Discourse Complements Lexical Semantics for Non-factoid Answer Reranking

@inproceedings{Jansen2014DiscourseCL,
  title={Discourse Complements Lexical Semantics for Non-factoid Answer Reranking},
  author={Peter Jansen and M. Surdeanu and Peter Clark},
  booktitle={ACL},
  year={2014}
}
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 representation centered around discourse markers, and a deep one based on Rhetorical Structure Theory. We evaluate the proposed model on two corpora from different genres and domains: one from Yahoo! Answers and one from the biology domain, and two types of non-factoid questions: manner and reason. We… Expand
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
Discourse-Based Approach to Involvement of Background Knowledge for Question Answering
TLDR
A concept of a virtual discourse tree to improve question answering (Q/A) recall for complex, multi-sentence questions and observes a substantial increase of performance answering complex questions such as Yahoo! Answers and www.2carpros.com. Expand
One Vector is Not Enough: Entity-Augmented Distributed Semantics for Discourse Relations
TLDR
This work computes distributed meaning representations for each discourse argument by composition up the syntactic parse tree and performs a downward compositional pass to capture the meaning of coreferent entity mentions. Expand
Spinning Straw into Gold: Using Free Text to Train Monolingual Alignment Models for Non-factoid Question Answering
TLDR
It is shown that these alignment models trained directly from discourse structures imposed on free text improve performance considerably over an information retrieval baseline and a neural network language model trained on the same data. Expand
Beyond Factoid QA: Effective Methods for Non-factoid Answer Sentence Retrieval
TLDR
This work introduces the answer sentence retrieval task for non-factoid Web queries, and investigates how this task can be effectively solved under a learning to rank framework, and designs two types of features, namely semantic and context features, beyond traditional text matching features. Expand
Rhetoric Map of an Answer to Compound Queries
TLDR
The rhetoric map of an answer is built to prevent it from firing by queries whose keywords occur in non-adjacent areas of the Answer Map and the improvement of search relevance is evaluated by filtering out search results not satisfying the proposed rule system. Expand
Discovering Rhetoric Agreement between a Request and Response
TLDR
It is concluded that learning rhetoric structures in the form of CDTs is the key source of data to support answering complex questions, chatbots and dialogue management and with classification of multi-sentence answers in factoid question-answering systems. Expand
Learning Discourse-Level Structures for Question Answering
TLDR
A graph representation and matching technique for parse structures for paragraphs of text have been developed and the operation of generalization of two parse thickets is defined as a measure of semantic similarity between paragraphs ofText to be the maximal common sub-thicket of theseparse thickets. Expand
Rhetorical Agreement: Maintaining Cohesive Conversations
TLDR
It is concluded that learning rhetorical structures in the form of CDTs is the key source of data to support answering complex questions, chatbots and dialogue management and also with classification of multi-sentence answers in factoid question-answering systems. Expand
Semantic Enrichment for Non-factoid Question Answering
TLDR
Different taxonomies of semantic relations that are utilized for answering different types of non-factoid questions and different challenges for identifying semantic relations with their approaches to address them are discussed. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 25 REFERENCES
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
Corpus-based Question Answering for why-Questions
TLDR
NAZEQA, a Japanese why-QA system based on the proposed corpus-based approach, clearly outperforms a baseline that uses hand-crafted patterns with a Mean Reciprocal Rank (top-5) of 0.305, making it presumably the best-performing fully implemented why- QA system. Expand
Ranking community answers by modeling question-answer relationships via analogical reasoning
TLDR
This work proposes an analogical reasoning-based approach which measures the analogy between the new question-answer linkages and those of relevant knowledge which contains only positive links; the candidate answer which has the most analogous link is assumed to be the best answer. Expand
Why-Question Answering using Intra- and Inter-Sentential Causal Relations
TLDR
This is the first work that uses both intra- and inter-sentential causal relations for why-QA, and a method for assessing the appropriateness of causal relations as answers to a given question using the semantic orientation of excitation proposed by Hashimoto et al. (2012). Expand
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
The rhetorical parsing, summarization, and generation of natural language texts
This thesis is an inquiry into the nature of the high-level, rhetorical structure of unrestricted natural language texts, computational means to enable its derivation, and two applications (inExpand
High-performance, open-domain question answering from large text collections
TLDR
The theoretical concepts developed in the thesis are instrumental to the extraction of correct answers as response to a test set of 893 fact-seeking questions from a 3 Gigabyte text collection, and Experimental results show important qualitative improvements with respect to output from Web search engines. 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
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
Text-level Discourse Parsing with Rich Linguistic Features
TLDR
An RST-style text-level discourseparser, based on the HILDA discourse parser, is developed, which significantly improves its tree-building step by incorporating its own rich linguistic features. Expand
...
1
2
3
...