Related papers: Generating Contradictory, Neutral, and Entailing S…
Complex textual information extraction tasks are often posed as sequence labeling or \emph{shallow parsing}, where fields are extracted using local labels made consistent through probabilistic inference in a graphical model with constrained…
Consider learning a generative model for time-series data. The sequential setting poses a unique challenge: Not only should the generator capture the conditional dynamics of (stepwise) transitions, but its open-loop rollouts should also…
Existing methods to measure sentence similarity are faced with two challenges: (1) labeled datasets are usually limited in size, making them insufficient to train supervised neural models; (2) there is a training-test gap for unsupervised…
Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor…
Many Natural Language Generation (NLG) tasks aim to generate a single output text given an input prompt. Other settings require the generation of multiple texts, e.g., for Synthetic Traffic Generation (STG). This generation task is crucial…
Inference tasks in signal processing are often characterized by the availability of reliable statistical modeling with some missing instance-specific parameters. One conventional approach uses data to estimate these missing parameters and…
Unsupported and unfalsifiable claims we encounter in our daily lives can influence our view of the world. Characterizing, summarizing, and -- more generally -- making sense of such claims, however, can be challenging. In this work, we focus…
Generating paragraphs of diverse contents is important in many applications. Existing generation models produce similar contents from homogenized contexts due to the fixed left-to-right sentence order. Our idea is permuting the sentence…
We present a generative model for multitask conditional language generation. Our guiding hypothesis is that a shared set of latent skills underlies many disparate language generation tasks, and that explicitly modelling these skills in a…
Most work on neural natural language generation (NNLG) focus on controlling the content of the generated text. We experiment with controlling several stylistic aspects of the generated text, in addition to its content. The method is based…
Neural network-based generative language models like ELMo and BERT can work effectively as general purpose sentence encoders in text classification without further fine-tuning. Is it possible to adapt them in a similar way for use as…
In this paper, we tackle the task of definition modeling, where the goal is to learn to generate definitions of words and phrases. Existing approaches for this task are discriminative, combining distributional and lexical semantics in an…
Do state-of-the-art models for language understanding already have, or can they easily learn, abilities such as boolean coordination, quantification, conditionals, comparatives, and monotonicity reasoning (i.e., reasoning about word…
Automatically describing video content with text description is challenging but important task, which has been attracting a lot of attention in computer vision community. Previous works mainly strive for the accuracy of the generated…
In this paper, we propose a generative model which learns the relationship between language and human action in order to generate a human action sequence given a sentence describing human behavior. The proposed generative model is a…
This paper describes a neural semantic parser that maps natural language utterances onto logical forms which can be executed against a task-specific environment, such as a knowledge base or a database, to produce a response. The parser…
Pre-trained language models have proven their unique powers in capturing implicit language features. However, most pre-training approaches focus on the word-level training objective, while sentence-level objectives are rarely studied. In…
A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we…
Generative models for text have substantially contributed to tasks like machine translation and language modeling, using maximum likelihood optimization (MLE). However, for creative text generation, where multiple outputs are possible and…
Many natural language inference (NLI) datasets contain biases that allow models to perform well by only using a biased subset of the input, without considering the remainder features. For instance, models are able to make a classification…