Phil Blunsom

Neural Variational Inference for Text Processing

2015 · arXiv (Cornell University)

Recent advances in neural variational inference have spawned a renaissance in deep latent variable models. In this paper we introduce a generic variational inference framework for generative and conditional models of text. While traditional variational …

Latent Predictor Networks for Code Generation

2016 · arXiv (Cornell University)

Many language generation tasks require the production of text conditioned on both structured and unstructured inputs. We present a novel neural network architecture which generates an output sequence conditioned on an arbitrary number of input …

Learning and Evaluating General Linguistic Intelligence

2019 · arXiv (Cornell University)

We define general linguistic intelligence as the ability to reuse previously acquired knowledge about a language's lexicon, syntax, semantics, and pragmatic conventions to adapt to new tasks quickly. Using this definition, we analyze state-of-the-art natural …

Mind the Gap: Assessing Temporal Generalization in Neural Language Models

2021 · arXiv (Cornell University)

Our world is open-ended, non-stationary, and constantly evolving; thus what we talk about and how we talk about it change over time. This inherent dynamic nature of language contrasts with the current static language modelling …

Revisiting the Compositional Generalization Abilities of Neural Sequence Models

2022 · arXiv (Cornell University)

Compositional generalization is a fundamental trait in humans, allowing us to effortlessly combine known phrases to form novel sentences. Recent works have claimed that standard seq-to-seq models severely lack the ability to compositionally generalize. In …

Human Feedback is not Gold Standard

2023 · arXiv (Cornell University)

Human feedback has become the de facto standard for evaluating the performance of Large Language Models, and is increasingly being used as a training objective. However, it is not clear which properties of a generated …

Teaching Machines to Read and Comprehend

2015 · arXiv (Cornell University)

Teaching machines to read natural language documents remains an elusive challenge. Machine reading systems can be tested on their ability to answer questions posed on the contents of documents that they have seen, but until …

Reasoning about Entailment with Neural Attention

2015 · arXiv (Cornell University)

While most approaches to automatically recognizing entailment relations have used classifiers employing hand engineered features derived from complex natural language processing pipelines, in practice their performance has been only slightly better than bag-of-word pair classifiers …

Discovering Discrete Latent Topics with Neural Variational Inference

2017 · arXiv (Cornell University)

Topic models have been widely explored as probabilistic generative models of documents. Traditional inference methods have sought closed-form derivations for updating the models, however as the expressiveness of these models grows, so does the difficulty …

The NarrativeQA Reading Comprehension Challenge

2018 · Transactions of the Association for Computational Linguistics

Reading comprehension (RC)—in contrast to information retrieval—requires integrating information and reasoning about events, entities, and their relations across a full document. Question answering is conventionally used to assess RC ability, in both artificial agents and …

LSTMs Can Learn Syntax-Sensitive Dependencies Well, But Modeling Structure Makes Them Better

2018

Adhiguna Kuncoro, Chris Dyer, John Hale, Dani Yogatama, Stephen Clark, Phil Blunsom. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018.

e-SNLI: Natural Language Inference with Natural Language Explanations

2018 · arXiv (Cornell University)

In order for machine learning to garner widespread public adoption, models must be able to provide interpretable and robust explanations for their decisions, as well as learn from human-provided explanations at train time. In this …

Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems

2017

Solving algebraic word problems requires executing a series of arithmetic operations-a program-to obtain a final answer. However, since programs can be arbitrarily complicated, inducing them directly from question-answer pairs is a formidable challenge. To make …