AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频


pub
生成解读视频

AI 溯源

AI解析本论文相关学术脉络


Master Reading Tree
生成 溯源树

AI 精读

AI抽取本论文的概要总结


微博一下
We have introduced Synset Relation-Enhanced Framework, a synset relationenhanced framework with a try-again mechanism that takes into account WordNet relations and augments WordNet glosses with mentions from the web under simple hypotheses and rules

A Synset Relation enhanced Framework with a Try again Mechanism for Word Sense Disambiguation

EMNLP 2020, pp.6229-6240, (2020)

被引用0|浏览161
下载 PDF 全文
引用
微博一下

摘要

Contextual embeddings are proved to be overwhelmingly effective to the task of Word Sense Disambiguation (WSD) compared with other sense representation techniques. However, these embeddings fail to embed sense knowledge in semantic networks. In this paper, we propose a Synset Relation-Enhanced Framework (SREF) that leverages sense relatio...更多

代码

数据

0
简介
  • Word Sense Disambiguation (WSD) is an ongoing research area in Natural Language Processing community.
  • According to Navigli (2009), most of WSD solutions can be categorized into supervised and knowledge-based approaches
  • For supervised systems, they rely on sense-annotated data to train either word experts (Zhong and Ng, 2010) or a neural language model (Raganato et al, 2017a) for disambiguation and perform better than their.
  • There is much space to explore regarding how to better exploit knowledge in a sense inventory such as different WordNet relations and super-sense that categorizes WordNet senses into 45 clusters
重点内容
  • Word Sense Disambiguation (WSD) is an ongoing research area in Natural Language Processing community
  • We demonstrate how the number of labeled sentences in SemCor affects the performance of SREFsup and LMMS
  • We have introduced Synset Relation-Enhanced Framework (SREF), a synset relationenhanced framework with a try-again mechanism that takes into account WordNet relations and augments WordNet glosses with mentions from the web under simple hypotheses and rules
  • Empirical experiments have proved the effectiveness of SREF from both knowledgebased and supervised perspectives, obtaining major and minor improvements over previous state-of-the-art performance, respectively
  • We intend to scale SREFkb to a multilingual version and explore the possibilities of using the multilingual WordNet so that abundant knowledge regarding English can be transferred to other languages
  • When applying the proposed strategy to tackle WSD, our system achieves state-of-the-art performance among knowledge-based systems
  • It is worth investigating regarding how to better incorporate sense embedding into other downstream tasks
方法
  • Figure 1 demonstrates the overall concept of the framework without the try-again mechanism using an example
  • It relies on a K-NN algorithm to predict the correct sense of each word under disambiguation.
  • (1) The words in the linguistic explanation of a synset tend to be less ambiguous and are often skewed to MFS/WordNet 1st sense
  • This is supported by the fact that more than 75% of the WordNet gloss words are labeled as MFS in the Princeton WordNet Gloss Corpus (Mihalcea and Moldovan, 2001)
结果
  • An ablation study is first implemented to illustrate how the proposed factors contribute to the final WSD performance and a test set example is given regarding the tryagain mechanism.
  • This has revealed the potential of such a fine-grained WordNet gloss utilization, and the employment of more valuable resources such as Wikipedia rather than web mentions for further investigation
  • Another noteworthy observation is that the sense embedding enhancement damages adverb disambiguation performance
结论
  • The authors have introduced SREF, a synset relationenhanced framework with a try-again mechanism that takes into account WordNet relations and augments WordNet glosses with mentions from the web under simple hypotheses and rules.
  • The authors intend to scale SREFkb to a multilingual version and explore the possibilities of using the multilingual WordNet so that abundant knowledge regarding English can be transferred to other languages.
  • It is worth investigating regarding how to better incorporate sense embedding into other downstream tasks
总结
  • Introduction:

