非監督式語意表徵的強化學習方法

Unsupervised Sense Representation by Reinforcement Learning

李廣和(Guang-He Lee)

指導教授 ： 陳縕儂

國立臺灣大學/電機資訊學院/資訊工程學研究所/碩士(2017年)

https://doi.org/10.6342/NTU201701669

摘要

本論文嘗試以非監督式的方法解決語意混淆問題，其語意表徵的學習必須建立在有情景的語意選擇功能之下。過往在學習語意表徵的研究多半無法兼顧表徵學習的精細度與語意選擇的效率性。本論文提出了一個模組化的架構，支持靈活的模組來優化各自的目標：一模組選擇詞對應之語意，另一模組針對選到的語意來學習表徵向量，因此達成第一個支持線性語意選擇功能的純語意階層表徵學習模型。對比於傳統的架構，我們使用了加強學習來達成了以下三種好處。一、加強學習的決策架構比起機率與分群更能描述人在選擇語意的機制；二、我們藉由加強學習的方法，提出了在模組化架構底下第一個能只用單一目標函數的非監督式語意表徵模型；三、我們更在語意選擇中引入了加強學習中多元的探索功能來增加穩健性。在基準資料集的實驗結果顯示出本論文的方法在同義字選擇與(最高餘弦相似度的)情景字相似性的實驗中都超越了最先進的方法。

關鍵字

非監督式語意表徵 ； 表徵學習 ； 加強學習

並列摘要

This paper proposes to address the word sense ambiguity issue in an unsupervised manner, where word sense representations are learned along a word sense selection mechanism given contexts. Prior work about learning sense embeddings suffered from either coarse-grained representation learning or inefficient sense selection. The proposed modular framework implements flexible modules to optimize distinct mechanisms: sense selection and representation learning, achieving the first purely sense-level representation learning system with linear-time sense selection. In contrast to conventional methods, we leverage reinforcement learning as the learning algorithm, which exhibits the following advantages. First, the decision making process under reinforcement learning better captures the sense selection mechanism than probabilistic and clustering methods. Second, our reinforcement learning algorithm realizes the first single objective function for modular unsupervised sense representation systems. Finally, we introduce various exploration techniques under reinforcement learning on sense selection to enhance robustness. The experiments on benchmark data show that the proposed approach achieves the state-of-the-art performance on synonym selection as well as on contextual word similarities in terms of MaxSimC.

並列關鍵字

Unsupervised Sense Representation ； Representation Learning ； Reinforcement Learning

參考文獻

[1] S. Wold, K. Esbensen, and P. Geladi, “Principal component analysis,” Chemometrics and intelligent laboratory systems, vol. 2, no. 1-3, pp. 37–52, 1987.

[3] T. K. Landauer, Latent semantic analysis. Wiley Online Library, 2006.

[5] J. Pennington, R. Socher, and C. D. Manning, “Glove: Global vectors for word representation.,” vol. 14, pp. 1532–1543, 2014.

[14] N.-Q. Pham, G. Kruszewski, and G. Boleda, “Convolutional neural network language models,” in Proc. of EMNLP, 2016.

[15] T. Mikolov, M. Karafiát, L. Burget, J. Cernockỳ, and S. Khudanpur, “Recurrent neural network based language model.,” in Interspeech, vol. 2, p. 3, 2010.