Seminar Topics and Projects
Giuseppe Attardi Giuseppe Attardi
Dipartimento di Informatica Dipartimento di Informatica
Università di Pisa Università di Pisa
Università di Pisa
Deep Learning Tokenizer Deep Learning Tokenizer
Depling 2016 challenge requires tokenizer for Depling 2016 challenge requires tokenizer for any of the Universal Dependency TreeBank any of the Universal Dependency TreeBank
Build a DL tokenizer using Keras based on Build a DL tokenizer using Keras based on the approach of:
the approach of:
Basile, Valerio and Bos, Johan and Evang, Kilian A General-Purpose Machine Learning Method for Tokenization and Sentence Boundary Detection (2013), http://gmb.let.rug.nl/elephant/
Deep Learning POS for UD Deep Learning POS for UD
Depling 2016 challenge requires tokenizer for Depling 2016 challenge requires tokenizer for any of the Universal Dependency TreeBank any of the Universal Dependency TreeBank
Build a DL POS using CNN, for example a Build a DL POS using CNN, for example a LSTM that uses word embeddings and
LSTM that uses word embeddings and possible charcater embeddings.
possible charcater embeddings.
Deep Learning Morph Deep Learning Morph
Analyzer Analyzer
Depling 2016 challenge requires tokenizer for Depling 2016 challenge requires tokenizer for any of the Universal Dependency TreeBank any of the Universal Dependency TreeBank
Build a DL morphological analyzer that Build a DL morphological analyzer that copmutes the morphology of each word, copmutes the morphology of each word, using Keras and charcaher embeddings.
using Keras and charcaher embeddings.
UD extensions UD extensions
Write scripts to extract additional relations Write scripts to extract additional relations from the analysis of UD parse trees
from the analysis of UD parse trees
Convolutional Networks for Sentiment Convolutional Networks for Sentiment
Analysis Analysis
Annotated Data: SemEval training setAnnotated Data: SemEval training set
Unannotated Data: 50 million tweetsUnannotated Data: 50 million tweets
Code: DeepNL, https://github.com/attardi/Code: DeepNL, https://github.com/attardi/
deepnl deepnl
Article: A. Severyn, A. Moschitti.UNITNArticle: A. Severyn, A. Moschitti.UNITN
: Training Deep Convolutional Neural Network : Training Deep Convolutional Neural Network
for Twitter Sentiment for Twitter Sentiment
Classification Classification
POS tagging using Word POS tagging using Word
Embeddings Embeddings
Data: Evalita 2016Data: Evalita 2016
Embeddings: Embeddings:
http://tanl.di.unipi.it/embeddings/
http://tanl.di.unipi.it/embeddings/
Article: Stratos, M. Collins. Simple Semi-Article: Stratos, M. Collins. Simple Semi- Supervised POS Tagging.
Supervised POS Tagging.
http://www.cs.columbia.edu/~stratos/research http://www.cs.columbia.edu/~stratos/research
/naacl15semipos.pdf /naacl15semipos.pdf
Negation/Speculation Negation/Speculation
Extraction Extraction
Determine the scope of negative or Determine the scope of negative or speculative statements:
speculative statements:
The lyso-platelet had no effect
MnlI-AluI could suppress the basal-level activity
Approach:Approach:
Classifier for identifying cues
Classifier to determine scope
DataData
BioScope collection
Corpus of Product Reviews Corpus of Product Reviews
Download reviews from online shopsDownload reviews from online shops
Classify as positive/negative according to Classify as positive/negative according to stars
stars
Train classifier to assign scoreTrain classifier to assign score
Relation Extraction Relation Extraction
Exploit word embeddings as features + extra Exploit word embeddings as features + extra hand-coded features
hand-coded features
Use the Factor Based Compositional Use the Factor Based Compositional Embedding Model (FCM)
Embedding Model (FCM)
http://www.cs.jhu.edu/~mrg/publications/finer http://www.cs.jhu.edu/~mrg/publications/finer
e-naacl-2015.pdf e-naacl-2015.pdf
SemEval 2014 Relation Extraction dataSemEval 2014 Relation Extraction data
Entity Linking with Embeddings Entity Linking with Embeddings
Experiment with technique:Experiment with technique:
