240 likes | 417 Views
Final talk. Automatically Acquiring a Dictionary of Emotion-Provoking Events. Student: Hoa Vu- Trong – VNU Supervisor: Graham sensei - NAIST. Can Twitter benefit a dialogue system?. Twitter users. Dialog System. Machine : Hello! User : Hello! User : A guy next to me today,
E N D
Final talk Automatically Acquiring a Dictionary of Emotion-Provoking Events Student: Hoa Vu-Trong – VNU Supervisor: Graham sensei - NAIST
Can Twitter benefit a dialogue system? Twitter users Dialog System Machine: Hello! User: Hello! User: A guy next to me today, are too noisy ! Machine: That's so annoying! User:
Motivation Emotion is not present in specific word. 4% of words imply emotion [1] • Text emotion classifier • I feel happy today • I met my friend today Simple architecture of dialogue system with emotion adaption. [1] Pennebaker, J.W., Mehl, M.R., Niederhoffer, K.: Psychological aspects of natural language use: Our words, our selves. Annual Review of Psychology 54, 547–577 (2003)
Motivation • Arbitrarily large set of emotion-provoking events can be collected from Twitter You must be very happy 400M tweets/day
Method Emotion and Event have relation. Pattern learning is an effective way to harvest semantic relation Espresso (Pantel and Pennacchiotti 06). Ex: “I'mhappythatI have the support of my friends. I love all of them!” “I'msadthattomorrow is Monday and I have to work. It's bad day” Pattern: I beEMOTIONthatEVENT Instances: happy – I have the support of my friends sad – tomorrow is Monday and I have to work
Espresso Algorithm Used in mining semantic relation (eg: is-a, has-a …) begins with some seed instances. Each iteration contains 3 phases: Pattern Induction Pattern ranking Instance extraction Stopping criterion: enough patterns, average reliabilty of the patterns decrease t% or exeeds defined number of iterations.
Espresso Algorithm Pattern Induction: Infers all the patterns P that connect the seed instances. Ex: I'mhappythatI have the support of my friends. I love all of them! I'msadthattomorrow is Monday and I have to work. It's bad day I beEMOTIONthatEVENT . I love all of you I beEMOTIONthatEVENT .It be bad day I be EMOTION that EVENT - 2 times EMOTION that EVENT . - 2 times EMOTION that EVENT . I love all – 1 time … …
Espresso Algorithm Pattern ranking: Rank all the patterns and extract top K reliable ones. Reliable patterns: one that both highly precise and one that extract many instances (more in next slides).
Espresso Algorithm Instance Extraction: Retrieves top M reliable instances match K patterns extracted from previous phase. Reliable instance: one that highly associated with as many reliable patterns. (more in next slides)
Espresso Algorithm Strength of association between instance i(x,y) and pattern p is measured by PMI.
Espresso Algorithm Pattern reliability: Instance reliability:
Grouping events • Relieve sparsityissues to some extent by sharing statistics among the events in a single group • allows humans to understand the events better, highlighting the important events shared by many people • Using hierarchical agglomerative clustering and the single-linkage criterion using cosine similarity as a distance measure
Experiments Data corpus: 30 million tweets from Neubig and Duh 13' [1] Tweet normalization by Han et al 12' [2] Stanford parser [3] was employed to make sure that event must be a sentence [1] Graham Neubig, Kevin Duh.How Much is Said in a Tweet? A Multilingual, Information-theoretic Perspective in AAAI Spring Symposium on Analyzing Microtext. Stanford, California. March 2013. [2] Han et al. Automatically Constructing a Normalisation Dictionary for Microblogs in EMLNP 2012 http://nlp.stanford.edu/software/lex-parser.shtml
Experiments 6 basic emotion classes defined by Ekman [1] : Anger: angry, mad Digust: digusted, terrible Fear: afraid, scared Happiness: happy, glad Sadness: sad, upset Surprise: surprised, astonished [1]Ekman, P.: Universals and cultural dierences in facial expressions of emotions. Nebraska Symposium on Motivation 19, 207{283 (1972)}
Experiments We start the system with the seed instances collected by the pattern: “I be EMOTION that EVENT” Reliability of seed instances is 1. Stopping criterion: limit iterations.
Result Happiness: 14027 events Sadness: 3909 events Fear: 8798 events Anger: 2133 events Surprise: 2466 events Disgust: 26 events
Result Some new patterns: I feel EMOTION when EVENT I be EMOTION because EVENT I be EMOTION EVENT I get so EMOTION when EVENT Make me EMOTION when EVENT Get really EMOTION that EVENT Be really EMOTION to hear that EVENT Be EMOTION to know that EVENT EMOTION at the fact that EVENT be EMOTION to death that EVENT …
Evaluation Using Mean Reciprocal Rank(MMR):
Evaluation Measuring recall Asking 30 people about 5 events that provoke each of five emotions
Evaluation Evaluation emotion-provoking events Human evaluation on top 100 groups.
Disscusion Recall is still relatively low Events extracted from Twitter were somewhat biased towards everyday events or events regarding love and dating for surprise we didn’t manage to extract any of the emotions created by the annotators at all
In Conclusion This work focus on acquiring emotion-provoking events Using Espresso algorithm to learn patterns and extract events then similar events are grouped to create a dictionary. Paper summited to EACL 2014