Omnia Mutantur, Nihil Interit: Connecting Past with Present by Finding Corresponding Terms across Time

In the current fast-paced world, people tend to possess limited knowledge about things from the past. For example, some young users may not know that Walkman played similar function as iPod does nowadays. In this paper, we approach the temporal correspondence problem in which, given an input term (e.g., iPod) and the target time (e.g. 1980s), the task is to find the counterpart of the query that existed in the target time. We propose an approach that transforms word contexts across time based on their neural network representations. We then experimentally demonstrate the effectiveness of our method on the New York Times Annotated Corpus.

[1]  John Blitzer,et al.  Domain Adaptation with Structural Correspondence Learning , 2006, EMNLP.

[2]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[3]  Geoffrey Hughes,et al.  Words in time: A Social History of the English Vocabulary , 1989 .

[4]  Wei Gao,et al.  Learning to rank only using training data from related domain , 2010, SIGIR.

[5]  Gerhard Weikum,et al.  Incorporating terminology evolution for query translation in text retrieval with association rules , 2010, CIKM '10.

[6]  Wei Gao,et al.  Relevant knowledge helps in choosing right teacher: active query selection for ranking adaptation , 2011, SIGIR.

[7]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[8]  Katsumi Tanaka,et al.  High-speed Detection of Ontological Knowledge and Bi-directional Lexico-Syntactic Patterns from the Web , 2010, J. Softw..

[9]  Wei Fan,et al.  Heterogeneous cross domain ranking in latent space , 2009, CIKM.

[10]  Steven Skiena,et al.  Statistically Significant Detection of Linguistic Change , 2014, WWW.

[11]  Slav Petrov,et al.  Temporal Analysis of Language through Neural Language Models , 2014, LTCSS@ACL.

[12]  J. Aitchison.  Language Change: Progress or Decay? , 1981 .

[13]  Katsumi Tanaka,et al.  Content-based retrieval for heterogeneous domains: domain adaptation by relative aggregation points , 2012, SIGIR '12.

[14]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[15]  Erez Lieberman,et al.  Quantifying the evolutionary dynamics of language , 2007, Nature.

[16]  Rada Mihalcea,et al.  Word Epoch Disambiguation: Finding How Words Change Over Time , 2012, ACL.

[17]  Qiang Yang,et al.  Topic-bridged PLSA for cross-domain text classification , 2008, SIGIR '08.

[18]  M. Pagel,et al.  Frequency of word-use predicts rates of lexical evolution throughout Indo-European history , 2007, Nature.

[19]  Gerhard Weikum,et al.  Bridging the Terminology Gap in Web Archive Search , 2009, WebDB.

[20]  Susan T. Dumais,et al.  Improving information retrieval using latent semantic indexing , 1988 .

[21]  Quoc V. Le,et al.  Exploiting Similarities among Languages for Machine Translation , 2013, ArXiv.

[22]  Kevin Duh,et al.  A framework for analyzing semantic change of words across time , 2014, IEEE/ACM Joint Conference on Digital Libraries.

[23]  Jules D. Gliesche.  Review of Principles of Linguistic Change: Social factors , 2005 .

[24]  Feiping Nie,et al.  Cross-language web page classification via dual knowledge transfer using nonnegative matrix tri-factorization , 2011, SIGIR.

[25]  George Karypis,et al.  A Comparison of Document Clustering Techniques , 2000 .

[26]  Kjetil Nørvåg,et al.  Exploiting time-based synonyms in searching document archives , 2010, JCDL '10.

[27]  Thomas Risse,et al.  NEER: An Unsupervised Method for Named Entity Evolution Recognition , 2012, COLING.

[28]  Qiang Yang,et al.  Spectral domain-transfer learning , 2008, KDD.

[29]  John Blitzer,et al.  Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification , 2007, ACL.