Aaron Jaech


2018

pdf bib
Collecting Code-Switched Data from Social Media
Gideon Mendels | Victor Soto | Aaron Jaech | Julia Hirschberg
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Community Member Retrieval on Social Media Using Textual Information
Aaron Jaech | Shobhit Hathi | Mari Ostendorf
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

This paper addresses the problem of community membership detection using only text features in a scenario where a small number of positive labeled examples defines the community. The solution introduces an unsupervised proxy task for learning user embeddings: user re-identification. Experiments with 16 different communities show that the resulting embeddings are more effective for community membership identification than common unsupervised representations.

pdf bib
Low-Rank RNN Adaptation for Context-Aware Language Modeling
Aaron Jaech | Mari Ostendorf
Transactions of the Association for Computational Linguistics, Volume 6

A context-aware language model uses location, user and/or domain metadata (context) to adapt its predictions. In neural language models, context information is typically represented as an embedding and it is given to the RNN as an additional input, which has been shown to be useful in many applications. We introduce a more powerful mechanism for using context to adapt an RNN by letting the context vector control a low-rank transformation of the recurrent layer weight matrix. Experiments show that allowing a greater fraction of the model parameters to be adjusted has benefits in terms of perplexity and classification for several different types of context.

pdf bib
Personalized Language Model for Query Auto-Completion
Aaron Jaech | Mari Ostendorf
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Query auto-completion is a search engine feature whereby the system suggests completed queries as the user types. Recently, the use of a recurrent neural network language model was suggested as a method of generating query completions. We show how an adaptable language model can be used to generate personalized completions and how the model can use online updating to make predictions for users not seen during training. The personalized predictions are significantly better than a baseline that uses no user information.

2016

pdf bib
Phonological Pun-derstanding
Aaron Jaech | Rik Koncel-Kedziorski | Mari Ostendorf
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
A Neural Model for Language Identification in Code-Switched Tweets
Aaron Jaech | George Mulcaire | Mari Ostendorf | Noah A. Smith
Proceedings of the Second Workshop on Computational Approaches to Code Switching

pdf bib
Hierarchical Character-Word Models for Language Identification
Aaron Jaech | George Mulcaire | Shobhit Hathi | Mari Ostendorf | Noah A. Smith
Proceedings of The Fourth International Workshop on Natural Language Processing for Social Media

2015

pdf bib
Talking to the crowd: What do people react to in online discussions?
Aaron Jaech | Victoria Zayats | Hao Fang | Mari Ostendorf | Hannaneh Hajishirzi
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
What Your Username Says About You
Aaron Jaech | Mari Ostendorf
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing