Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model

Extraction from raw text to a knowledge base of entities and fine-grained types is often cast as prediction into a flat set of entity and type labels, neglecting the rich hierarchies over types and entities contained in curated ontologies. Previous attempts to incorporate hierarchical structure have yielded little benefit and are restricted to shallow ontologies. This paper presents new methods using real and complex bilinear mappings for integrating hierarchical information, yielding substantial improvement over flat predictions in entity linking and fine-grained entity typing, and achieving new state-of-the-art results for end-to-end models on the benchmark FIGER dataset. We also present two new human-annotated datasets containing wide and deep hierarchies which we will release to the community to encourage further research in this direction: MedMentions, a collection of PubMed abstracts in which 246k mentions have been mapped to the massive UMLS ontology; and TypeNet, which aligns Freebase types with the WordNet hierarchy to obtain nearly 2k entity types. In experiments on all three datasets we show substantial gains from hierarchy-aware training.

Most work on knowledge base completion focuses on relations between entities, while entity types are also important knowledge. This paper addresses the problem of fine-grained entity typing for knowledge base completion. Context information plays a vital role in fine-grained entity typing, hence there is an urgent need to find ideal context representations. This paper presents a new approach CNNJM (convolutional neural network joint model) to learn the embeddings of the entities and their contextual information using convolutional neural network and correctly categorize the entities into their fine-grained type classes. We show that CNNJM outperforms state-of-art methods on a fine-grained entity typing benchmark.

Fine-grained Entity typing (FGET) is the task of assigning a fine-grained type from a hierarchy to entity mentions in the text. As the taxonomy of types evolves continuously, it is desirable for an entity typing system to be able to recognize novel types without additional training. This work proposes a zero-shot entity typing approach that utilizes the type description available from Wikipedia to build a distributed semantic representation of the types. During training, our system learns to align the entity mentions and their corresponding type representations on the known types. At test time, any new type can be incorporated into the system given its Wikipedia descriptions. We evaluate our approach on FIGER, a public benchmark entity tying dataset. Because the existing test set of FIGER covers only a small portion of the fine-grained types, we create a new test set by manually annotating a portion of the noisy training data. Our experiments demonstrate the effectiveness of the proposed method in recognizing novel types that are not present in the training data.

Fine-grained entity typing, which aims to assign specific types to entity mentions in text, is attracting increasing attention in the field of natural language processing (NLP). However, it is quite a challenging problem due to the highly ambiguous nature of many entity mentions. Most existing entity typing methods based on attention mechanism generally extract the salient features separately from the entity mention and the contextual words. However, these approaches suffer from <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">two main limitations</i> : (1) They ignore the rich information contained by entity mentions when applying the attention mechanisms. (2) They do not consider the diversity of attention processes which can be beneficial in finding the discriminative features. To address these issues, we propose the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">diversified semantic attention model (DSAM)</i> for fine-grained entity typing, and the main novelties are: (1) It explicitly pursues the diversity of attention and is able to maximally gather discriminative information. (2) It integrates two level attentions—the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">mention-level attention</i> and the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">context-level attention—</i> to jointly capture the rich information from mentions and contexts to enhance their mutual promotions. (3) It combines the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">attention maps constraint</i> and the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">attention segments constrain</i> to exploit the subtle semantic differences for distinguishing the subtypes. Importantly, the proposed DSAM approach can be trained end-to-end without employing ad-hoc features or post-processing. Extensive experiments using three benchmark datasets demonstrated that our DSAM approach achieves competitive performance compared to the current state-of-the-art methods used for fine-grained entity typing.

Fine-grained entity typing aims to identify the semantic type of an entity in a particular plain text. It is an important task which can be helpful for a lot of natural language processing (NLP) applications. Most existing methods typically extract features separately from the entity mention and context words for type classification. These methods inevitably fail to model complex correlations between entity mentions and context words. They also neglect rich background information about these entities in knowledge bases (KBs). To address these issues, we take information from KBs into consideration to bridge entity mentions and their context together, and thereby propose Knowledge-Attention Neural Fine-Grained Entity Typing. Experimental results and case studies on real-world datasets demonstrate that our model significantly outperforms other state-of-the-art methods, revealing the effectiveness of incorporating KB information for entity typing. Code and data for this paper can be found at https://github.com/thunlp/KNET.

Fine-grained entity typing (FET) aims to assign proper semantic types to entity mentions according to their context, which is a fundamental task in various entity-leveraging applications. Current FET systems usually establish on large-scale weaklysupervised/distantly annotation data, which may contain abundant noise and thus severely hinder the performance of the FET task. Although previous studies have made great success in automatically identifying the noisy labels in FET, they usually rely on some auxiliary resources which may be unavailable in real-world applications (e.g., pre-defined hierarchical type structures, humanannotated subsets). In this paper, we propose a novel approach to automatically correct noisy labels for FET without external resources. Specifically, it first identifies the potentially noisy labels by estimating the posterior probability of a label being positive or negative according to the logits output by the model, and then relabel candidate noisy labels by training a robust model over the remaining clean labels. Experiments on two popular benchmarks prove the effectiveness of our method. Our source code can be obtained from https://github.com/CCIIPLab/DenoiseFET.

Hongliang Dai, Yangqiu Song, Haixun Wang. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

In recent years, distantly-supervised relation extraction has achieved a certain success by using deep neural networks. Distant Supervision (DS) can automatically generate large-scale annotated data by aligning entity pairs from Knowledge Bases (KB) to sentences. However, these DS-generated datasets inevitably have wrong labels that result in incorrect evaluation scores during testing, which may mislead the researchers. To solve this problem, we build a new dataset NYTH, where we use the DS-generated data as training data and hire annotators to label test data. Compared with the previous datasets, NYT-H has a much larger test set and then we can perform more accurate and consistent evaluation. Finally, we present the experimental results of several widely used systems on NYT-H. The experimental results show that the ranking lists of the comparison systems on the DS-labelled test data and human-annotated test data are different. This indicates that our human-annotated data is necessary for evaluation of distantly-supervised relation extraction.

