US 11,783,812 B2
Dialogue act classification in group chats with DAG-LSTMs
Ozan Irsoy, New York, NY (US); Rakesh Gosangi, Long Island City, NY (US); Haimin Zhang, Short Hills, NJ (US); Mu-Hsin Wei, Redmond, WA (US); Peter John Lund, New York, NY (US); Duccio Pappadopulo, New York, NY (US); Brendan Michael Fahy, New York, NY (US); Neophytos Nephytou, Glen Cove, NY (US); and Camilo Ortiz Diaz, New York, NY (US)
Assigned to Bloomberg Finance L.P.
Filed by Bloomberg Finance L.P., New York, NY (US)
Filed on Apr. 19, 2021, as Appl. No. 17/234,745.
Claims priority of provisional application 63/016,601, filed on Apr. 28, 2020.
Prior Publication US 2021/0335346 A1, Oct. 28, 2021
Int. Cl. G10L 15/28 (2013.01); G10L 15/16 (2006.01)
CPC G10L 15/16 (2013.01) [G10L 15/28 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A computer implemented method for classifying a dialogue act in a chat log, comprising:
mapping each word of the dialogue act to a word vector representation;
computing an utterance vector representation of the dialogue act based on the word vector representations using a bidirectional long short-term memory (LSTM) architecture;
computing an additional utterance vector representation of the dialogue act based on the utterance vector representation, the computing the additional utterance vector representation comprising:
applying a skip connection between the dialogue act of a participant and an immediately prior dialogue act of the same participant; and
computing the additional utterance vector representation based on an utterance vector representation of the skip connection to the immediately prior dialogue act of the same participant;
mapping the additional utterance vector representation, with a directed-acyclic-graph long short-term memory network (DAG-LSTM), to a classification of the dialogue act; and
outputting the classification of the dialogue act.