10 citations · 19 across the 9 of their papers we have counts for
10 papers
The Stable Entropy Hypothesis and Entropy-Aware Decoding: An Analysis and Algorithm for Robust Natural Language Generation
Kushal Arora, Timothy J. O'Donnell, Doina Precup +2
State-of-the-art language generation models can degenerate when applied to open-ended generation problems such as text completion, story generation, or dialog modeling. This degene…
Evaluating Distributional Distortion in Neural Language Modeling
Benjamin LeBrun, Alessandro Sordoni, Timothy J. O'Donnell
A fundamental characteristic of natural language is the high rate at which speakers produce novel expressions. Because of this novelty, a heavy-tail of rare events accounts for a s…
Systematic Generalization with Edge Transformers
Leon Bergen, Timothy J. O'Donnell, Dzmitry Bahdanau
Recent research suggests that systematic generalization in natural language understanding remains a challenge for state-of-the-art neural models such as Transformers and Graph Neur…
Compositional Generalization in Dependency Parsing
Emily Goodwin, Siva Reddy, Timothy J. O'Donnell +1
Compositionality -- the ability to combine familiar units like words into novel phrases and sentences -- has been the focus of intense interest in artificial intelligence in recent…
Jointly Learning Truth-Conditional Denotations and Groundings using Parallel Attention
Leon Bergen, Dzmitry Bahdanau, Timothy J. O'Donnell
We present a model that jointly learns the denotations of words together with their groundings using a truth-conditional semantics. Our model builds on the neurosymbolic approach o…
Linguistic Dependencies and Statistical Dependence
Jacob Louis Hoover, Alessandro Sordoni, Wenyu Du +1
Are pairs of words that tend to occur together also likely to stand in a linguistic dependency? This empirical question is motivated by a long history of literature in cognitive sc…
Characterizing Idioms: Conventionality and Contingency
Michaela Socolof, Jackie Chi Kit Cheung, Michael Wagner +1
Idioms are unlike most phrases in two important ways. First, the words in an idiom have non-canonical meanings. Second, the non-canonical meanings of words in an idiom are continge…
Recursive Top-Down Production for Sentence Generation with Latent Trees
Shawn Tan, Yikang Shen, Timothy J. O'Donnell +2
We model the recursive production property of context-free grammars for natural and synthetic languages. To this end, we present a dynamic programming algorithm that marginalises o…
Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach
Wenyu Du, Zhouhan Lin, Yikang Shen +3
It is commonly believed that knowledge of syntactic structure should improve language modeling. However, effectively and computationally efficiently incorporating syntactic structu…
Probing Linguistic Systematicity
Emily Goodwin, Koustuv Sinha, Timothy J. O'Donnell
Recently, there has been much interest in the question of whether deep natural language understanding models exhibit systematicity; generalizing such that units like words make con…