    Word Sense Disambiguation (WSD) is an ongoing research area in Natural Language Processing community.
  • According to Navigli (2009), most of WSD solutions can be categorized into supervised and knowledge-based approaches
  • For supervised systems, they rely on sense-annotated data to train either word experts (Zhong and Ng, 2010) or a neural language model (Raganato et al, 2017a) for disambiguation and perform better than their.
  • There is much space to explore regarding how to better exploit knowledge in a sense inventory such as different WordNet relations and super-sense that categorizes WordNet senses into 45 clusters
  • Methods:

    Figure 1 demonstrates the overall concept of the framework without the try-again mechanism using an example
  • It relies on a K-NN algorithm to predict the correct sense of each word under disambiguation.
  • (1) The words in the linguistic explanation of a synset tend to be less ambiguous and are often skewed to MFS/WordNet 1st sense
  • This is supported by the fact that more than 75% of the WordNet gloss words are labeled as MFS in the Princeton WordNet Gloss Corpus (Mihalcea and Moldovan, 2001)
  • Results:

    An ablation study is first implemented to illustrate how the proposed factors contribute to the final WSD performance and a test set example is given regarding the tryagain mechanism.
  • This has revealed the potential of such a fine-grained WordNet gloss utilization, and the employment of more valuable resources such as Wikipedia rather than web mentions for further investigation
  • Another noteworthy observation is that the sense embedding enhancement damages adverb disambiguation performance
  • Conclusion:

    The authors have introduced SREF, a synset relationenhanced framework with a try-again mechanism that takes into account WordNet relations and augments WordNet glosses with mentions from the web under simple hypotheses and rules.
  • The authors intend to scale SREFkb to a multilingual version and explore the possibilities of using the multilingual WordNet so that abundant knowledge regarding English can be transferred to other languages.
  • It is worth investigating regarding how to better incorporate sense embedding into other downstream tasks
表格
  • Table1: Wordnet Synset Gloss Length (Number of Gloss Words per Synset) and Lemma Ambiguity (Number of Synsets per Lemma) in Different POS
  • Table2: Query Examples for Some Glosses
  • Table3: Ablation Study on ALL (F1-%)
  • Table4: F1-% Performance on all-words WSD datasets, * represents those performance obtained (partially) as a development set. † denotes the systems that make use of the prior knowledge of MFS for unseen lemmas during testing. ‡ are systems proposed after this paper was submitted. Bold and underlined figures indicate the current (submission time) and previous state-of-the-art performance on the evaluation framework, respectively
  • Table5: Performance on Lexical Sample Datasets on standard WSD datasets separately (SE2, SE3, SE07, SE13, and SE15) and on their combined dataset (ALL). It has also shown those systems’ performance on ‘ALL’ from POS perspectives
  • Table6: Performance on MFS and LFS against the ‘ALL’ dataset, where senses are partitioned into MFS and LFS according to their rank in WordNet
  • Table7: Performance on Similarity-based Tasks
Download tables as Excel
相关工作
  • In order to tackle WSD, approaches in two streams have been well developed over the last few decades, namely supervised and knowledgebased approaches. Their major difference is whether a sense-annotated corpus is employed.

    2.1 Supervised Systems

    Supervised systems originally regard WSD as a sense classification problem, building one classifier for each target word. IMS (Zhong and Ng, 2010), among others (Tsatsaronis et al, 2007, Iacobacci et al, 2016, Papandrea et al, 2017), is the most widespread system that leverages SVM to classify senses. In recent years, a more efficient supervised scheme has been proposed. Rather than training a few classifiers, it constructs a single neural architecture (Raganato et al, 2017a) with an annotated corpus and disambiguates words based on the output of the last layer. These methods have not outperformed traditional counterparts until sense definitions were incorporated (Luo et al, 2018). It has also become a trend that newly proposed systems (Kumar et al, 2019; Huang et al, 2019; Loureiro and Jorge, 2019; Vial et al, 2019; Scarlini et al, 2020) tend to exploit WordNet sense knowledge one way or another.
基金
  • This work was supported by the National Natural Science Foundation of China (under Project No 61375053) and the graduate innovation fund of Shanghai University of Finance and Economics (under Project No CXJJ-2019-395)
研究对象与分析
standard all-words WSD datasets: 5
In this section, we evaluate our system using the evaluation framework provided by Raganato et al (2017b). This framework includes five standard all-words WSD datasets: SensEval-2 (SE2, Palmer et al, 2001), SensEval-3 (SE3, Snyder and Palmer, 2004), SemEval-2007 (SE07, Pradhan et al, 2007), SemEval-2013 (SE13, Navigli et al, 2013) and SemEval-2015 (SE15, Moro and Navigli, 2015). We also show how our system performs on lexical sample datasets including SensEval-2 (SE2-LS, Kilgarriff, 2001) and SensEval-3 (SE3-LS, Mihalcea et al, 2004)

