Extracting Knowledge from Web Text with Monte Carlo Tree Search

Liu, Guiliang; Xu, Li; Jiakang, Wang; Sun, Mingming; Li, Ping

doi:10.1145/3366423.3380010

Cited by 20 publications

(18 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are two types of information extraction systems: Closed Information Extraction (CIE) systems identify instances from a fixed and finite set of corpora, considering only a closed set of relationships between two arguments [10]. On the other hand, Open Information Extraction (OIE) systems use a domain-independent approach and are capable of extracting entities and relationship triples from natural language sentences.…”

Section: Information Extractionmentioning

confidence: 99%

LILLIE: Information extraction and database integration using linguistics and learning-based algorithms

Smith

Papadopoulos

Braschler

et al. 2022

Information Systems

View full text Add to dashboard Cite

Querying both structured and unstructured data via a single common query interface such as SQL or natural language has been a long standing research goal. Moreover, as methods for extracting information from unstructured data become ever more powerful, the desire to integrate the output of such extraction processes with ''clean'', structured data grows. We are convinced that for successful integration into databases, such extracted information in the form of ''triples'' needs to be both (1) of high quality and ( 2) have the necessary generality to link up with varying forms of structured data. It is the combination of both these aspects, which heretofore have been usually treated in isolation, where our approach breaks new ground.The cornerstone of our work is a novel, generic method for extracting open information triples from unstructured text, using a combination of linguistics and learning-based extraction methods, thus uniquely balancing both precision and recall. Our system called LILLIE (LInked Linguistics and Learning-Based Information Extractor) uses dependency tree modification rules to refine triples from a high-recall learning-based engine, and combines them with syntactic triples from a high-precision engine to increase effectiveness. In addition, our system features several augmentations, which modify the generality and the degree of granularity of the output triples. Even though our focus is on addressing both quality and generality simultaneously, our new method substantially outperforms current state-of-the-art systems on the two widely-used CaRB and Re-OIE16 benchmark sets for information extraction.We have made our code publicly available 1 to facilitate further research.

show abstract

Section: Information Extractionmentioning

confidence: 99%

LILLIE: Information extraction and database integration using linguistics and learning-based algorithms

Smith

Papadopoulos

Braschler

et al. 2022

Information Systems

View full text Add to dashboard Cite

show abstract

“…However, this model lacks the elegance to identify discontinuous structures, which may lead to poor recall. Cui et al [5], Sun et al [28] and Liu et al [18] built generation-based OIE extractor by directly decoding a prediction sequence containing a list of facts from the input source sentence, thus addressing the discontinuous structure recognition problem. Nevertheless, these methods have difficulty in capturing the token order within pieces of arguments and predicates, as they usually perform free token-level decoding operation.…”

Section: Related Workmentioning

confidence: 99%

“…With the explosive growth of the web corpora, extracting structured knowledge from unstructured, open-domain and diverse web text has become increasingly important to the web content mining [11,18,22]. This task is known as Open Information Extraction (OIE).…”

Section: Introductionmentioning

confidence: 99%

“…Existing OIE approaches usually follow the generation-based or labeling-based framework. Generation-based models [5,17,18,28] cast OIE into a text generation problem and leverage the sequence-to-sequence architecture, which allows for selecting source tokens to generate arbitrary output facts [20]. Nevertheless, this kind of models inevitably suffer from the well known problem: exposure bias.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Semi-Open Information Extraction

Zhang

Sheng

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

Open Information Extraction (OIE), the task aimed at discovering all textual facts organized in the form of (subject, predicate, object) found within a sentence, has gained much attention recently. However, in some knowledge-driven applications such as question answering, we often have a target entity and hope to obtain its structured factual knowledge for better understanding, instead of extracting all possible facts aimlessly from the corpus. In this paper, we define a new task, namely Semi-Open Information Extraction (SOIE), to address this need. The goal of SOIE is to discover domain-independent facts towards a particular entity from general and diverse web text. To facilitate research on this new task, we propose a large-scale human-annotated benchmark called SOIED, consisting of 61,984 facts for 8,013 subject entities annotated on 24,000 Chinese sentences collected from the web search engine.In addition, we propose a novel unified model called USE for this task. First, we introduce subject-guided sequence as input to a pretrained language model and normalize the hidden representations conditioned on the subject embedding to encode the sentence in a subject-aware manner. Second, we decompose SOIE into three uncoupled subtasks: predicate extraction, object extraction, and boundary alignment. They can all be formulated as the problem of table filling by forming a two-dimensional tag table based on a task-specific tagging scheme. Third, we introduce a collaborative learning strategy that enables the interactive relations among subtasks to be better exploited by explicitly exchanging informative clues. Finally, we evaluate USE and several strong baselines on our new dataset. Experimental results demonstrate the advantages of the proposed method and reveal insight for future improvement.

show abstract

“…While the performance of open information extraction systems (i.e. systems that extract information from general web text) has improved in recent years [4,16,27], the quality of extracted information has not yet reached a level where an integration into knowledge graphs like DBpedia should be done without further filtering.…”

Section: Introduction 1motivation and Problemmentioning

confidence: 99%

Information Extraction From Co-Occurring Similar Entities

Heist

Paulheim

2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

Knowledge about entities and their interrelations is a crucial factor of success for tasks like question answering or text summarization. Publicly available knowledge graphs like Wikidata or DBpedia are, however, far from being complete. In this paper, we explore how information extracted from similar entities that co-occur in structures like tables or lists can help to increase the coverage of such knowledge graphs. In contrast to existing approaches, we do not focus on relationships within a listing (e.g., between two entities in a table row) but on the relationship between a listing's subject entities and the context of the listing. To that end, we propose a descriptive rule mining approach that uses distant supervision to derive rules for these relationships based on a listing's context. Extracted from a suitable data corpus, the rules can be used to extend a knowledge graph with novel entities and assertions. In our experiments we demonstrate that the approach is able to extract up to 3M novel entities and 30M additional assertions from listings in Wikipedia. We find that the extracted information is of high quality and thus suitable to extend Wikipedia-based knowledge graphs like DBpedia, YAGO, and CaLiGraph. For the case of DBpedia, this would result in an increase of covered entities by roughly 50%.

show abstract

Extracting Knowledge from Web Text with Monte Carlo Tree Search

Cited by 20 publications

References 19 publications

LILLIE: Information extraction and database integration using linguistics and learning-based algorithms

LILLIE: Information extraction and database integration using linguistics and learning-based algorithms

Semi-Open Information Extraction

Information Extraction From Co-Occurring Similar Entities

Contact Info

Product

Resources

About