Exploring Correlation of Dependency Relation Paths for Answer Extraction

By Dan Shen, Dietrich Klakow. 2006

60 citations recorded by the source corpus.

In this paper, we explore correlation of dependency relation paths to rank candidate answers in answer extraction. Using the correlation measure, we compare dependency relations of a candidate answer and mapped question phrases in sentence with the corresponding relations in question. Different from previous studies, we propose an approximate phrase mapping algorithm and incorporate the mapping score into the correlation measure. The correlations are further incorporated into a Maximum Entropy-based ranking model which estimates path weights from training. Experimental results show that our method significantly outperforms state-of-the-art syntactic relation-based methods by up to 20% in MRR.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

SQuAD: 100,000+ Questions for Machine Comprehension of Text (2016, methodology): “…a question is similar to answer extraction , the ﬁnal step in the open-domain QA pipeline, methods for which include bootstrapping surface patterns (Ravichandran and Hovy, 2002), using dependency trees (Shen and Klakow, 2006), and using a factor graph over multiple sentences (Sun et al., 2013).”
Adaptive Document Retrieval for Deep Question Answering (2018, background): “The latter step often involves hand-written rules or machine learning classiﬁers (c. f. Shen and Klakow, 2006; Kaisser and Becker, 2004), and recently also deep neural networks (e. g. Chen et al., 2017; Wang et al., 2018) The number of candidate documents n affects the interplay between both…”
Analysis of Wikipedia-based Corpora for Question Answering (2018, background): “Given a document, answer extraction (Shen and Klakow, 2006; Sultan et al., 2016) finds answer phrases whereas answer selection (Wang et al.”
What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA (2007, methodology): “We follow a similar setup to Shen and Klakow (2006) by automatically selecting answer candidate sentences and then comparing against a human-judged gold standard.”
Using Semantic Roles to Improve Question Answering (2007, methodology): “Syn-tactic structure matching has been applied to passage retrieval (Cui et al., 2005) and answer extraction (Shen and Klakow, 2006).”
A Survey of Answer Extraction Techniques in Factoid Question Answering (2006, methodology): “This is similar to the way Shen and Klakow (2006) and Cui et al. (2005) ranks each word in candidate answer sentence for being the actual answer.”
Learning from On-Line User Feedback in Neural Question Answering on the Web (2019, background): “Answer extraction has traditionally been based on linguistic rules or pattern matching [13, 20, 31, 37], whereas deep neural networks [11, 17, 35, 42] have evolved only recently as the state-of-the-art.”