CSCI 544 Applied NLP: Proposing a Group Project

Due Date: November 19, 2015, (10:59 AM PST)

We will try to comment on proposals submitted before November 6 by the following week. Submitting later may delay approval. Failure to submit the proposal by the due date (November 19, 10:59 AM PST) will result in zero credit for both the project and assignment 4 (because assignment 4 is closely related to the project).

Online proposal submission.

Help in picking a topic

Domain adaptation

Domain adaptation is a topic that can be explored in a variety of NLP tasks. For many of these tasks, there are large corpora and software tools trained on these corpora. However, performance of the tools may drop when used in domains different from the training corpus. The idea of domain adaptation is to annotate a small amount of training data in the new domain and create a model based on both the large out-of-domain corpus and the small in-domain corpus. This can be applied to NLP tasks such as part of speech tagging, named entity recognition and parsing.

D. McClosky, E. Charniak and M. Johnson. (2010). Automatic domain adaptation for parsing. NAACL.
H. Daume III. (2007). Frustratingly easy domain adaptation. ACL.

Speech recognition / speech synthesis topics

Build a limited-domain speech recognizer. You may use out-of-the-box acoustic models, or adapt out-of-the-box acoustic models to a particular speaker. In the latter case you will have a speaker-dependent speech recognizer. You can build domain-specific language models using one of the language modeling toolkits mentioned below.
Build a grapheme to phoneme converter. The input will be a word and the output a sequence of phonemes. You may train and test your model using a pronunciation dictionary, e.g., the CMU pronouncing dictionary.
Speech recognition error simulation.

NLU topics

Recognition of multiword expressions such as compound nouns, proper names, and idioms.
Word sense disambiguation.
Unsupervised learning of lexical semantics.
Learn a probabilistic context-free grammar from a corpus.
Build a limited-domain NLU system using a parser.
Semantic role labeling.
Automatically grade student answers.
Detection of grammatical errors, e.g., wrong prepositions.

Discourse topics

Coreference resolution.
Information extraction.
Discourse segmentation.
Discourse parsing.
Build a simple natural language generation system.
Build a simple summarization system.

Dialogue topics

Build a limited-domain goal-oriented dialogue system.
Build a simple chat-oriented dialogue system.
Develop dialogue management strategies using reinforcement learning.

Help in finding data

NLTK data: a large repository of many kinds of data.
Message Understanding Conferences 3 and 4 (information extraction, named entity recognition, coreference resolution).
FrameNet (Semantic Role information).
PropBank / AMR info.
Computational Natural Language Learning conference shared tasks:

1999 and 2000: chunking;
2001: clause identification (good for discourse parsing);
2002 and 2003: named entity recognition;
2004 and 2005: semantic role labeling;
2008: syntactic and semantic dependencies.