A framework for entailed relation recognition

Roth, Dan; Sammons, Mark; Vydiswaran, V. G. Vinod

doi:10.3115/1667583.1667603

Cited by 10 publications

(12 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to the formulation in [24], the information need is modeled as a structured query consisting of three elements: the relation of interest, R, and the two entities, E1 and E2, participating in the relation. The entities take specific roles in the relation, i.e., the entities are "typed" for a particular relation.…”

Section: Searching For Evidencementioning

confidence: 99%

Gauging the internet doctor

Vydiswaran

Zhai

Roth

2011

Proceedings of the 2011 Workshop on Data Mining for Medicine and Healthcare

Self Cite

View full text Add to dashboard Cite

As more and more content is published and consumed online, it is imperative to know if an information nugget found on the Web is trustworthy or not. This is especially important for online medical information as it affects the most vulnerable group of users looking for medical help online. In this paper, we study the feasibility of automatically assessing the trustworthiness of a medical claim based on community knowledge, and propose techniques to assign a reliability score for an information nugget based on support over a community-generated collection. Specifically, we model the trustworthiness of a medical claim based on experiences shared by users in health forums and mailing lists. The proposed claim scores can be used to rank related claims on their relative trustworthiness. We further extend the notion of trustworthiness to a site (or equivalently, a database of claims from the site) and propose a scheme to rank sites based on aggregating the trust scores of claims from the site. Our experiments show that community knowledge can be exploited to help users distinguish reliable medical claims from unreliable ones. The proposed techniques can be applied to other domains where similar corpora are available.

show abstract

Section: Searching For Evidencementioning

confidence: 99%

Gauging the internet doctor

Vydiswaran

Zhai

Roth

2011

Proceedings of the 2011 Workshop on Data Mining for Medicine and Healthcare

Self Cite

View full text Add to dashboard Cite

show abstract

“…Only a few works considered improving the evidence presentation in claim verification problems. Roth et al (2009) introduce the task of Entailed Relation Recognition -given a set of short paragraphs and a relational fact in the triple form of (argument 1 , relation, argument 2 ), finding the paragraphs that can entail this fact. They first use Expanded Lexical Retrieval to rank and keep the topk paragraphs as candidates, then build a TE classifier over each (candidate, statement) pair.…”

Section: Related Workmentioning

confidence: 99%

“…A simple approach to identifying evidence is to detect the top-k sentences that are lexically similar to the claim, as some pipeline systems (Roth et al, 2009;Thorne et al, 2018) do. However, a claimunaware fixed k is less optimal, adding noise or missing key supporting factors, consequently limiting the performance.…”

Section: Evidence Identificationmentioning

confidence: 99%

TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verification

Yin¹,

Roth²

2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

Determining whether a given claim is supported by evidence is a fundamental NLP problem that is best modeled as Textual Entailment. However, given a large collection of text, finding evidence that could support or refute a given claim is a challenge in itself, amplified by the fact that different evidence might be needed to support or refute a claim. Nevertheless, most prior work decouples evidence identification from determining the truth value of the claim given the evidence.We propose to consider these two aspects jointly. We develop TWOWINGOS (twowing optimization strategy), a system that, while identifying appropriate evidence for a claim, also determines whether or not the claim is supported by the evidence. Given the claim, TWOWINGOS attempts to identify a subset of the evidence candidates; given the predicted evidence, it then attempts to determine the truth value of the corresponding claim. We treat this challenge as coupled optimization problems, training a joint model for it. TWOWINGOS offers two advantages: (i) Unlike pipeline systems, it facilitates flexible-size evidence set, and (ii) Joint training improves both the claim verification and the evidence identification. Experiments on a benchmark dataset show state-of-the-art performance. 1

show abstract

“…RTE is the task of determining, for two textual expressions T (text) and H (hypothesis), whether the meaning of H can be inferred from the meaning of T (Dagan and Glickman, 2004). In RE, RTE systems have been applied to validate a given relation instance (Wang and Neumann, 2008) and to extract instances entailing a given target relation (Romano et al, 2006;Bar-Haim et al, 2007;Roth et al, 2009). …”

Section: Related Workmentioning

confidence: 99%