boundary
TLDR
This paper proposes the first approach for applying distant supervision to cross-sentence relation extraction with a graph representation that can incorporate both standard dependencies and discourse relations, thus providing a unifying way to model relations within and across sentences. Expand
If You Can’t Beat Them Join Them: Handcrafted Features Complement Neural Nets for Non-Factoid Answer Reranking
TLDR
It is shown that a neural approach to the task of non-factoid answer reranking can benefit from the inclusion of tried-and-tested handcrafted features and can be combined with additional features, in particular, the discourse features used by previous research. Expand
...
1
2
...

References

SHOWING 1-10 OF 27 REFERENCES
Higher-order Lexical Semantic Models for Non-factoid Answer Reranking
TLDR
This work introduces a higher-order formalism that allows all these lexical semantic models to chain direct evidence to construct indirect associations between question and answer texts, by casting the task as the traversal of graphs that encode direct term associations. Expand
Automatic question answering using the web: Beyond the Factoid
TLDR
A Question Answering (QA) system that goes beyond answering factoid questions is described and evaluated, by comparing the performance of baseline algorithms against the proposed algorithms for various modules in the QA system. Expand
Discourse Complements Lexical Semantics for Non-factoid Answer Reranking
We propose a robust answer reranking model for non-factoid questions that integrates lexical semantics with discourse information, driven by two representations of discourse: a shallow representationExpand
Question Answering Using Enhanced Lexical Semantic Models
TLDR
This work focuses on improving the performance using models of lexical semantic resources and shows that these systems can be consistently and significantly improved with rich lexical semantics information, regardless of the choice of learning algorithms. Expand
Learning to Rank Answers to Non-Factoid Questions from Web Collections
TLDR
This work shows that it is possible to exploit existing large collections of question–answer pairs to extract such features and train ranking models which combine them effectively, providing one of the most compelling evidence to date that complex linguistic features such as word senses and semantic roles can have a significant impact on large-scale information retrieval tasks. Expand
HILDA: A Discourse Parser Using Support Vector Machine Classification
TLDR
This article presents HILDA, an implemented discourse parser based on RST and Support Vector Machine (SVM) classification that outperforms other discourse parsers for tree structure construction and discourse relation labeling. Expand
Back to Basics for Monolingual Alignment: Exploiting Word Similarity and Contextual Evidence
We present a simple, easy-to-replicate monolingual aligner that demonstrates state-of-the-art performance while relying on almost no supervision and a very small number of external resources. BasedExpand
Bridging the lexical chasm: statistical approaches to answer-finding
TLDR
It is shown that the task of “answer-finding” differs from both document retrieval and tradition question-answering, presenting challenges different from those found in these problems. Expand
Statistical Machine Translation for Query Expansion in Answer Retrieval
We present an approach to query expansion in answer retrieval that uses Statistical Machine Translation (SMT) techniques to bridge the lexical gap between questions and answers. SMT-based queryExpand
A Noisy-Channel Approach to Question Answering
TLDR
This work introduces a probabilistic noisy-channel model for question answering and shows how it can be exploited in the context of an end-to-end QA system, and shows that the model is flexible enough to accommodate within one mathematical framework many QA-specific resources and techniques. Expand
...
1
2
3
...