2022 ACL 最全事件抽取和关系抽取相关论文

2022 ACL 最全事件抽取和关系抽取相关论文

事件触发词抽取

Saliency as Evidence: Event Detection with Trigger Saliency Attribution

• Liu, Jian and Chen, Yufeng and Xu, Jinan
• https://aclanthology.org/2022.acl-long.313
• https://github.com/jianliu-ml/saliencyed
• Event detection (ED) is a critical subtask of event extraction that seeks to identify event triggers of certain types in texts. Despite significant advances in ED, existing methods typically follow a "one model fits all types’’ approach, which sees no differences between event types and often results in a quite skewed performance. Finding the causes of skewed performance is crucial for the robustness of an ED model, but to date there has been little exploration of this problem. This research examines the issue in depth and presents a new concept termed trigger salience attribution, which can explicitly quantify the underlying patterns of events. On this foundation, we develop a new training mechanism for ED, which can distinguish between trigger-dependent and context-dependent types and achieve promising performance on two benchmarks. Finally, by highlighting many distinct characteristics of trigger-dependent and context-dependent types, our work may promote more research into this problem.

事件论元抽取

Document-Level Event Argument Extraction via Optimal Transport

• Pouran Ben Veyseh, Amir and Nguyen, Minh Van and Dernoncourt, Franck and Min, Bonan and Nguyen, Thien
• https://aclanthology.org/2022.findings-acl.130
• Event Argument Extraction (EAE) is one of the sub-tasks of event extraction, aiming to recognize the role of each entity mention toward a specific event trigger. Despite the success of prior works in sentence-level EAE, the document-level setting is less explored. In particular, whereas syntactic structures of sentences have been shown to be effective for sentence-level EAE, prior document-level EAE models totally ignore syntactic structures for documents. Hence, in this work, we study the importance of syntactic structures in document-level EAE. Specifically, we propose to employ Optimal Transport (OT) to induce structures of documents based on sentence-level syntactic structures and tailored to EAE task. Furthermore, we propose a novel regularization technique to explicitly constrain the contributions of unrelated context words in the final prediction for EAE. We perform extensive experiments on the benchmark document-level EAE dataset RAMS that leads to the state-of-the-art performance. Moreover, our experiments on the ACE 2005 dataset reveals the effectiveness of the proposed model in the sentence-level EAE by establishing new state-of-the-art results.

Efficient Argument Structure Extraction with Transfer Learning and Active Learning

• Hua, Xinyu and Wang, Lu
• https://aclanthology.org/2022.findings-acl.36
• The automation of extracting argument structures faces a pair of challenges on (1) encoding long-term contexts to facilitate comprehensive understanding, and (2) improving data efficiency since constructing high-quality argument structures is time-consuming. In this work, we propose a novel context-aware Transformer-based argument structure prediction model which, on five different domains, significantly outperforms models that rely on features or only encode limited contexts. To tackle the difficulty of data annotation, we examine two complementary methods: (i) transfer learning to leverage existing annotated data to boost model performance in a new target domain, and (ii) active learning to strategically identify a small amount of samples for annotation. We further propose model-independent sample acquisition strategies, which can be generalized to diverse domains. With extensive experiments, we show that our simple-yet-effective acquisition strategies yield competitive results against three strong comparisons. Combined with transfer learning, substantial F1 score boost (5-25) can be further achieved during the early iterations of active learning across domains.

Have my arguments been replied to? Argument Pair Extraction as Machine Reading Comprehension

• Bao, Jianzhu and Sun, Jingyi and Zhu, Qinglin and Xu, Ruifeng
• https://aclanthology.org/2022.acl-short.4
• https://github.com/hlt-hitsz/mrc_ape
• Argument pair extraction (APE) aims to automatically mine argument pairs from two interrelated argumentative documents. Existing studies typically identify argument pairs indirectly by predicting sentence-level relations between two documents, neglecting the modeling of the holistic argument-level interactions. Towards this issue, we propose to address APE via a machine reading comprehension (MRC) framework with two phases. The first phase employs an argument mining (AM) query to identify all arguments in two documents. The second phase considers each identified argument as an APE query to extract its paired arguments from another document, allowing to better capture the argument-level interactions. Also, this framework enables these two phases to be jointly trained in a single MRC model, thereby maximizing the mutual benefits of them. Experimental results demonstrate that our approach achieves the best performance, outperforming the state-of-the-art method by 7.11% in F1 score.

Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction

• Huang, Kuan-Hao and Hsu, I-Hung and Natarajan, Prem and Chang, Kai-Wei and Peng, Nanyun
• https://aclanthology.org/2022.acl-long.317
• https://github.com/pluslabnlp/x-gear
• We present a study on leveraging multilingual pre-trained generative language models for zero-shot cross-lingual event argument extraction (EAE). By formulating EAE as a language generation task, our method effectively encodes event structures and captures the dependencies between arguments. We design language-agnostic templates to represent the event argument structures, which are compatible with any language, hence facilitating the cross-lingual transfer. Our proposed model finetunes multilingual pre-trained generative language models to generate sentences that fill in the language-agnostic template with arguments extracted from the input passage. The model is trained on source languages and is then directly applied to target languages for event argument extraction. Experiments demonstrate that the proposed model outperforms the current state-of-the-art models on zero-shot cross-lingual EAE. Comprehensive studies and error analyses are presented to better understand the advantages and the current limitations of using generative language models for zero-shot cross-lingual transfer EAE.

Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction

• Ma, Yubo and Wang, Zehao and Cao, Yixin and Li, Mukai and Chen, Meiqi and Wang, Kun and Shao, Jing
• https://aclanthology.org/2022.acl-long.466
• https://github.com/mayubo2333/PAIE
• In this paper, we propose an effective yet efficient model PAIE for both sentence-level and document-level Event Argument Extraction (EAE), which also generalizes well when there is a lack of training data. On the one hand, PAIE utilizes prompt tuning for extractive objectives to take the best advantages of Pre-trained Language Models (PLMs). It introduces two span selectors based on the prompt to select start/end tokens among input texts for each role. On the other hand, it captures argument interactions via multi-role prompts and conducts joint optimization with optimal span assignments via a bipartite matching loss. Also, with a flexible prompt design, PAIE can extract multiple arguments with the same role instead of conventional heuristic threshold tuning. We have conducted extensive experiments on three benchmarks, including both sentence- and document-level EAE. The results present promising improvements from PAIE (3.5% and 2.3% F1 gains in average on three benchmarks, for PAIE-base and PAIE-large respectively). Further analysis demonstrates the efficiency, generalization to few-shot settings, and effectiveness of different extractive prompt tuning strategies. Our code is available at https://github.com/mayubo2333/PAIE.

事件抽取

Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding

• Wang, Sijia and Yu, Mo and Chang, Shiyu and Sun, Lichao and Huang, Lifu
• https://aclanthology.org/2022.findings-acl.16
• https://github.com/VT-NLP/Event_Query_Extract
• Event extraction is typically modeled as a multi-class classification problem where event types and argument roles are treated as atomic symbols. These approaches are usually limited to a set of pre-defined types. We propose a novel event extraction framework that uses event types and argument roles as natural language queries to extract candidate triggers and arguments from the input text. With the rich semantics in the queries, our framework benefits from the attention mechanisms to better capture the semantic correlation between the event types or argument roles and the input text. Furthermore, the query-and-extract formulation allows our approach to leverage all available event annotations from various ontologies as a unified model. Experiments on ACE and ERE demonstrate that our approach achieves state-of-the-art performance on each dataset and significantly outperforms existing methods on zero-shot event extraction.

Legal Judgment Prediction via Event Extraction with Constraints

• Feng, Yi and Li, Chuanyi and Ng, Vincent
• https://aclanthology.org/2022.acl-long.48
• https://github.com/wapay/epm
• While significant progress has been made on the task of Legal Judgment Prediction (LJP) in recent years, the incorrect predictions made by SOTA LJP models can be attributed in part to their failure to (1) locate the key event information that determines the judgment, and (2) exploit the cross-task consistency constraints that exist among the subtasks of LJP. To address these weaknesses, we propose EPM, an Event-based Prediction Model with constraints, which surpasses existing SOTA models in performance on a standard LJP dataset.

Dynamic Prefix-Tuning for Generative Template-based Event Extraction

• Liu, Xiao and Huang, Heyan and Shi, Ge and Wang, Bo
• https://aclanthology.org/2022.acl-long.358
• We consider event extraction in a generative manner with template-based conditional generation. Although there is a rising trend of casting the task of event extraction as a sequence generation problem with prompts, these generation-based methods have two significant challenges, including using suboptimal prompts and static event type information. In this paper, we propose a generative template-based event extraction method with dynamic prefix (GTEE-DynPref) by integrating context information with type-specific prefixes to learn a context-specific prefix for each context. Experimental results show that our model achieves competitive results with the state-of-the-art classification-based model OneIE on ACE 2005 and achieves the best performances on ERE. Additionally, our model is proven to be portable to new types of events effectively.