引用论文
  • Eneko Agirre, Oier López de Lacalle, and Aitor Soroa. 2014. Random walks for knowledge-based word sense disambiguation. Computational Linguistics, 40(1):57-84.
    Google ScholarLocate open access versionFindings
  • Eneko Agirre, Oier López de Lacalle, and Aitor Soroa. 2018. The risk of sub-optimal use of Open Source NLP Software: UKB is inadvert-ently state-of-theart in knowledge-based WSD. In Proceedings of Workshop for NLP Open Source Software, pages 29-33, Melbourne, Australia: Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Satanjeev Banerjee and Ted Pedersen. 2002. An adapted Lesk algorithm for word sense disambiguation using wordnet. In International conference on intelligent text processing and computational linguistics, pages 136-145. Springer.
    Google ScholarLocate open access versionFindings
  • Pierpaolo Basile, Annalina Caputo, and Giovanni Semeraro. 201An enhanced Lesk word sense disambiguation algorithm through a distributional semantic model. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pages 1591-1600, Dublin, Ireland. Dublin City University and Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Michele Bevilacqua and Roberto Navigli. 2020. Breaking Through the 80% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2854-2864. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Sudha Bhingardive, Dhirendra Singh, Rudra Murthy V, Hanumant Redkar and Pushpak Bhattacharyya. 2015. Unsupervised most frequent sense detection using word embeddings. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1238-1243, Denver, Colorado, Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Terra Blevins and Luke Zettlemoyer. 2020. Moving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1006-101Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Jose Camacho-Collados, Mohammad Taher Pilehvar, and Roberto Navigli. 2016. Nasari: Integrating explicit knowledge and corpus statistics for a multilingual representation of concepts and entities. Artificial Intelligence, 240:36-64.
    Google ScholarLocate open access versionFindings
  • Daniel Cer, Mona Diab, Eneko Agirre, Iñigo LopezGazpio, Lucia Specia. 2017. SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation. In Proceedings of the SemEval workshop at ACL 2017, pages 1-14.
    Google ScholarLocate open access versionFindings
  • Devendra Singh Chaplot and Ruslan Salakhutdinov. 2018. Knowledge-based word sense disambiguation using topic models. In Thirty-Second AAAI Conference on Artificial Intelligence.
    Google ScholarLocate open access versionFindings
  • Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171-4186, Minneapolis, Minnesota. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Christian Hadiwinoto, Hwee Tou Ng and Wee Chung Gan. Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations. In EMNLP-IJCNLP 2019, pages 3507-3512, Hong Kong, China.
    Google ScholarLocate open access versionFindings
  • Luyao Huang, Chi Sun, Xipeng Qiu and Xuanjing Huang. GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3507-3512, Hong Kong, China, Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Ignacio Iacobacci, Mohammad Taher Pilehvar, and Roberto Navigli. 2016. Embeddings for word sense disambiguation: An evaluation study. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 897-907, Berlin, Germany. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Adam Kilgarriff. 2001. English lexical sample task description. In Proceedings of SENSEVAL-2 Second International Workshop on Evaluating Word Sense Disambiguation Systems, pages 17–20, Toulouse,France.
    Google ScholarLocate open access versionFindings
  • Sawan Kumar, Sharmistha Jat, Karan Saxena and Partha Talukdar. 2019. Zero-shot Word Sense Disambiguation using Sense Definition Embeddings. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5670-5681, Florence, Italy. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Michael Lesk. 1986. Automatic sense disambiguation using machine readable dictionaries: How to tell a pine cone from an ice cream cone. In Proceedings of the 5th Annual International Conference on Systems Documentation, SIGDOC ’86, pages 2426, New York, NY, USA. ACM.