R. Blanco, G. Ottaviano, E. Meiji. 2014. Fast and Space-Efficient Entity Linking in Queries.
labs.yahoo.com/_c/uploads/WSDM-2015-blanco.pdf
Extraction of Semantic Extraction of Semantic
Hierarchies Hierarchies
Use word embeddings as measure of semantic distance
Use Wikipedia as source of text
http://ir.hit.edu.cn/~jguo/papers/acl2014- hypernym.pdf
Aconitum Ranuncolacee
Plant Organism
Suggested Topics for Suggested Topics for
Seminars
Seminars
Neural Reasoning Neural Reasoning
B. Peng, Z. Lu, H. Li, K.F. WongToward B. Peng, Z. Lu, H. Li, K.F. WongToward Neural Network-based Reasoning
Neural Network-based Reasoning
A. Kumar et al.A. Kumar et al.Ask Me Anything: Dynamic Ask Me Anything: Dynamic Memory Networks for Natural Language Memory Networks for Natural Language
Processing Processing
Question Answering Question Answering
Bowl Competition (QANTA vs Jennings)Bowl Competition (QANTA vs Jennings)
https://www.youtube.com/watch?
v=kTXJCEvCDYk
Iyyer et al. 2014: A Neural Network for
Factoid Question Answering over Paragraphs
IBM Watson:IBM Watson:
http://www.aaai.org/Magazine/Watson/watson.php
TAC:TAC:
http://www.nist.gov/tac/2008/qa/index.html
Image Understanding Image Understanding
H. Y. Gao et al. Are You Talking to a H. Y. Gao et al. Are You Talking to a Machine? Dataset and Methods for Machine? Dataset and Methods for
Multilingual Image Question Answering, Multilingual Image Question Answering,
NIPS, 2015.
NIPS, 2015.
Deep Learning Deep Learning
Applications Applications
Character RNNs on text and code
http://karpathy.github.io/2015/05/21/rnn-effec8veness/
Morphology
Better Word Representations with Recursive Neural Networks for Morphology – Luong et al.
Polysemous words
Improving Word Representa8ons Via Global Context And Multiple Word Prototypes by Huang et al. 2012
Natural language Inference (Logic)
Question Answering
Image – Sentence mapping
Entity Linking Entity Linking
Entity Kierarchy EmbeddingsEntity Kierarchy Embeddings
http://www.cs.cmu.edu/~zhitingh/data/acl15entity.
Deep Learning tsunami over Deep Learning tsunami over NLP NLP
C. Manning. 2015. C. Manning. 2015.
http://www.mitpressjournals.org/doi/pdf/10.11 http://www.mitpressjournals.org/doi/pdf/10.11
62/COLI_a_00239 62/COLI_a_00239
Opinion Mining Opinion Mining
B. Liu. Sentiment Analisis and Subjectivity. B. Liu. Sentiment Analisis and Subjectivity.
2010. Handbook of NLP.
2010. Handbook of NLP.
http://www.cs.uic.edu/~liub/FBS/NLP- http://www.cs.uic.edu/~liub/FBS/NLP-
handbook-sentiment-analysis.pdf handbook-sentiment-analysis.pdf
Semantic Role Labeling Semantic Role Labeling
http://ufal.mff.cuni.cz/conll2009-st/task-http://ufal.mff.cuni.cz/conll2009-st/task- description.html
description.html
DL for NLP DL for NLP
Neural Machine TranslationNeural Machine Translation
D. Bahdanau, K. Cho, Y. Bengio. Neural machine translation by jointly learning to align and translate.
http://arxiv.org/pdf/1409.0473v6
Natural Language from scratchNatural Language from scratch
Zhang, X., & LeCun, Y. (2015). Text Understanding from Scratch.
http://arxiv.org/abs/1502.01710