Unified Structure Generation for Universal Information Extraction

• Lu, Yaojie and Liu, Qing and Dai, Dai and Xiao, Xinyan and Lin, Hongyu and Han, Xianpei and Sun, Le and Wu, Hua
• https://aclanthology.org/2022.acl-long.395
• https://github.com/universal-ie/UIE
• Information extraction suffers from its varying targets, heterogeneous structures, and demand-specific schemas. In this paper, we propose a unified text-to-structure generation framework, namely UIE, which can universally model different IE tasks, adaptively generate targeted structures, and collaboratively learn general IE abilities from different knowledge sources. Specifically, UIE uniformly encodes different extraction structures via a structured extraction language, adaptively generates target extractions via a schema-based prompt mechanism {–} structural schema instructor, and captures the common IE abilities via a large-scale pretrained text-to-structure model. Experiments show that UIE achieved the state-of-the-art performance on 4 IE tasks, 13 datasets, and on all supervised, low-resource, and few-shot settings for a wide range of entity, relation, event and sentiment extraction tasks and their unification. These results verified the effectiveness, universality, and transferability of UIE.

关系抽取

HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction

• Li, Dongyang and Zhang, Taolin and Hu, Nan and Wang, Chengyu and He, Xiaofeng
• https://aclanthology.org/2022.findings-acl.202
• https://github.com/matnlp/hiclre
• Distant supervision assumes that any sentence containing the same entity pairs reflects identical relationships. Previous works of distantly supervised relation extraction (DSRE) task generally focus on sentence-level or bag-level de-noising techniques independently, neglecting the explicit interaction with cross levels. In this paper, we propose a hierarchical contrastive learning Framework for Distantly Supervised relation extraction (HiCLRE) to reduce noisy sentences, which integrate the global structural information and local fine-grained interaction. Specifically, we propose a three-level hierarchical learning framework to interact with cross levels, generating the de-noising context-aware representations via adapting the existing multi-head self-attention, named Multi-Granularity Recontextualization. Meanwhile, pseudo positive samples are also provided in the specific level for contrastive learning via a dynamic gradient-based data augmentation strategy, named Dynamic Gradient Adversarial Perturbation. Experiments demonstrate that HiCLRE significantly outperforms strong baselines in various mainstream DSRE datasets.

Learning Reasoning Patterns for Relational Triple Extraction with Mutual Generation of Text and Graph

• Chen, Yubo and Zhang, Yunqi and Huang, Yongfeng
• https://aclanthology.org/2022.findings-acl.129
• Relational triple extraction is a critical task for constructing knowledge graphs. Existing methods focused on learning text patterns from explicit relational mentions. However, they usually suffered from ignoring relational reasoning patterns, thus failed to extract the implicitly implied triples. Fortunately, the graph structure of a sentence{‘}s relational triples can help find multi-hop reasoning paths. Moreover, the type inference logic through the paths can be captured with the sentence{’}s supplementary relational expressions that represent the real-world conceptual meanings of the paths’ composite relations. In this paper, we propose a unified framework to learn the relational reasoning patterns for this task. To identify multi-hop reasoning paths, we construct a relational graph from the sentence (text-to-graph generation) and apply multi-layer graph convolutions to it. To capture the relation type inference logic of the paths, we propose to understand the unlabeled conceptual expressions by reconstructing the sentence from the relational graph (graph-to-text generation) in a self-supervised manner. Experimental results on several benchmark datasets demonstrate the effectiveness of our method.