    Google ScholarLocate open access versionFindings
  • Daniel Loureiro and Alípio Mário Jorge. 2019. Language modelling makes sense: Propagating representations through WordNet for full coverage word sense disambiguation. In Proceedings of the 57th Annual Meeting of the Association for
    Google ScholarLocate open access versionFindings
  • Computational Linguistics, pages 5682-5691, Florence, Italy. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Fuli Luo, Tianyu Liu, Qiaolin Xia, Baobao Chang, and Zhifang Sui. 2018. Incorporating glosses into neural word sense disambiguation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2473-2482, Melbourne, Australia. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Diana McCarthy, Rob Koeling, Julie Weeds, and John Carroll. 2007. Unsupervised acquisition of predominant word senses. Computational Linguistics, 33(4):553-590.
    Google ScholarLocate open access versionFindings
  • Oren Melamud, Jacob Goldberger, and Ido Dagan. 2016. context2vec: Learning generic context embedding with bidirectional LSTM. In Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning, pages 51-61.
    Google ScholarLocate open access versionFindings
  • Rada Mihalcea and Dan I. Moldovan. 2001. Extended wordNet: progress report. In Proceedings of NAACL Workshop on WordNet and Other Lexical Resources, pages 95-100.
    Google ScholarLocate open access versionFindings
  • Rada Mihalcea, Timothy Chklovski, and Adam Kilgarriff. 2004. The senseval-3 English lexical sample task. In Proceedings of SENSEVAL-3, the Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text, pages 25– 28, Barcelona, Spain.
    Google ScholarLocate open access versionFindings
  • George A. Miller, Martin Chodorow, Shari Landes, Claudia Leacock, and Robert G. Thomas. 1994. Using a semantic concordance for sense identification. In HUMAN LANGUAGE TECHNOLOGY: Proceedings of a Workshop held at Plainsboro, New Jersey, March 8-11, 1994.
    Google ScholarLocate open access versionFindings
  • George A. Miller. 1995. WordNet: a lexical database for English. Communications of the ACM, 41(2): 39-41.
    Google ScholarLocate open access versionFindings
  • Tristan Miller and Iryna Gurevych. 2015. Automatic disambiguation of English puns. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (ACL–IJCNLP 2015), pages 719-729, Beijing, China. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Tristan Miller, Chris Biemann, Torsten Zesch, Iryna Gurevych. 2012. Using Distributional Similarity for Lexical Expansion in Knowledge-based Word Sense Disambiguation. In Proceedings of COLING 2012, pages 1781-1796, Mumbai, India. The COLING 2012 Organizing Committee.
    Google ScholarLocate open access versionFindings
  • Andrea Moro and Roberto Navigli. 2015. SemEval-
    Google ScholarFindings
  • 2015 task 13: Multilingual all-words sense disambiguation and entity linking. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 288-297, Denver, Colorado. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Andrea Moro, Alessandro Raganato, and Roberto Navigli. 2014. Entity linking meets word sense disambiguation: a unified approach. Transactions of the Association for Computational Linguistics, 2:231-244.
    Google ScholarLocate open access versionFindings
  • Preslav Nakov, Doris Hoogeveen, Lluís Màrquez, Alessandro Moschitti, Hamdy Mubarak, Timothy Baldwin, Karin Verspoor. 2017. SemEval-2017 Task 3: Community Question Answering. In Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017), pages 27-48.
    Google ScholarLocate open access versionFindings
  • Roberto Navigli, David Jurgens, and Daniele Vannella. 2013. SemEval-2013 task 12: Multilingual word sense disambiguation. In Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013), pages 222-231, Atlanta, Georgia, USA. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Roberto Navigli. 2009. Word sense disambiguation: A survey. ACM Computing Surveys, 41(2):10:110:69.
