Automatic relation extraction (RE) for types of interest is of great importance for interpreting massive text corpora in an efficient manner. Traditional RE models have heavily relied on human-annotated corpus for training, which can be costly in generating labeled data and become obstacles when dealing with more relation types. Thus, more RE extraction systems have shifted to be built upon training data automatically acquired by linking to knowledge bases (distant supervision). However, due to the incompleteness of knowledge bases and the context-agnostic labeling, the training data collected via distant supervision (DS) can be very noisy. In recent years, as increasing attention has been brought to tackling question-answering (QA) tasks, user feedback or datasets of such tasks become more accessible. In this paper, we propose a novel framework, ReQuest, to leverage question-answer pairs as an indirect source of supervision for relation extraction, and study how to use such supervision to reduce noise induced from DS. Our model jointly embeds relation mentions, types, QA entity mention pairs and text features in two low-dimensional spaces (RE and QA), where objects with same relation types or semantically similar question-answer pairs have similar representations. Shared features connect these two spaces, carrying clearer semantic knowledge from both sources. ReQuest, then use these learned embeddings to estimate the types of test relation mentions. We formulate a global objective function and adopt a novel margin-based QA loss to reduce noise in DS by exploiting semantic evidence from the QA dataset. Our experimental results achieve an average of 11% improvement in F1 score on two public RE datasets combined with TREC QA dataset.
Distant supervision (DS) is a well-established method for relation extraction from text, based on the assumption that when a knowledge-base contains a relation between a term pair, then sentences that contain that pair are likely to express the relation. In this paper, we use the results of a crowdsourcing relation extraction task to identify two problems with DS data quality: the widely varying degree of false positives across different relations, and the observed causal connection between relations that are not considered by the DS method. The crowdsourcing data aggregation is performed using ambiguity-aware CrowdTruth metrics, that are used to capture and interpret inter-annotator disagreement. We also present preliminary results of using the crowd to enhance DS training data for a relation classification model, without requiring the crowd to annotate the entire set.
We explore methods to extract relations between named entities from free text in an unsupervised setting. In addition to standard feature extraction, we develop a novel method to re-weight word embeddings. We alleviate the problem of features sparsity using an individual feature reduction. Our approach exhibits a significant improvement by 5.8% over the state-of-the-art relation clustering scoring a F1-score of 0.416 on the NYT-FB dataset.
Kernel methods have produced state-of-the-art results for a number of NLP tasks such as relation extraction, but suffer from poor scalability due to the high cost of computing kernel similarities between natural language structures. A recently proposed technique, kernelized locality-sensitive hashing (KLSH), can significantly reduce the computational cost, but is only applicable to classifiers operating on kNN graphs. Here we propose to use random subspaces of KLSH codes for efficiently constructing an explicit representation of NLP structures suitable for general classification methods. Further, we propose an approach for optimizing the KLSH model for classification problems by maximizing an approximation of mutual information between the KLSH codes (feature vectors) and the class labels. We evaluate the proposed approach on biomedical relation extraction datasets, and observe significant and robust improvements in accuracy w.r.t. state-of-the-art classifiers, along with drastic (orders-of-magnitude) speedup compared to conventional kernel methods.
Most work in relation extraction forms a prediction by looking at a short span of text within a single sentence containing a single entity pair mention. This approach often does not consider interactions across mentions, requires redundant computation for each mention pair, and ignores relationships expressed across sentence boundaries. These problems are exacerbated by the document- (rather than sentence-) level annotation common in biological text. In response, we propose a model which simultaneously predicts relationships between all mention pairs in a document. We form pairwise predictions over entire paper abstracts using an efficient self-attention encoder. All-pairs mention scores allow us to perform multi-instance learning by aggregating over mentions to form entity pair representations. We further adapt to settings without mention-level annotation by jointly training to predict named entities and adding a corpus of weakly labeled data. In experiments on two Biocreative benchmark datasets, we achieve state of the art performance on the Biocreative V Chemical Disease Relation dataset for models without external KB resources. We also introduce a new dataset an order of magnitude larger than existing human-annotated biological information extraction datasets and more accurate than distantly supervised alternatives.
Information Extraction (IE) refers to automatically extracting structured relation tuples from unstructured texts. Common IE solutions, including Relation Extraction (RE) and open IE systems, can hardly handle cross-sentence tuples, and are severely restricted by limited relation types as well as informal relation specifications (e.g., free-text based relation tuples). In order to overcome these weaknesses, we propose a novel IE framework named QA4IE, which leverages the flexible question answering (QA) approaches to produce high quality relation triples across sentences. Based on the framework, we develop a large IE benchmark with high quality human evaluation. This benchmark contains 293K documents, 2M golden relation triples, and 636 relation types. We compare our system with some IE baselines on our benchmark and the results show that our system achieves great improvements.
Sentences with gapping, such as Paul likes coffee and Mary tea, lack an overt predicate to indicate the relation between two or more arguments. Surface syntax representations of such sentences are often produced poorly by parsers, and even if correct, not well suited to downstream natural language understanding tasks such as relation extraction that are typically designed to extract information from sentences with canonical clause structure. In this paper, we present two methods for parsing to a Universal Dependencies graph representation that explicitly encodes the elided material with additional nodes and edges. We find that both methods can reconstruct elided material from dependency trees with high accuracy when the parser correctly predicts the existence of a gap. We further demonstrate that one of our methods can be applied to other languages based on a case study on Swedish.
