activity
20152017
most citedCharagram: Embedding Words and Sentences via Character n-grams

43 citations · 109 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CL20179 cited

Hierarchically-Attentive RNN for Album Summarization and Storytelling

Licheng Yu, Mohit Bansal, Tamara L. Berg

We address the problem of end-to-end visual storytelling. Given a photo album, our model first selects the most representative (summary) photos, and then composes a natural languag…

cs.CL2017

Reinforced Video Captioning with Entailment Rewards

Ramakanth Pasunuru, Mohit Bansal

Sequence-to-sequence models have shown promising improvements on the temporal task of video captioning, but they optimize word-level cross-entropy loss during training. First, usin…

cs.CL201737 cited

Shortcut-Stacked Sentence Encoders for Multi-Domain Inference

Yixin Nie, Mohit Bansal

We present a simple sequential sentence encoder for multi-domain natural language inference. Our encoder is based on stacked bidirectional LSTM-RNNs with shortcut connections and f…

cs.CL20178 cited

Video Highlight Prediction Using Audience Chat Reactions

Cheng-Yang Fu, Joon Lee, Mohit Bansal +1

Sports channel video portals offer an exciting domain for research on multimodal, multilingual analysis. We present methods addressing the problem of automatic video highlight pred…

cs.CL20179 cited

Source-Target Inference Models for Spatial Instruction Understanding

Hao Tan, Mohit Bansal

Models that can execute natural language instructions for situated robotic tasks such as assembly and navigation have several useful applications in homes, offices, and remote scen…

cs.CL201643 cited

Charagram: Embedding Words and Sentences via Character n-grams

John Wieting, Mohit Bansal, Kevin Gimpel +1

We present Charagram embeddings, a simple approach for learning character-based compositional models to embed textual sequences. A word or sentence is represented using a character…