    Google ScholarLocate open access versionFindings
  • Martha Palmer, Christiane Fellbaum, Scott Cotton, Lauren Delfs, and Hoa Trang Dang. 2001. English tasks: All-words and verb lexical sample. In Proceedings of SENSEVAL-2 Second International Workshop on Evaluating Word Sense Disambiguation Systems, pages 21-24, Toulouse, France. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Simone Papandrea, Alessandro Raganato and Claudio Delli Bovi. 2017. SupWSD: A Flexible Toolkit for Supervised Word Sense Disambiguation. In Proceedings of the EMNLP 2017 System Demonstrations. pages 103-108, Copenhagen, Denmark, Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Matthew Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 2227-2237, New Orleans, Louisiana. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Simone Paolo Ponzetto and Roberto Navigli. 2010. Knowledge-rich Word Sense Disambiguation Rivaling Supervised Systems. In Proceedings of the 48th Annual Meeting of the Association for
    Google ScholarLocate open access versionFindings
  • Computational Linguistics, pages 1522-1531, Uppsala, Sweden. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Sameer Pradhan, Edward Loper, Dmitriy Dligach, and Martha Palmer. 2007. SemEval-2007 task-17: English lexical sample, SRL and all words. In Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval-2007), pages 87-92, Prague, Czech Republic. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Alessandro Raganato, Claudio Delli Bovi, and Roberto Navigli. 2017a. Neural sequence learning models for word sense disambiguation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1156-1167, Copenhagen, Denmark. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Alessandro Raganato, Jose Camacho-Collados, and Roberto Navigli. 2017b. Word sense disambiguation: A unified evaluation framework and empirical comparison. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 99-110, Valencia, Spain. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Bianca Scarlini, Tommaso Pasini, Roberto Navigli. 2020. SENSEMBERT: Context-Enhanced Sense Embeddings for Multilingual Word Sense Disambiguation. In Thirty-fourth AAAI Conference on Artificial Intelligence.
    Google ScholarLocate open access versionFindings
  • Benjamin Snyder and Martha Palmer. 2004. The English all-words task. In Senseval-3: Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text, pages 41-43, Barcelona, Spain. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • George Tsatsaronis, Michalis Vazirgiannis and Ion Androutsopoulos. 2007. Word Sense Disambiguation with Spreading Activation Networks Generated from Thesauri. In Proceedings of the 20th International Joint Conference on Artificial Intelligence, pages 17251730, Hyderabad, India.
    Google ScholarLocate open access versionFindings
  • Loïc Vial, Benjamin Lecouteux and Didier Schwab. Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation. In proceedings of the 10th Global WordNet Conference.
    Google ScholarLocate open access versionFindings
  • Loïc Vial, Benjamin Lecouteux, and Didier Schwab. 2018. UFSAC: Unification of Sense Annotated Corpora and Tools. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan.
    Google ScholarLocate open access versionFindings
  • Yinglin Wang, Ming Wang and Hamido Fujita. 2020. Word Sense Disambiguation: A Comprehensive Knowledge Exploitation Framework. KnowledgeBased Systems, 10530.
    Google ScholarLocate open access versionFindings
  • Gregor Wiedemann, Steffen Remus, Avi Chawla and Chris Biemann. Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings. In KONVENS 2019.
    Google ScholarLocate open access versionFindings
  • Zhi Zhong and Hwee Tou Ng. 2010. It makes sense: A wide-coverage word sense disambiguation system for free text. In Proceedings of the ACL 2010 System Demonstrations, pages 78-83, Uppsala, Sweden. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
作者
Ming Wang
Ming Wang
Yinglin Wang
Yinglin Wang
您的评分 :
0

 

标签
评论
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科