A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation Extraction

• Liu, Yang and Hu, Jinpeng and Wan, Xiang and Chang, Tsung-Hui
• https://aclanthology.org/2022.findings-acl.62
• https://github.com/lylylylylyly/simplefsre
• Few-Shot Relation Extraction aims at predicting the relation for a pair of entities in a sentence by training with a few labelled examples in each relation. Some recent works have introduced relation information (i.e., relation labels or descriptions) to assist model learning based on Prototype Network. However, most of them constrain the prototypes of each relation class implicitly with relation information, generally through designing complex network structures, like generating hybrid features, combining with contrastive learning or attention networks. We argue that relation information can be introduced more explicitly and effectively into the model. Thus, this paper proposes a direct addition approach to introduce relation information. Specifically, for each relation class, the relation representation is first generated by concatenating two views of relations (i.e., [CLS] token embedding and the mean value of embeddings of all tokens) and then directly added to the original prototype for both train and prediction. Experimental results on the benchmark dataset FewRel 1.0 show significant improvements and achieve comparable results to the state-of-the-art, which demonstrates the effectiveness of our proposed approach. Besides, further analyses verify that the direct addition is a much more effective way to integrate the relation representations and the original prototypes.

Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion

• Xie, Yiqing and Shen, Jiaming and Li, Sha and Mao, Yuning and Han, Jiawei
• https://aclanthology.org/2022.findings-acl.23
• https://github.com/veronicium/eider
• Document-level relation extraction (DocRE) aims to extract semantic relations among entity pairs in a document. Typical DocRE methods blindly take the full document as input, while a subset of the sentences in the document, noted as the evidence, are often sufficient for humans to predict the relation of an entity pair. In this paper, we propose an evidence-enhanced framework, Eider, that empowers DocRE by efficiently extracting evidence and effectively fusing the extracted evidence in inference. We first jointly train an RE model with a lightweight evidence extraction model, which is efficient in both memory and runtime. Empirically, even training the evidence model on silver labels constructed by our heuristic rules can lead to better RE performance. We further design a simple yet effective inference process that makes RE predictions on both extracted evidence and the full document, then fuses the predictions through a blending layer. This allows Eider to focus on important sentences while still having access to the complete information in the document. Extensive experiments show that Eider outperforms state-of-the-art methods on three benchmark datasets (e.g., by 1.37/1.26 Ign F1/F1 on DocRED).

RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction

• Chia, Yew Ken and Bing, Lidong and Poria, Soujanya and Si, Luo
• https://aclanthology.org/2022.findings-acl.5
• https://github.com/declare-lab/relationprompt
• Despite the importance of relation extraction in building and representing knowledge, less research is focused on generalizing to unseen relations types. We introduce the task setting of Zero-Shot Relation Triplet Extraction (ZeroRTE) to encourage further research in low-resource relation extraction methods. Given an input sentence, each extracted triplet consists of the head entity, relation label, and tail entity where the relation label is not seen at the training stage. To solve ZeroRTE, we propose to synthesize relation examples by prompting language models to generate structured texts. Concretely, we unify language model prompts and structured text approaches to design a structured prompt template for generating synthetic relation samples when conditioning on relation label prompts (RelationPrompt). To overcome the limitation for extracting multiple relation triplets in a sentence, we design a novel Triplet Search Decoding method. Experiments on FewRel and Wiki-ZSL datasets show the efficacy of RelationPrompt for the ZeroRTE task and zero-shot relation classification. Our code and data are available at github.com/declare-lab/RelationPrompt.

Pretrained Knowledge Base Embeddings for improved Sentential Relation Extraction

• Papaluca, Andrea and Krefl, Daniel and Suominen, Hanna and Lenskiy, Artem
• https://aclanthology.org/2022.acl-srw.29
• https://github.com/brunoliegibastonliegi/pretrained-kb-embeddings-for-re
• In this work we put forward to combine pretrained knowledge base graph embeddings with transformer based language models to improve performance on the sentential Relation Extraction task in natural language processing. Our proposed model is based on a simple variation of existing models to incorporate off-task pretrained graph embeddings with an on-task finetuned BERT encoder. We perform a detailed statistical evaluation of the model on standard datasets. We provide evidence that the added graph embeddings improve the performance, making such a simple approach competitive with the state-of-the-art models that perform explicit on-task training of the graph embeddings. Furthermore, we ob- serve for the underlying BERT model an interesting power-law scaling behavior between the variance of the F1 score obtained for a relation class and its support in terms of training examples.

