Abstract
(WSD). In particular, the technique proposed by Yuan et al. (2016) returned state-of-the-art performance
in several benchmarks, but neither the training data nor the source code was released.
This paper presents the results of a reproduction study and analysis of this technique using only
openly available datasets (GigaWord, SemCor, OMSTI) and software (TensorFlow). Our study
showed that similar results can be obtained with much less data than hinted at by Yuan et al.
(2016). Detailed analyses shed light on the strengths and weaknesses of this method. First,
adding more unannotated training data is useful, but is subject to diminishing returns. Second,
the model can correctly identify both popular and unpopular meanings. Finally, the limited sense
coverage in the annotated datasets is a major limitation. All code and trained models are made
freely available.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the International Conference on Computational Linguistics (COLING 2018) |
| Publisher | International Conference on Computational Linguistics (COLING) |
| Pages | 354-365 |
| Number of pages | 12 |
| ISBN (Print) | 9781948087506 |
| Publication status | Published - 2018 |
| Event | 27th International Conference on Computational Linguistics COLING 2018 - Santa Fe, NM Duration: 20 Aug 2018 → 26 Aug 2018 Conference number: 27 |
Conference
| Conference | 27th International Conference on Computational Linguistics COLING 2018 |
|---|---|
| Abbreviated title | COLING 2018 |
| City | Santa Fe, NM |
| Period | 20/08/18 → 26/08/18 |
Cite this
}
Deep Dive into Word Sense Disambiguation with LSTM. / Le, M.N.; Postma, M.C.; Urbani, J.; Vossen, P.T.J.M.
Proceedings of the International Conference on Computational Linguistics (COLING 2018). International Conference on Computational Linguistics (COLING), 2018. p. 354-365.Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review
TY - GEN
T1 - Deep Dive into Word Sense Disambiguation with LSTM
AU - Le, M.N.
AU - Postma, M.C.
AU - Urbani, J.
AU - Vossen, P.T.J.M.
PY - 2018
Y1 - 2018
N2 - LSTM-based language models have been shown effective in Word Sense Disambiguation(WSD). In particular, the technique proposed by Yuan et al. (2016) returned state-of-the-art performancein several benchmarks, but neither the training data nor the source code was released.This paper presents the results of a reproduction study and analysis of this technique using onlyopenly available datasets (GigaWord, SemCor, OMSTI) and software (TensorFlow). Our studyshowed that similar results can be obtained with much less data than hinted at by Yuan et al.(2016). Detailed analyses shed light on the strengths and weaknesses of this method. First,adding more unannotated training data is useful, but is subject to diminishing returns. Second,the model can correctly identify both popular and unpopular meanings. Finally, the limited sensecoverage in the annotated datasets is a major limitation. All code and trained models are madefreely available.
AB - LSTM-based language models have been shown effective in Word Sense Disambiguation(WSD). In particular, the technique proposed by Yuan et al. (2016) returned state-of-the-art performancein several benchmarks, but neither the training data nor the source code was released.This paper presents the results of a reproduction study and analysis of this technique using onlyopenly available datasets (GigaWord, SemCor, OMSTI) and software (TensorFlow). Our studyshowed that similar results can be obtained with much less data than hinted at by Yuan et al.(2016). Detailed analyses shed light on the strengths and weaknesses of this method. First,adding more unannotated training data is useful, but is subject to diminishing returns. Second,the model can correctly identify both popular and unpopular meanings. Finally, the limited sensecoverage in the annotated datasets is a major limitation. All code and trained models are madefreely available.
UR - https://www.researchgate.net/publication/327500586_A_Deep_Dive_into_Word_Sense_Disambiguation_with_LSTM
UR - https://github.com/cltl/LSTM-WSD
UR - https://aclanthology.info/events/coling-2018
M3 - Conference contribution
SN - 9781948087506
SP - 354
EP - 365
BT - Proceedings of the International Conference on Computational Linguistics (COLING 2018)
PB - International Conference on Computational Linguistics (COLING)
ER -