תקציר
This paper empirically studies the effects of representation choices on neural sentiment analysis for Modern Hebrew, a morphologically rich language (MRL) for which no sentiment analyzer currently exists. We study two dimensions of representational choices: (i) the granularity of the input signal (token-based vs. morpheme-based), and (ii) the level of encoding of vocabulary items (string-based vs. character-based). We hypothesise that for MRLs, languages where multiple meaning-bearing elements may be carried by a single space-delimited token, these choices will have measurable effects on task perfromance, and that these effects may vary for different architectural designs: fully-connected, convolutional or recurrent. Specifically, we hypothesize that morpheme-based representations will have advantages in terms of their generalization capacity and task accuracy, due to their better OOV coverage. To empirically study these effects, we develop a new sentiment analysis benchmark for Hebrew, based on 12K social media comments, and provide two instances thereof: token-based and morpheme-based. Our experiments show that the effect of representational choices vary with architectural types. While fully-connected and convolutional networks slightly prefer token-based settings, RNNs benefit from a morpheme-based representation, in accord with the hypothesis that explicit morphological information may help generalize. Our endeavor also delivers the first state-of-the-art broad-coverage sentiment analyzer for Hebrew, with over 89% accuracy, alongside an established benchmark to further study the effects of linguistic representation choices on neural networks’ task performance.
שפה מקורית | אנגלית |
---|---|
כותר פרסום המארח | COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings |
עורכים | Emily M. Bender, Leon Derczynski, Pierre Isabelle |
מוציא לאור | Association for Computational Linguistics (ACL) |
עמודים | 2242-2252 |
מספר עמודים | 11 |
מסת"ב (אלקטרוני) | 9781948087506 |
סטטוס פרסום | פורסם - 2018 |
אירוע | 27th International Conference on Computational Linguistics, COLING 2018 - Santa Fe, ארצות הברית משך הזמן: 20 אוג׳ 2018 → 26 אוג׳ 2018 |
סדרות פרסומים
שם | COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings |
---|
כנס
כנס | 27th International Conference on Computational Linguistics, COLING 2018 |
---|---|
מדינה/אזור | ארצות הברית |
עיר | Santa Fe |
תקופה | 20/08/18 → 26/08/18 |
הערה ביבליוגרפית
Publisher Copyright:© 2018 COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings. All rights reserved.