What Do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification

• Bassignana, Elisa andPlank, Barbara
• https://aclanthology.org/2022.acl-srw.7
• https://github.com/Kaleidophon/deep-significance
• Over the last five years, research on Relation Extraction (RE) witnessed extensive progress with many new dataset releases. At the same time, setup clarity has decreased, contributing to increased difficulty of reliable empirical evaluation (Taill’e et al., 2020). In this paper, we provide a comprehensive survey of RE datasets, and revisit the task definition and its adoption by the community. We find that cross-dataset and cross-domain setups are particularly lacking. We present an empirical study on scientific Relation Classification across two datasets. Despite large data overlap, our analysis reveals substantial discrepancies in annotation. Annotation discrepancies strongly impact Relation Classification performance, explaining large drops in cross-dataset evaluations. Variation within further sub-domains exists but impacts Relation Classification only to limited degrees. Overall, our study calls for more rigour in reporting setups in RE and evaluation across multiple test sets.

RFBFN: A Relation-First Blank Filling Network for Joint Relational Triple Extraction

• Li, Zhe and Fu, Luoyi and Wang, Xinbing and Zhang, Haisong and Zhou, Chenghu
• https://aclanthology.org/2022.acl-srw.2
• https://github.com/lizhe2016/RFBFN
• Joint relational triple extraction from unstructured text is an important task in information extraction. However, most existing works either ignore the semantic information of relations or predict subjects and objects sequentially. To address the issues, we introduce a new blank filling paradigm for the task, and propose a relation-first blank filling network (RFBFN). Specifically, we first detect potential relations maintained in the text to aid the following entity pair extraction. Then, we transform relations into relation templates with blanks which contain the fine-grained semantic representation of the relations. Finally, corresponding subjects and objects are extracted simultaneously by filling the blanks. We evaluate the proposed model on public benchmark datasets. Experimental results show our model outperforms current state-of-the-art methods. The source code of our work is available at: https://github.com/lizhe2016/RFBFN.

Simple and Effective Knowledge-Driven Query Expansion for {QA}-Based Product Attribute Extraction

• Shinzato, Keiji and Yoshinaga, Naoki and Xia, Yandi and Chen, Wei-Te
• https://aclanthology.org/2022.acl-short.25
• A key challenge in attribute value extraction (AVE) from e-commerce sites is how to handle a large number of attributes for diverse products. Although this challenge is partially addressed by a question answering (QA) approach which finds a value in product data for a given query (attribute), it does not work effectively for rare and ambiguous queries. We thus propose simple knowledge-driven query expansion based on possible answers (values) of a query (attribute) for QA-based AVE. We retrieve values of a query (attribute) from the training data to expand the query. We train a model with two tricks, knowledge dropout and knowledge token mixing, which mimic the imperfection of the value knowledge in testing. Experimental results on our cleaned version of AliExpress dataset show that our method improves the performance of AVE (+6.08 macro F1), especially for rare and ambiguous attributes (+7.82 and +6.86 macro F1, respectively).

Dis-ReX: A Multilingual Dataset for Distantly Supervised Relation Extraction

• Bhartiya, Abhyuday and Badola, Kartikeya and ., Mausam
• https://aclanthology.org/2022.acl-short.95
• https://github.com/dair-iitd/DiS-ReX
• Our goal is to study the novel task of distant supervision for multilingual relation extraction (Multi DS-RE). Research in Multi DS-RE has remained limited due to the absence of a reliable benchmarking dataset. The only available dataset for this task, RELX-Distant (Koksal and Ozgur, 2020), displays several unrealistic characteristics, leading to a systematic overestimation of model performance. To alleviate these concerns, we release a new benchmark dataset for the task, named DiS-ReX. We also modify the widely-used bag attention models using an mBERT encoder and provide the first baseline results on the proposed task. We show that DiS-ReX serves as a more challenging dataset than RELX-Distant, leaving ample room for future research in this domain.

Enhanced Multi-Channel Graph Convolutional Network for Aspect Sentiment Triplet Extraction

• Chen, Hao and Zhai, Zepeng and Feng, Fangxiang and Li, Ruifan and Wang, Xiaojie
• https://aclanthology.org/2022.acl-long.212
• https://github.com/ccchenhao997/emcgcn-aste
• Aspect Sentiment Triplet Extraction (ASTE) is an emerging sentiment analysis task. Most of the existing studies focus on devising a new tagging scheme that enables the model to extract the sentiment triplets in an end-to-end fashion. However, these methods ignore the relations between words for ASTE task. In this paper, we propose an Enhanced Multi-Channel Graph Convolutional Network model (EMC-GCN) to fully utilize the relations between words. Specifically, we first define ten types of relations for ASTE task, and then adopt a biaffine attention module to embed these relations as an adjacent tensor between words in a sentence. After that, our EMC-GCN transforms the sentence into a multi-channel graph by treating words and the relation adjacent tensor as nodes and edges, respectively. Thus, relation-aware node representations can be learnt. Furthermore, we consider diverse linguistic features to enhance our EMC-GCN model. Finally, we design an effective refining strategy on EMC-GCN for word-pair representation refinement, which considers the implicit results of aspect and opinion extraction when determining whether word pairs match or not. Extensive experimental results on the benchmark datasets demonstrate that the effectiveness and robustness of our proposed model, which outperforms state-of-the-art methods significantly.

