Learning TFC Meeting, SRI March 2005 On the Collective Classification of “Speech Acts” Vitor R. Carvalho & William W. Cohen Carnegie Mellon University

Classifying into Acts From EMNLP-04, Learning to Classify into Speech Acts, Cohen- Carvalho-Mitchell From EMNLP-04, Learning to Classify into Speech Acts, Cohen- Carvalho-Mitchell An Act is described as a verb- noun pair (e.g., propose meeting, request information) - Not all pairs make sense. One single message may contain multiple acts. An Act is described as a verb- noun pair (e.g., propose meeting, request information) - Not all pairs make sense. One single message may contain multiple acts. Try to describe commonly observed behaviors, rather than all possible speech acts in English. Also include non- linguistic usage of (e.g. delivery of files) Try to describe commonly observed behaviors, rather than all possible speech acts in English. Also include non- linguistic usage of (e.g. delivery of files) Nouns Verbs

Idea: Predicting Acts from Surrounding Acts Delivery Request Commit Proposal Request Commit Delivery Commit Delivery > Act has little or no correlation with other acts of same message Strong correlation with previous and next message’s acts Example of Sequence

 Winograd and Flores, 1986: “Conversation for Action Structure”  Murakoshi et al. 1999; “ Construction of Deliberation Structure in ” Related work on the Sequential Nature of Negotiations

Data: CSPACE Corpus Few large, free, natural corpora are available Few large, free, natural corpora are available CSPACE corpus (Kraut & Fussell) CSPACE corpus (Kraut & Fussell) o s associated with a semester-long project for Carnegie Mellon MBA students in 1997 o 15,000 messages from 277 students, divided in 50 teams (4 to 6 students/team) o Rich in task negotiation. o More than 1500 messages (from 4 teams) were labeled in terms of “Speech Act”. o One of the teams was double labeled, and the inter- annotator agreement ranges from 72 to 83% (Kappa) for the most frequent acts.

Evidence of Sequential Correlation of Acts Transition diagram for most common verbs from CSPACE corpus It is NOT a Probabilistic DFA Act sequence patterns: (Request, Deliver+), (Propose, Commit+, Deliver+), (Propose, Deliver+), most common act was Deliver Less regularity than the expected ( considering previous deterministic negotiation state diagrams)

Content versus Context Content: Bag of Words features only Context: Parent and Child Features only ( table below) 8 MaxEnt classifiers, trained on 3F2 and tested on 1F3 team dataset Only 1 st child message was considered (vast majority – more than 95%) Kappa Values on 1F3 using Relational (Context) features and Textual (Content) features. Parent Boolean Features Child Boolean Features Parent_Request, Parent_Deliver, Parent_Commit, Parent_Propose, Parent_Directive, Parent_Commissive Parent_Meeting, Parent_dData Child_Request, Child_Deliver, Child_Commit, Child_Propose, Child_Directive, Child_Commissive, Child_Meeting, Child_dData Set of Context Features (Relational) Delivery Request Commit Proposal Request ??? Parent messageChild message

Collective Classification using Dependency Networks Dependency networks are probabilistic graphical models in which the full joint distribution of the network is approximated with a set of conditional distributions that can be learned independently. The conditional probability distributions in a DN are calculated for each node given its neighboring nodes (its Markov blanket). No acyclicity constraint. Simple parameter estimation – approximate inference (Gibbs sampling) No acyclicity constraint. Simple parameter estimation – approximate inference (Gibbs sampling) In this case, Markov blanket = parent message and child message In this case, Markov blanket = parent message and child message Heckerman et al., JMLR Neville & Jensen, KDD-MRDM Heckerman et al., JMLR Neville & Jensen, KDD-MRDM-2003.

Collective Classification algorithm (based on Dependency Networks Model)

Agreement versus Iteration Kappa versus iteration on 1F3 team dataset, using classifiers trained on 3F2 team data. Kappa versus iteration on 1F3 team dataset, using classifiers trained on 3F2 team data.

Leave-one-team-out Experiments 4 teams: 1f3(170 msgs), 2f2(137 msgs), 3f2(249 msgs) and 4f4(165 msgs) 4 teams: 1f3(170 msgs), 2f2(137 msgs), 3f2(249 msgs) and 4f4(165 msgs) (x axis)= Bag-of-words only (x axis)= Bag-of-words only (y-axis) = Collective classification results (y-axis) = Collective classification results Different teams present different styles for negotiations and task delegation. Different teams present different styles for negotiations and task delegation. Kappa Values

Leave-one-team-out Experiments Consistent improvement of Commissive, Commit and Meet acts Consistent improvement of Commissive, Commit and Meet acts Kappa Values

Leave-one-team-out Experiments Deliver and dData performance usually decreases Deliver and dData performance usually decreases Associated with data distribution, FYI, file sharing, etc. Associated with data distribution, FYI, file sharing, etc. For “non-delivery”, improvement in avg. Kappa is statistically significant (p=0.01 on a two-tailed T-test) For “non-delivery”, improvement in avg. Kappa is statistically significant (p=0.01 on a two-tailed T-test) Kappa Values

Act by Act Comparative Results Kappa values with and without collective classification, averaged over the four test sets in the leave-one-team out experiment.

Discussion and Conclusion  Sequential patterns of acts were observed in the CSPACE corpus.  These patterns, when studied an artificial experiment, were shown to contain valuable information to the -act classification problem.  Different teams present different styles for negotiations and task delegation.  We proposed a collective classification scheme for Speech Acts of messages. (based on a Dependency Network model)

Conclusion  Modest improvements over the baseline (bag of words) were observed on acts related to negotiation (Request, Commit, Propose, Meet, etc). A performance deterioration was observed for Delivery/dData (acts less associated with negotiations)  Agrees with general intuition on the sequential nature of negotiation steps.  Degree of linkage in our dataset is small – which makes the observed results encouraging.