Learning to Author Text with textual CBR

Textual reuse is an integral part of textual case-based reasoning (TCBR) which deals with solving new problems by reusing previous similar problem-solving experiences documented as text. We investigate the role of text reuse for text authoring applications that involve feedback or review generation. Generally providing feedback in the form of assigning a rating from a likert scale is far easier compared to articulating explanatory feedback as text. When previous feedback generated about the same or similar objects are maintained as cases, there is opportunity for knowledge reuse. In this paper, we show how compositional and transformational adaptation techniques can be applied once sentences in a given case are aligned to relevant structured attribute values. Three text reuse algorithms are introduced and evaluated on a dataset gathered from online Hotel reviews from TripAdvisor. Here cases consists of both structured sub-rating attributes together with textual feedback. Generally, aligned sentences linked to similar sub-rating values are clustered together and prototypical sentences are then extracted to enable reuse across similar authors. Experiments show a close similarity between our proposed texts and actual human edited review text. We also found that problems with variability in vocabulary are best addressed when prototypes are formulated from larger sets of similar sentences in contrast to smaller sets from local neighbourhoods.

[1]  Aidan Waugh,et al.  Using Experience on the Read/Write Web: The GhostWriter System , 2009 .

[2]  B. Díaz-Agudo,et al.  Textual CBR in jCOLIBRI : From Retrieval to Reuse ? , 2007 .

[3]  Kevin D. Ashley,et al.  Evaluation of Textual CBR Approaches , 1998 .

[4]  Balaraman Ravindran,et al.  Lexical Chains as Document Features , 2008, IJCNLP.

[5]  Susan Craw,et al.  Learning adaptation knowledge to improve case-based reasoning , 2006, Artif. Intell..

[6]  Pedro A. González-Calero,et al.  Building CBR systems with jcolibri , 2007, Sci. Comput. Program..

[7]  Ding-Wei Wang,et al.  Research on case adaptation techniques in case-based reasoning , 2004, Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).

[8]  Pedro A. González-Calero,et al.  A Substitution-based Adaptation Model , 1999, ICCBR Workshops.

[9]  Kevin D. Ashley,et al.  Textual case-based reasoning , 2005, Knowl. Eng. Rev..

[10]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[11]  Sutanu Chakraborti,et al.  Evaluation Measures for TCBR Systems , 2008, ECCBR.

[12]  Luc Lamontagne,et al.  Textual Reuse for Email Response , 2004, ECCBR.

[13]  Enric Plaza,et al.  Constructive Adaptation , 2002, ECCBR.

[14]  Luc Lamontagne,et al.  Case Retrieval Reuse Net (CR2N): An Architecture for Reuse of Textual Solutions , 2009, ICCBR.

[15]  Kevin D. Ashley,et al.  Reasoning with Textual Cases , 2005, ICCBR.

[16]  Enric Plaza,et al.  Semantics and Experience in the Future Web , 2008, ECCBR.

[17]  Nirmalie Wiratunga,et al.  Solution reuse for textual cases , 2008 .

[18]  Ralph Bergmann,et al.  Techniques and Knowledge Used for Adaptation During Case-Based Problem Solving , 1998, IEA/AIE.

[19]  Somayajulu Sripada,et al.  SUMTIME-METEO: Parallel Corpus of Naturally Occurring Forecast Texts and Weather Data , 2008 .

[20]  Pedro A. González-Calero,et al.  Modelling the CBR Life Cycle Using Description Logics , 1999, ICCBR.

[21]  Luc Lamontagne,et al.  Applying Case-Based Reasoning to Email Response , 2003, ICEIS.

[22]  Mario Lenz,et al.  Case Retrieval Nets: Basic Ideas and Extensions , 1996, KI.

[23]  Raquel Hervás,et al.  Story plot generation based on CBR , 2004, Knowl. Based Syst..

[24]  Agnar Aamodt,et al.  Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches , 1994, AI Commun..

[25]  Sutanu Chakraborti,et al.  Fast Case Retrieval Nets for Textual Data , 2006, ECCBR.

[26]  Stewart Massie,et al.  From Anomaly Reports to Cases , 2007, ICCBR.