Packed Levitated Marker for Entity and Relation Extraction

• Ye, Deming and Lin, Yankai and Li, Peng and Sun, Maosong
• https://aclanthology.org/2022.acl-long.337
• https://github.com/thunlp/PL-Marker
• Recent entity and relation extraction works focus on investigating how to obtain a better span representation from the pre-trained encoder. However, a major limitation of existing works is that they ignore the interrelation between spans (pairs). In this work, we propose a novel span representation approach, named Packed Levitated Markers (PL-Marker), to consider the interrelation between the spans (pairs) by strategically packing the markers in the encoder. In particular, we propose a neighborhood-oriented packing strategy, which considers the neighbor spans integrally to better model the entity boundary information. Furthermore, for those more complicated span pair classification tasks, we design a subject-oriented packing strategy, which packs each subject and all its objects to model the interrelation between the same-subject span pairs. The experimental results show that, with the enhanced marker feature, our model advances baselines on six NER benchmarks, and obtains a 4.1%-4.3% strict relation F1 improvement with higher speed over previous state-of-the-art models on ACE04 and ACE05. Our code and models are publicly available at https://github.com/thunlp/PL-Marker.

Pre-training to Match for Unified Low-shot Relation Extraction

• Liu, Fangchao and Lin, Hongyu and Han, Xianpei and Cao, Boxi and Sun, Le
• https://aclanthology.org/2022.acl-long.397
• https://github.com/fc-liu/mcmn
• Low-shot relation extraction (RE) aims to recognize novel relations with very few or even no samples, which is critical in real scenario application. Few-shot and zero-shot RE are two representative low-shot RE tasks, which seem to be with similar target but require totally different underlying abilities. In this paper, we propose Multi-Choice Matching Networks to unify low-shot relation extraction. To fill in the gap between zero-shot and few-shot RE, we propose the triplet-paraphrase meta-training, which leverages triplet paraphrase to pre-train zero-shot label matching ability and uses meta-learning paradigm to learn few-shot instance summarizing ability. Experimental results on three different low-shot RE tasks show that the proposed method outperforms strong baselines by a large margin, and achieve the best performance on few-shot RE leaderboard.

Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction

• Jie, Zhanming and Li, Jierui and Lu, Wei
• https://aclanthology.org/2022.acl-long.410
• https://github.com/allanj/deductive-mwp
• Solving math word problems requires deductive reasoning over the quantities in the text. Various recent research efforts mostly relied on sequence-to-sequence or sequence-to-tree models to generate mathematical expressions without explicitly performing relational reasoning between quantities in the given context. While empirically effective, such approaches typically do not provide explanations for the generated expressions. In this work, we view the task as a complex relation extraction problem, proposing a novel approach that presents explainable deductive reasoning steps to iteratively construct target expressions, where each step involves a primitive operation over two quantities defining their relation. Through extensive experiments on four benchmark datasets, we show that the proposed model significantly outperforms existing strong baselines. We further demonstrate that the deductive procedure not only presents more explainable steps but also enables us to make more accurate predictions on questions that require more complex reasoning.

MILIE: Modular & Iterative Multilingual Open Information Extraction

• Kotnis, Bhushan and Gashteovski, Kiril and Rubio, Daniel and Shaker, Ammar and Rodriguez-Tembras, Vanesa and Takamoto, Makoto and Niepert, Mathias and Lawrence, Carolin
• https://aclanthology.org/2022.acl-long.478
• Open Information Extraction (OpenIE) is the task of extracting (subject, predicate, object) triples from natural language sentences. Current OpenIE systems extract all triple slots independently. In contrast, we explore the hypothesis that it may be beneficial to extract triple slots iteratively: first extract easy slots, followed by the difficult ones by conditioning on the easy slots, and therefore achieve a better overall extraction.Based on this hypothesis, we propose a neural OpenIE system, MILIE, that operates in an iterative fashion. Due to the iterative nature, the system is also modularit is possible to seamlessly integrate rule based extraction systems with a neural end-to-end system, thereby allowing rule based systems to supply extraction slots which MILIE can leverage for extracting the remaining slots. We confirm our hypothesis empirically: MILIE outperforms SOTA systems on multiple languages ranging from Chinese to Arabic. Additionally, we are the first to provide an OpenIE test dataset for Arabic and Galician.

