Learn More
Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted , predicting utterances one at a time while ignoring their influence on future outcomes. Modeling the future direction of a dialogue is crucial to generating coherent, interesting dialogues, a need which led(More)
We propose a simple, fast decoding algorithm that fosters diversity in neural generation. The algorithm modifies the standard beam search algorithm by penalizing hypotheses that are siblings—expansions of the same parent node in the search—thus favoring including hypotheses from diverse parents. We evaluate the model on three neural generation tasks:(More)
In this paper, drawing intuition from the Turing test, we propose using ad-versarial training for open-domain dialogue generation: the system is trained to produce sequences that are indistinguishable from human-generated dialogue utterances. We cast the task as a reinforcement learning (RL) problem where we jointly train two systems, a genera-tive model to(More)
While neural networks have been successfully applied to many natural language processing tasks, they come at the cost of interpretability. In this paper, we propose a general methodology to analyze and interpret decisions from a neural model by observing the effects on the model of erasing various parts of the representation , such as input word-vector(More)
Segmentation of clitics has been shown to improve accuracy on a variety of Arabic NLP tasks. However, state-of-the-art Ara-bic word segmenters are either limited to formal Modern Standard Arabic, performing poorly on Arabic text featuring dialectal vocabulary and grammar, or rely on linguistic knowledge that is hand-tuned for each dialect. We extend an(More)
The ability to map descriptions of scenes to 3D geometric representations has many applications in areas such as art, education , and robotics. However, prior work on the text to 3D scene generation task has used manually specified object categories and language that identifies them. We introduce a dataset of 3D scenes annotated with natural language(More)
The production of color language is essential for grounded language generation. Color descriptions have many challenging properties: they can be vague, compositionally complex, and denotationally rich. We present an effective approach to generating color descriptions using recurrent neural networks and a Fourier-transformed color representation. Our model(More)