We study the problem of few-shot Fine-grained Entity Typing (FET), where only a few annotated entity mentions with contexts are given for each entity type. Recently, prompt-based tuning has demonstrated superior performance to standard fine-tuning in few-shot scenarios by formulating the entity type classification task as a ''fill-in-the-blank'' problem. This allows effective utilization of the strong language modeling capability of Pre-trained Language Models (PLMs). Despite the success of current prompt-based tuning approaches, two major challenges remain: (1) the verbalizer in prompts is either manually designed or constructed from external knowledge bases, without considering the target corpus and label hierarchy information, and (2) current approaches mainly utilize the representation power of PLMs, but have not explored their generation power acquired through extensive general-domain pre-training. In this work, we propose a novel framework for few-shot FET consisting of two modules: (1) an entity type label interpretation module automatically learns to relate type labels to the vocabulary by jointly leveraging few-shot instances and the label hierarchy, and (2) a type-based contextualized instance generator produces new instances based on given instances to enlarge the training set for better generalization. On three benchmark datasets, our model outperforms existing methods by significant margins. Code can be found at https://github.com/teapot123/Fine-Grained-Entity-Typing.

This paper investigates how to effectively incorporate a pre-trained masked language model (MLM), such as BERT, into an encoder-decoder (EncDec) model for grammatical error correction (GEC). The answer to this question is not as straightforward as one might expect because the previous common methods for incorporating a MLM into an EncDec model have potential drawbacks when applied to GEC. For example, the distribution of the inputs to a GEC model can be considerably different (erroneous, clumsy, etc.) from that of the corpora used for pre-training MLMs; however, this issue is not addressed in the previous methods. Our experiments show that our proposed method, where we first fine-tune a MLM with a given GEC corpus and then use the output of the fine-tuned MLM as additional features in the GEC model, maximizes the benefit of the MLM. The best-performing model achieves state-of-the-art performances on the BEA-2019 and CoNLL-2014 benchmarks. Our code is publicly available at: https://github.com/kanekomasahiro/bert-gec.

Transformer-based masked language models such as BERT, trained on general corpora, have shown impressive performance on downstream tasks. It has also been demonstrated that the downstream task performance of such models can be improved by pretraining larger models for longer on more data. In this work, we empirically evaluate the extent to which these results extend to tasks in science. We use 14 domain-specific transformer-based models (including ScholarBERT, a new 770Mparameter science-focused masked language model pretrained on up to 225B tokens) to evaluate the impact of training data, model size, pretraining and finetuning time on 12 downstream scientific tasks. Interestingly, we find that increasing model size, training data, or compute time does not always lead to significant improvements (i.e., >1% F1), if any, in scientific information extraction tasks. We offer possible explanations for this surprising result.

Owing to its unique literal and aesthetical characteristics, automatic generation of Chinese poetry is still challenging in Artificial Intelligence, which can hardly be straightforwardly realized by end-to-end methods. In this paper, we propose a novel iterative polishing framework for highly qualified Chinese poetry generation. In the first stage, an encoder-decoder structure is utilized to generate a poem draft. Afterwards, our proposed Quality-Aware Masked Language Model (QA-MLM) is employed to polish the draft towards higher quality in terms of linguistics and literalness. Based on a multi-task learning scheme, QA-MLM is able to determine whether polishing is needed based on the poem draft. Furthermore, QA-MLM is able to localize improper characters of the poem draft and substitute with newly predicted ones accordingly. Benefited from the masked language model structure, QA-MLM incorporates global context information into the polishing process, which can obtain more appropriate polishing results than the unidirectional sequential decoding. Moreover, the iterative polishing process will be terminated automatically when QA-MLM regards the processed poem as a qualified one. Both human and automatic evaluation have been conducted, and the results demonstrate that our approach is effective to improve the performance of encoder-decoder structure.

In this paper, we firstly empirically find that existing models struggle to handle hard mentions due to their insufficient contexts, which consequently limits their overall typing performance. To this end, we propose to exploit sibling mentions for enhancing the mention representations. Specifically, we present two different metrics for sibling selection and employ an attentive graph neural network to aggregate information from sibling mentions. The proposed graph model is scalable in that unseen test mentions are allowed to be added as new nodes for inference. Exhaustive experiments demonstrate the effectiveness of our sibling learning strategy, where our model outperforms ten strong baselines. Moreover, our experiments indeed prove the superiority of sibling mentions in helping clarify the types for hard mentions.

We present LOME, a system for performing multilingual information extraction. Given a text document as input, our core system identifies spans of textual entity and event mentions with a FrameNet (Baker et al., 1998) parser. It subsequently performs coreference resolution, fine-grained entity typing, and temporal relation prediction between events. By doing so, the system constructs an event and entity focused knowledge graph. We can further apply third-party modules for other types of annotation, like relation extraction. Our (multilingual) first-party modules either outperform or are competitive with the (monolingual) state-of-the-art. We achieve this through the use of multilingual encoders like XLM-R (Conneau et al., 2020) and leveraging multilingual training data. LOME is available as a Docker container on Docker Hub. In addition, a lightweight version of the system is accessible as a web demo.

BPEmb is a collection of pre-trained subword unit embeddings in 275 languages, based on Byte-Pair Encoding (BPE). In an evaluation using fine-grained entity typing as testbed, BPEmb performs competitively, and for some languages better than alternative subword approaches, while requiring vastly fewer resources and no tokenization.