Reading group on Distributional Semantic Models
This is the web page of the reading group on distributional semantic models. The reading group welcomes computational linguists, linguists, psycholinguists, NLP people and every possible flavor in between.
We will meet on Tuesdays at 11am in the Aquarium (Room 3.23, Geb. C7.4) probably every second week.
Next week
Our next meeting will be
- on Tuesday, January 10th, 11am. Carina will present this paper:
- Kober, T., Weeds, J., Reffin, J., & Weir, D. (2016). Improving Sparse Word Representations with Distributional Inference for Semantic Composition. arXiv preprint arXiv:1608.06794. https://arxiv.org/pdf/1608.06794v1.pdf
Mailing list
If you are interested in receiving emails regarding the reading group, email Alessandra (zarcone (at) coli.uni-saarland.de) to be added to the mailing list.
Calendar
I will update a Google calendar with current talks, as well as show titles in the table below. You can use the calendar to see what papers we presented so far and to integrate it in your calendar app of choice (iCal/ICS - HTML).
(To import it into Google Calendar, pick "Other Calendars" -> "Add by URL" and copy the ICS link there).
Paper suggestions
The reading group encourages paper suggestions from the participants. Here's a few suggestions for papers to discuss. Email Alessandra (zarcone (at) coli.uni-saarland.de) to add your suggestions to this list:
- Chen, X., Qiu, X., Zhu, C., Wu, S., & Huang, X. (2015) Sentence Modeling with Gated Recursive Neural Network.In Proceedings of EMNLP. https://aclweb.org/anthology/D/D15/D15-1092.pdf
- Goyal, K., Jauhar, S. K., Li, H., Sachan, M., Srivastava, S., & Hovy, E. H. (2013). A Structured Distributional Semantic Model for Event Co-reference. In ACL (2) (pp. 467-473). http://www.anthology.aclweb.org/P/P13/P13-2.pdf#page=515
- Gupta, A., Boleda, G., Baroni, M., & Padó, S. (2015). Distributional vectors encode referential attributes. In Proceedings of EMNLP. https://aclweb.org/anthology/D/D15/D15-1002.pdf
- Gupta, A., Utt, J., & Padó, S. (2015). Dissecting the Practical Lexical Function Model for Compositional Distributional Semantics. Lexical and Computational Semantics (* SEM 2015), 153. http://anthology.aclweb.org/S/S15/S15-1.pdf#page=171
- Kiela, D., Hill, F., & Clark, S. (2015) Specializing Word Embeddings for Similarity or Relatedness. In Proceedings of EMNLP. https://aclweb.org/anthology/D/D15/D15-1242.pdf
- Levy, O., Goldberg, Y., & Dagan, I. (2015). Improving distributional similarity with lessons learned from word embeddings. TACL, 3, 211-225.
- Li, J., & Jurafsky, D. (2015). Do Multi-Sense Embeddings Improve Natural Language Understanding?. In Proceedings of EMNLP. https://aclweb.org/anthology/D/D15/D15-1200.pdf
- Li, J., Jurafsky, D., & Hovy, E. (2015). When Are Tree Structures Necessary for Deep Learning of Representations? In Proceedings of EMNLP. https://aclweb.org/anthology/D/D15/D15-1278.pdf
- Mitchell, J., & Steedman, M. (2015) Orthogonality of Syntax and Semantics within Distributional Spaces. In Proceedings of ACL
- Murray, K., & Chiang, D. (2015). Auto-Sizing Neural Networks: With Applications to n-gram Language Models. In Proceedings of EMNLP. https://aclweb.org/anthology/D/D15/D15-1107.pdf
- Polajnar, T., Rimell, L., & Clark, S. (2015). An Exploration of Discourse-Based Sentence Spaces for Compositional Distributional Semantics. In Proceedings of EMNLP. https://aclweb.org/anthology/W/W15/W15-2701.pdf
- Roller, S., Erk, K., & Boleda, G. (2014). Inclusive yet selective: Supervised distributional hypernymy detection. In Proceedings of COLING, Dublin, Ireland. http://aclweb.org/anthology//C/C14/C14-1097.pdf
- Schnabel, T., Labutov, I., Mimno, D., & Joachims, T. (2015). Evaluation methods for unsupervised word embeddings. In Proceedings of EMNLP. http://www.anthology.aclweb.org/D/D15/D15-1036.pdf
- Tsvetkov, Y., Faruqui, M., Ling, W., Lample, G., Dyer, C. (2015). Evaluation of Word Vector Representations by Subspace Alignment. In Proceedings of EMNLP. http://www.aclweb.org/anthology/D15-1243
- Weeds, J., Clarke, D., Reffin, J., Weir, D., & Keller, B. (2014). Learning to distinguish hypernyms and co-hyponyms. In Proceedings of COLING (pp. 2249-2259). http://www.aclweb.org/anthology/C14-1212
"One might
consider LSA's maximal knowledge of the world
to be analogous to a well-read nun's knowledge of sex,
a level of knowledge often deemed
a sufficient basis for advising the young"
Landauer et al. An introduction to Latent Semantic Analysis