Finding support sentences for entities

Blanco, Roi; Zaragoza, Hugo

doi:10.1145/1835449.1835507

Cited by 32 publications

(27 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, Blanco and Zaragoza (2010) focus on finding and ranking sentences that explain the relationship between an entity and a query. Our work is different in that we want to explain the relationship between two entities, rather than a query.…”

Section: Related Workmentioning

confidence: 99%

Learning to Explain Entity Relationships in Knowledge Graphs

Voskarides

Meij

Tsagkias

et al. 2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

View full text Add to dashboard Cite

We study the problem of explaining relationships between pairs of knowledge graph entities with human-readable descriptions. Our method extracts and enriches sentences that refer to an entity pair from a corpus and ranks the sentences according to how well they describe the relationship between the entities. We model this task as a learning to rank problem for sentences and employ a rich set of features. When evaluated on a large set of manually annotated sentences, we find that our method significantly improves over state-of-the-art baseline models.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning to Explain Entity Relationships in Knowledge Graphs

Voskarides

Meij

Tsagkias

et al. 2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

View full text Add to dashboard Cite

show abstract

“…Next, check if s j has only one associated named entity, then s j is not ambiguous, as in Algorithm 4 (line 10-11). If s j is associated with more than one named entities, disambiguate its named entities as in Algorithm 4 (line [13][14][15]. After disambiguating the named entities for s j , insert an entity-synonym relationship (e i , s j ) plus the publication time of d n , i.e., PubTime(d n ), in the output set and move the index pointer by the size of s j , that is ptr = (ptr + w) in Algorithm 3(line [11][12].…”

Section: Identifying and Disambiguating Synonyms Using The Nyt Corpusmentioning

confidence: 99%

“…Generally, because sentences are much smaller than documents and thus have limited content compared to documents, the effectiveness of the retrieval of sentences is significantly worse. To address this problem, Blanco and Zaragoza [15] proposed to use the context of sentences in order to improve the effectiveness of sentence retrieval.…”

Section: Related Workmentioning

confidence: 99%

“…The field ID specifies a prediction's unique number, PARENTID and TITLE represent a unique number and the title of d p respectively ENTITY contains a set of annotated entities p entity ⊂d e , FUTURE_DATE consists of "future" temporal expressions p future annotated in p, PUB_DATE is the publication date of the parent document d p and TEXT is a prediction's text p txt or the sentence of p. Note that each prediction must contain at least one "future" temporal expression, that is, p future = ∅. In addition, we explicitly model the context of the prediction p ctx , represented by the field CONTEXT and defined as surrounding sentences of the main sentence [15]. In our work, we define the context p ctx as the sentence immediately before and the one immediately after p txt .…”

Section: Prediction Modelmentioning

confidence: 99%

See 1 more Smart Citation

Time-aware approaches to information retrieval

Kanhabua

2012

SIGIR Forum

View full text Add to dashboard Cite

In this thesis, we address major challenges in searching temporal document collections. In such collections, documents are created and/or edited over time. Examples of temporal document collections are web archives, news archives, blogs, personal emails and enterprise documents. Unfortunately, traditional IR approaches based on term-matching only can give unsatisfactory results when searching temporal document collections. The reason for this is twofold: the contents of documents are strongly time-dependent, i.e., documents are about events happened at particular time periods, and a query representing an information need can be time-dependent as well, i.e., a temporal query.Our contributions in this thesis are different time-aware approaches within three topics in IR: content analysis, query analysis, and retrieval and ranking models. In particular, we aim at improving the retrieval effectiveness by 1) analyzing the contents of temporal document collections, 2) performing an analysis of temporal queries, and 3) explicitly modeling the time dimension into retrieval and ranking.Leveraging the time dimension in ranking can improve the retrieval effectiveness if information about the creation or publication time of documents is available. In this thesis, we analyze the contents of documents in order to determine the time of non-timestamped documents using temporal language models. We subsequently employ the temporal language models for determining the time of implicit temporal queries, and the determined time is used for re-ranking search results in order to improve the retrieval effectiveness.We study the effect of terminology changes over time and propose an approach to handling terminology changes using time-based synonyms. In addition, we propose different methods for predicting the effectiveness of temporal queries, so that a particular query enhancement technique can be performed to improve the overall performance. When the time dimension is incorporated into ranking, documents will be ranked according to both textual and temporal similarity. In this case, time uncertainty should also be taken into account. Thus, we propose a ranking model that considers the time uncertainty, and improve ranking by combining multiple features using learning-to-rank techniques.Through extensive evaluation, we show that our proposed time-aware approaches outperform traditional retrieval methods and improve the retrieval effectiveness in searching temporal document collections.

show abstract

“…This is different from the task of explaining relationships between entities in a knowledge base [9], since we include also yet unknown facts from documents. It is also different from explaining the relationship between entities and ad-hoc queries [2], since we look at relations between entities in documents. To isolate different kinds of errors, we evaluate the correctness of each fact extraction separately from the relevance of the fact for the query.…”

Section: Introductionmentioning

confidence: 99%

Finding Relevant Relations in Relevant Documents

Schuhmacher

Roth

Ponzetto

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This work studies the combination of a document retrieval and a relation extraction system for the purpose of identifying query-relevant relational facts. On the TREC Web collection, we assess extracted facts separately for correctness and relevance. Despite some TREC topics not being covered by the relation schema, we find that this approach reveals relevant facts, and in particular those not yet known in the knowledge base DBpedia. The study confirms that mention frequency, document relevance, and entity relevance are useful indicators for fact relevance. Still, the task remains an open research problem.

show abstract

Finding support sentences for entities

Cited by 32 publications

References 24 publications

Learning to Explain Entity Relationships in Knowledge Graphs

Learning to Explain Entity Relationships in Knowledge Graphs

Time-aware approaches to information retrieval

Finding Relevant Relations in Relevant Documents

Contact Info

Product

Resources

About