命名实体识别

Extracting Person Names from User Generated Text: Named-Entity Recognition for Combating Human Trafficking

• Li, Yifei and Nair, Pratheeksha and Pelrine, Kellin and Rabbany, Reihaneh
• https://aclanthology.org/2022.findings-acl.225
• https://github.com/tudou0002/NEAT
• Online escort advertisement websites are widely used for advertising victims of human trafficking. Domain experts agree that advertising multiple people in the same ad is a strong indicator of trafficking. Thus, extracting person names from the text of these ads can provide valuable clues for further analysis. However, Named-Entity Recognition (NER) on escort ads is challenging because the text can be noisy, colloquial and often lacking proper grammar and punctuation. Most existing state-of-the-art NER models fail to demonstrate satisfactory performance in this task. In this paper, we propose NEAT (Name Extraction Against Trafficking) for extracting person names. It effectively combines classic rule-based and dictionary extractors with a contextualized language model to capture ambiguous names (e.g penny, hazel) and adapts to adversarial changes in the text by expanding its dictionary. NEAT shows 19% improvement on average in the F1 classification score for name extraction compared to previous state-of-the-art in two domain-specific datasets.

Extract-Select: A Span Selection Framework for Nested Named Entity Recognition with Generative Adversarial Training

• Huang, Peixin and Zhao, Xiang and Hu, Minghao and Fang, Yang and Li, Xinyi and Xiao, Weidong
• https://aclanthology.org/2022.findings-acl.9
• Nested named entity recognition (NER) is a task in which named entities may overlap with each other. Span-based approaches regard nested NER as a two-stage span enumeration and classification task, thus having the innate ability to handle this task. However, they face the problems of error propagation, ignorance of span boundary, difficulty in long entity recognition and requirement on large-scale annotated data. In this paper, we propose Extract-Select, a span selection framework for nested NER, to tackle these problems. Firstly, we introduce a span selection framework in which nested entities with different input categories would be separately extracted by the extractor, thus naturally avoiding error propagation in two-stage span-based approaches. In the inference phase, the trained extractor selects final results specific to the given entity category. Secondly, we propose a hybrid selection strategy in the extractor, which not only makes full use of span boundary but also improves the ability of long entity recognition. Thirdly, we design a discriminator to evaluate the extraction result, and train both extractor and discriminator with generative adversarial training (GAT). The use of GAT greatly alleviates the stress on the dataset size. Experimental results on four benchmark datasets demonstrate that Extract-Select outperforms competitive nested NER models, obtaining state-of-the-art results. The proposed model also performs well when less labeled data are given, proving the effectiveness of GAT.

关键词抽取

MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction

• Zhang, Linhan and Chen, Qian and Wang, Wen and Deng, Chong and Zhang, ShiLiang and Li, Bing and Wang, Wei and Cao, Xin
• https://aclanthology.org/2022.findings-acl.34
• https://github.com/linhanz/mderank
• Keyphrase extraction (KPE) automatically extracts phrases in a document that provide a concise summary of the core content, which benefits downstream information retrieval and NLP tasks. Previous state-of-the-art methods select candidate keyphrases based on the similarity between learned representations of the candidates and the document. They suffer performance degradation on long documents due to discrepancy between sequence lengths which causes mismatch between representations of keyphrase candidates and the document. In this work, we propose a novel unsupervised embedding-based KPE approach, Masked Document Embedding Rank (MDERank), to address this problem by leveraging a mask strategy and ranking candidates by the similarity between embeddings of the source document and the masked document. We further develop a KPE-oriented BERT (KPEBERT) model by proposing a novel self-supervised contrastive learning method, which is more compatible to MDERank than vanilla BERT. Comprehensive evaluations on six KPE benchmarks demonstrate that the proposed MDERank outperforms state-of-the-art unsupervised KPE approach by average 1.80 $F1@15$ improvement. MDERank further benefits from KPEBERT and overall achieves average 3.53 $F1@15$ improvement over SIFRank."

最近工作