We study the problem of textual relation embedding with distant supervision. To combat the wrong labeling problem of distant supervision, we propose to embed textual relations with global statistics of relations, i.e., the co-occurrence statistics of textual and knowledge base relations collected from the entire corpus. This approach turns out to be more robust to the training noise introduced by distant supervision. On a popular relation extraction dataset, we show that the learned textual relation embedding can be used to augment existing relation extraction models and significantly improve their performance. Most remarkably, for the top 1,000 relational facts discovered by the best existing model, the precision can be improved from 83.9% to 89.3%.
State-of-the-art models for joint entity recognition and relation extraction strongly rely on external natural language processing (NLP) tools such as POS (part-of-speech) taggers and dependency parsers. Thus, the performance of such joint models depends on the quality of the features obtained from these NLP tools. However, these features are not always accurate for various languages and contexts. In this paper, we propose a joint neural model which performs entity recognition and relation extraction simultaneously, without the need of any manually extracted features or the use of any external tool. Specifically, we model the entity recognition task using a CRF (Conditional Random Fields) layer and the relation extraction task as a multi-head selection problem (i.e., potentially identify multiple relations for each entity). We present an extensive experimental setup, to demonstrate the effectiveness of our method using datasets from various contexts (i.e., news, biomedical, real estate) and languages (i.e., English, Dutch). Our model outperforms the previous neural models that use automatically extracted features, while it performs within a reasonable margin of feature-based neural models, or even beats them.
Semi-supervised bootstrapping techniques for relationship extraction from text iteratively expand a set of initial seed instances. Due to the lack of labeled data, a key challenge in bootstrapping is semantic drift: if a false positive instance is added during an iteration, then all following iterations are contaminated. We introduce BREX, a new bootstrapping method that protects against such contamination by highly effective confidence assessment. This is achieved by using entity and template seeds jointly (as opposed to just one as in previous work), by expanding entities and templates in parallel and in a mutually constraining fashion in each iteration and by introducing higherquality similarity measures for templates. Experimental results show that BREX achieves an F1 that is 0.13 (0.87 vs. 0.74) better than the state of the art for four relationships.
Training accurate classifiers requires many labels, but each label provides only limited information (one bit for binary classification). In this work, we propose BabbleLabble, a framework for training classifiers in which an annotator provides a natural language explanation for each labeling decision. A semantic parser converts these explanations into programmatic labeling functions that generate noisy labels for an arbitrary amount of unlabeled data, which is used to train a classifier. On three relation extraction tasks, we find that users are able to train classifiers with comparable F1 scores from 5-100$\times$ faster by providing explanations instead of just labels. Furthermore, given the inherent imperfection of labeling functions, we find that a simple rule-based semantic parser suffices.
Luminoso participated in the SemEval 2018 task on "Capturing Discriminative Attributes" with a system based on ConceptNet, an open knowledge graph focused on general knowledge. In this paper, we describe how we trained a linear classifier on a small number of semantically-informed features to achieve an $F_1$ score of 0.7368 on the task, close to the task's high score of 0.75.
의미역 할당(SRL)은 텍스트 내 술어-인수(predicate-argument) 구조를 이해하고 하위 응용을 가능하게 하는 자연어 처리(NLP)의 핵심 과제이다. 광범위한 연구에도 불구하고, 통합적 관점에서 해당 분야를 비판적으로 종합하는 포괄적 서베이는 여전히 부족하다. 본 서베이는 기존 연구를 정리하는 것을 넘어 여러 기여를 한다. 우리는 모델 아키텍처, 구문 특징 모델링, 응용 시나리오, 멀티모달 확장을 축으로 SRL 연구를 분류하는 통합 4차원 분류체계를 제안한다. 구문 특징이 언제, 왜 도움이 되는지에 대한 비판적 분석을 제공하며, 구문 보조 접근법이 구문 비사용 대안 대비 일관된 이득을 제공하는 조건을 밝힌다. 대규모 언어 모델(LLM) 시대의 SRL에 대한 최초의 체계적 논의를 제공하며, LLM과 전문 SRL 시스템의 상보적 역할을 검토하고 하이브리드 접근의 방향을 제시한다. SRL 서베이의 범위를 시각, 비디오, 음성 모달리티를 포함한 멀티모달 설정까지 확장하고, 이러한 모달리티 간 평가의 구조적 차이를 분석한다. 문헌은 ACL Anthology, IEEE Xplore, ACM Digital Library, Google Scholar에 대한 체계적 검색을 통해 수집하였으며, 2000년부터 2025년까지의 출판물을 대상으로 명시적 포함·제외 기준을 적용하여 약 200편의 핵심 참고문헌을 도출하였다. SRL 벤치마크, 평가 지표, 패러다임 모델링 접근법을 도메인 전반의 실용적 응용과 함께 논의한다. 대규모 언어 모델과 더 넓은 NLP 영향력 속에서 변화하는 SRL의 역할을 다루며, 향후 연구 방향을 분석한다.