Search Results for author: Kechen Qin

Found 6 papers, 0 papers with code

Improving Query Graph Generation for Complex Question Answering over Knowledge Base

no code implementations EMNLP 2021 Kechen Qin, Cheng Li, Virgil Pavlu, Javed Aslam

Most of the existing Knowledge-based Question Answering (KBQA) methods first learn to map the given question to a query graph, and then convert the graph to an executable query to find the answer.

Graph Generation Question Answering

Ranking-Based Autoencoder for Extreme Multi-label Classification

no code implementations NAACL 2019 Bingyu Wang, Li Chen, Wei Sun, Kechen Qin, Kefeng Li, Hui Zhou

Extreme Multi-label classification (XML) is an important yet challenging machine learning task, that assigns to each instance its most relevant candidate labels from an extremely large label collection, where the numbers of labels, features and instances could be thousands or millions.

Classification Extreme Multi-Label Classification +2

Adapting RNN Sequence Prediction Model to Multi-label Set Prediction

no code implementations NAACL 2019 Kechen Qin, Cheng Li, Virgil Pavlu, Javed A. Aslam

Previous such RNN models define probabilities for sequences but not for sets; attempts to obtain a set probability are after-thoughts of the network design, including pre-specifying the label order, or relating the sequence probability to the set probability in ad hoc ways.

Multi-Label Classification

Winning on the Merits: The Joint Effects of Content and Style on Debate Outcomes

no code implementations TACL 2017 Lu Wang, Nick Beauchamp, Sarah Shugars, Kechen Qin

Using a dataset of 118 Oxford-style debates, our model's combination of content (as latent topics) and style (as linguistic features) allows us to predict audience-adjudicated winners with 74% accuracy, significantly outperforming linguistic features alone (66%).

Joint Modeling of Content and Discourse Relations in Dialogues

no code implementations ACL 2017 Kechen Qin, Lu Wang, Joseph Kim

We present a joint modeling approach to identify salient discussion points in spoken meetings as well as to label the discourse relations between speaker turns.

Cannot find the paper you are looking for? You can Submit a new open access paper.